2026
Journal article
Open Access
Associating physical function and capacity tests to free-living sensor data: a systematic review on technology and methods
Caramaschi Sara, Ghezzi Dario, Olsson Carl Magnus, Palumbo Filippo, Salvi Dario
Physical function and capacity tests are widely used for assessing health across various clinical conditions. However, traditional assessments may not accurately capture real-world health conditions reliably and frequently. Sensors, smartphones and wearable devices offer the potential to bridge this gap by collecting data in everyday life that may better reflect participants’ physical capabilities, and could be used to predict clinical outcomes and the performance of physical tests. However, there is a lack of comprehensive reviews and consensus in the field. This work reviews the literature on passively collected data from digital health technology in relation to physical function and capacity tests and informs future investigations in this domain. A systematic literature search was conducted following the PRISMA guidelines on 3 databases. Our analysis identifies cardiovascular and neurodegenerative diseases as the most frequently studied conditions, and wearables embedding inertial sensors as the most common device type. Most studies rely on one week-long data collection. Associations between physical test outcomes and metrics such as step count and activity intensity show correlations as high as 0.89 when machine learning is introduced. This review provides a comprehensive summary of current research on the use of digital health technology in free-living conditions and the clinical significance of data when associated with physical tests.Source: ACM TRANSACTIONS ON COMPUTING FOR HEALTHCARE, vol. 7 (issue 2)
DOI: 10.1145/3797893
Project(s): ’Conseguenze e sfide dell’invecchiamento,’ Project Age-IT
Metrics:
Caramaschi Sara, Ghezzi Dario, Olsson Carl Magnus, Palumbo Filippo, Salvi Dario
Physical function and capacity tests are widely used for assessing health across various clinical conditions. However, traditional assessments may not accurately capture real-world health conditions reliably and frequently. Sensors, smartphones and wearable devices offer the potential to bridge this gap by collecting data in everyday life that may better reflect participants’ physical capabilities, and could be used to predict clinical outcomes and the performance of physical tests. However, there is a lack of comprehensive reviews and consensus in the field. This work reviews the literature on passively collected data from digital health technology in relation to physical function and capacity tests and informs future investigations in this domain. A systematic literature search was conducted following the PRISMA guidelines on 3 databases. Our analysis identifies cardiovascular and neurodegenerative diseases as the most frequently studied conditions, and wearables embedding inertial sensors as the most common device type. Most studies rely on one week-long data collection. Associations between physical test outcomes and metrics such as step count and activity intensity show correlations as high as 0.89 when machine learning is introduced. This review provides a comprehensive summary of current research on the use of digital health technology in free-living conditions and the clinical significance of data when associated with physical tests.Source: ACM TRANSACTIONS ON COMPUTING FOR HEALTHCARE, vol. 7 (issue 2)
DOI: 10.1145/3797893
Project(s): ’Conseguenze e sfide dell’invecchiamento,’ Project Age-IT
Metrics:
See at:
dl.acm.org 
| CNR IRIS | CNR IRIS 
| CNR IRIS
2025
Conference article
Open Access
A protocol for balance and mobility training via sensorized movement analysis
Ghezzi D., Palumbo F.
Movement analysis is crucial for assessing physical and functional capacity in both well-being and sports. Clinical tests like the 30-Second Chair Stand Test (30CST) and the Timed Up and Go (TUG) test are commonly used for lower limb assessment. However, these tests don’t fully capture proprioception, coordination, strength, endurance, and flexibility—factors strongly linked to independence, longevity, and quality of life. The protocol for balance and mobility training created within the framework of the Tuscany Health Ecosystem utilizes sensor technologies and signal processing to analyze data from fitness-related movements. We developed the Squat Test (SQT) and Single Leg Deadlift Test (SLDLT), functional movements mimicking daily activities. This study investigates the impact of visual feedback on physical abilities. One group performs the tests while observing their balance on a monitor displaying foot pressure data from a sensorized mat as visual feedback. Another group performs the tests without this visual feedback. We hypothesize that while visual feedback may initially improve movement scores, it might create a dependency, hindering the development of true proprioceptive awareness and balance improvement; conversely, it can ease the learning of the necessary neuromuscular capabilities to improve the execution of the tests. The final comparison of the results will explain if visual feedback is relevant for motor learning improvement.DOI: 10.23919/splitech65624.2025.11091770
Metrics:
Ghezzi D., Palumbo F.
Movement analysis is crucial for assessing physical and functional capacity in both well-being and sports. Clinical tests like the 30-Second Chair Stand Test (30CST) and the Timed Up and Go (TUG) test are commonly used for lower limb assessment. However, these tests don’t fully capture proprioception, coordination, strength, endurance, and flexibility—factors strongly linked to independence, longevity, and quality of life. The protocol for balance and mobility training created within the framework of the Tuscany Health Ecosystem utilizes sensor technologies and signal processing to analyze data from fitness-related movements. We developed the Squat Test (SQT) and Single Leg Deadlift Test (SLDLT), functional movements mimicking daily activities. This study investigates the impact of visual feedback on physical abilities. One group performs the tests while observing their balance on a monitor displaying foot pressure data from a sensorized mat as visual feedback. Another group performs the tests without this visual feedback. We hypothesize that while visual feedback may initially improve movement scores, it might create a dependency, hindering the development of true proprioceptive awareness and balance improvement; conversely, it can ease the learning of the necessary neuromuscular capabilities to improve the execution of the tests. The final comparison of the results will explain if visual feedback is relevant for motor learning improvement.DOI: 10.23919/splitech65624.2025.11091770
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | CNR IRIS | CNR IRIS
2025
Conference article
Open Access
Reliable and repeatable smartphone based Timed Up and Go Test using inertial sensors
Salvi D., Olsson C. M., Caramaschi S., Palumbo F.
The Timed Up and Go (TUG) test is a widely used clinical assessment for mobility, balance, and fall risk. Traditional TUG tests rely on manual timing, which can introduce unwanted subjectivity and variability. Smartphones, with their embedded inertial sensors, offer a promising alternative for automated, objective, and remote TUG assessment. This paper presents a novel algorithm for computing TUG test duration from inertial data collected using smartphones, which makes use of the acceleration and the orientation signals produced by smartphones. The algorithm was assessed using data from a study involving 33 participants. Our results demonstrate high agreement between the computed TUG times and those measured by a reference device (maximum absolute LoA=2.9s). This has relevance for conditions such as Parkinson’s disease, frailty, and cardiac patient monitoring.DOI: 10.1109/wf-iot64238.2025.11270660
Project(s): European Union - Next Generation EU, in the context of The National Recovery and Resilience Plan, Investment 1.5 Ecosystems of Innovation, Project Tuscany Health Ecosystem (THE), CUP: B83C22003930001
Metrics:
Salvi D., Olsson C. M., Caramaschi S., Palumbo F.
The Timed Up and Go (TUG) test is a widely used clinical assessment for mobility, balance, and fall risk. Traditional TUG tests rely on manual timing, which can introduce unwanted subjectivity and variability. Smartphones, with their embedded inertial sensors, offer a promising alternative for automated, objective, and remote TUG assessment. This paper presents a novel algorithm for computing TUG test duration from inertial data collected using smartphones, which makes use of the acceleration and the orientation signals produced by smartphones. The algorithm was assessed using data from a study involving 33 participants. Our results demonstrate high agreement between the computed TUG times and those measured by a reference device (maximum absolute LoA=2.9s). This has relevance for conditions such as Parkinson’s disease, frailty, and cardiac patient monitoring.DOI: 10.1109/wf-iot64238.2025.11270660
Project(s): European Union - Next Generation EU, in the context of The National Recovery and Resilience Plan, Investment 1.5 Ecosystems of Innovation, Project Tuscany Health Ecosystem (THE), CUP: B83C22003930001
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | CNR IRIS | CNR IRIS
2025
Conference article
Open Access
Multisensor setup for functional capacity testing: the Malisa Dataset
Salvi D, Magnus Olsson C., Lamrani Laghrib H., Merle K., Pothier Noa, Yildirim S., La Rosa D., Palumbo F.
Functional capacity testing is essential for assessing mobility changes, which can impact independence across various populations and health conditions. This study aims to implement instrumented function tests using a combination of affordable sensors, including sensorized mats, sensorized shoes, smartphones, and smartwatches. The goal is to provide objective, reliable, and detailed data on test outcomes, such as gait analysis. We have created a dataset from 6 participants of varying ages, each performing 5 standardized functional tests: Timed Up and Go, 30-Second Chair Rise, Locomo challenge, 10-meter walk, and 40-meter walk. Alongside the dataset, we have developed a tool for visualizing the sensor signals and marking key events to facilitate data analysis. This dataset is intended to support researchers in developing algorithms for extracting test-specific parameters, and for comparing sensors in terms of quality of the signals and ease of setup.Source: LECTURE NOTES OF THE INSTITUTE FOR COMPUTER SCIENCES, SOCIAL INFORMATICS AND TELECOMMUNICATIONS ENGINEERING (INTERNET), vol. 612, pp. 170-178. Heraklion, Crete, Greece, 17-18/09/2024
DOI: 10.1007/978-3-031-85575-7_10
DOI: https://doi.org/10.1007/978-3-031-85575-7_10
Metrics:
Salvi D, Magnus Olsson C., Lamrani Laghrib H., Merle K., Pothier Noa, Yildirim S., La Rosa D., Palumbo F.
Functional capacity testing is essential for assessing mobility changes, which can impact independence across various populations and health conditions. This study aims to implement instrumented function tests using a combination of affordable sensors, including sensorized mats, sensorized shoes, smartphones, and smartwatches. The goal is to provide objective, reliable, and detailed data on test outcomes, such as gait analysis. We have created a dataset from 6 participants of varying ages, each performing 5 standardized functional tests: Timed Up and Go, 30-Second Chair Rise, Locomo challenge, 10-meter walk, and 40-meter walk. Alongside the dataset, we have developed a tool for visualizing the sensor signals and marking key events to facilitate data analysis. This dataset is intended to support researchers in developing algorithms for extracting test-specific parameters, and for comparing sensors in terms of quality of the signals and ease of setup.Source: LECTURE NOTES OF THE INSTITUTE FOR COMPUTER SCIENCES, SOCIAL INFORMATICS AND TELECOMMUNICATIONS ENGINEERING (INTERNET), vol. 612, pp. 170-178. Heraklion, Crete, Greece, 17-18/09/2024
DOI: 10.1007/978-3-031-85575-7_10
DOI: https://doi.org/10.1007/978-3-031-85575-7_10
Metrics:
2025
Conference article
Open Access
Objective characterization of timed up and go test via sensorized mats
Eriksson H., Ramkull M., Salvi D., Magnus Olsson C., Ghezzi D., La Rosa D., Palumbo F.
The Timed Up and Go (TUG) test is a widely recognized and standardized mobility test to measure basic mobility and balance capabilities. Despite the possibility to derive rich information about the patient, only the total time to complete the test is conventionally measured by a professional. This work examines the use of non-wearable sensors for the measurement of parameters of the test in an accurate and objective way. The study illustrates a system specifically designed for conducting the TUG test using a set of sensorized mats. The developed system is able to identify the following 4 phases of the test, with relative timestamps: TUG-time, Sit-to-Stand, Mid-Turning, and End-Turning-Stand-to-Sit. Additionally, meaningful parameters for gait assessment are also extracted: walking speed and stride length. Two experimental iterations were conducted to assess the reliability of the developed software. Both iterations involved two different groups of six healthy participants (41.58 ± 13.32 yrs; 6 females, 6 males) performing various walking types. Our results demonstrate that sensorized mats can be used to segment the phases of the test reliably and can additionally be used to quantify gait parameters during the walk phase of the test.Source: LECTURE NOTES OF THE INSTITUTE FOR COMPUTER SCIENCES, SOCIAL INFORMATICS AND TELECOMMUNICATIONS ENGINEERING, vol. 612, pp. 179-189. Heraklion, Crete, Greece, 17-18/09/2024
DOI: 10.1007/978-3-031-85575-7_11
DOI: https://doi.org/10.1007/978-3-031-85575-7_11
Metrics:
Eriksson H., Ramkull M., Salvi D., Magnus Olsson C., Ghezzi D., La Rosa D., Palumbo F.
The Timed Up and Go (TUG) test is a widely recognized and standardized mobility test to measure basic mobility and balance capabilities. Despite the possibility to derive rich information about the patient, only the total time to complete the test is conventionally measured by a professional. This work examines the use of non-wearable sensors for the measurement of parameters of the test in an accurate and objective way. The study illustrates a system specifically designed for conducting the TUG test using a set of sensorized mats. The developed system is able to identify the following 4 phases of the test, with relative timestamps: TUG-time, Sit-to-Stand, Mid-Turning, and End-Turning-Stand-to-Sit. Additionally, meaningful parameters for gait assessment are also extracted: walking speed and stride length. Two experimental iterations were conducted to assess the reliability of the developed software. Both iterations involved two different groups of six healthy participants (41.58 ± 13.32 yrs; 6 females, 6 males) performing various walking types. Our results demonstrate that sensorized mats can be used to segment the phases of the test reliably and can additionally be used to quantify gait parameters during the walk phase of the test.Source: LECTURE NOTES OF THE INSTITUTE FOR COMPUTER SCIENCES, SOCIAL INFORMATICS AND TELECOMMUNICATIONS ENGINEERING, vol. 612, pp. 179-189. Heraklion, Crete, Greece, 17-18/09/2024
DOI: 10.1007/978-3-031-85575-7_11
DOI: https://doi.org/10.1007/978-3-031-85575-7_11
Metrics:
2025
Journal article
Open Access
StepLogger and EvaalScore: the software suite of the IPIN onsite indoor localization competition
Girolami M., Baronti P., Potortì F., Crivello A., Palumbo F.
This paper illustrates the software suite developed for Track 1 of the IPIN competition, which evaluates smartphone apps for indoor localization. Competitors have one day before the trial day to survey the competition area. On the trial day, an independent “actor” carries the competing system on smartphone and walks a predefined path. Competing systems provide continuous location estimates, which are later compared to a ground truth. We describe the software suite used to gather and present the results: the StepLogger Android application for real-time logging of position estimates and the EvaalScore tool for performance evaluation. StepLogger collects location estimating data from competitors with a timestamp, while EvaalScore calculates the accuracy of the competing systems. The competition ranking is based on the third quartile of point localization error. The presented software suite ensures a standardized and fair assessment of competing systems, thus promoting reproducibility and transparency in indoor localization research.Source: SOFTWAREX, vol. 30
DOI: 10.1016/j.softx.2025.102115
Project(s): Age-IT
Metrics:
Girolami M., Baronti P., Potortì F., Crivello A., Palumbo F.
This paper illustrates the software suite developed for Track 1 of the IPIN competition, which evaluates smartphone apps for indoor localization. Competitors have one day before the trial day to survey the competition area. On the trial day, an independent “actor” carries the competing system on smartphone and walks a predefined path. Competing systems provide continuous location estimates, which are later compared to a ground truth. We describe the software suite used to gather and present the results: the StepLogger Android application for real-time logging of position estimates and the EvaalScore tool for performance evaluation. StepLogger collects location estimating data from competitors with a timestamp, while EvaalScore calculates the accuracy of the competing systems. The competition ranking is based on the third quartile of point localization error. The presented software suite ensures a standardized and fair assessment of competing systems, thus promoting reproducibility and transparency in indoor localization research.Source: SOFTWAREX, vol. 30
DOI: 10.1016/j.softx.2025.102115
Project(s): Age-IT
Metrics:
See at:
CNR IRIS | www.sciencedirect.com | CNR IRIS | CNR IRIS
2025
Conference article
Open Access
Performing audiometry using pupillometry: state-of-the-market and sensor selection
Crivello A., La Rosa D., Belli D., Milazzo M., Palumbo F.
Hearing impairment poses a significant global health challenge, impacting millions of individuals across all age groups. Early detection and intervention are paramount, especially in infants and young children, to mitigate the adverse effects on speech, language, and cognitive development. Traditional audiometry methods, however, rely on subjective patient responses, rendering them unsuitable for non-collaborative individuals such as infants, newborns, and those with cognitive impairments. To address this limitation, the APURE (Audiometry with PUpil REsponse) project seeks to develop an objective audiometer leveraging pupillometry, the measurement of pupil size and reactivity. This paper presents a comprehensive state-of-the-market survey of eye-tracking systems, a crucial step in identifying the most suitable sensors for the APURE project.Source: LECTURE NOTES OF THE INSTITUTE FOR COMPUTER SCIENCES, SOCIAL INFORMATICS AND TELECOMMUNICATIONS ENGINEERING, vol. 612, pp. 159-169. Heraklion, Crete, Greece, 17–18/09/2024
DOI: 10.1007/978-3-031-85575-7_9
Metrics:
Crivello A., La Rosa D., Belli D., Milazzo M., Palumbo F.
Hearing impairment poses a significant global health challenge, impacting millions of individuals across all age groups. Early detection and intervention are paramount, especially in infants and young children, to mitigate the adverse effects on speech, language, and cognitive development. Traditional audiometry methods, however, rely on subjective patient responses, rendering them unsuitable for non-collaborative individuals such as infants, newborns, and those with cognitive impairments. To address this limitation, the APURE (Audiometry with PUpil REsponse) project seeks to develop an objective audiometer leveraging pupillometry, the measurement of pupil size and reactivity. This paper presents a comprehensive state-of-the-market survey of eye-tracking systems, a crucial step in identifying the most suitable sensors for the APURE project.Source: LECTURE NOTES OF THE INSTITUTE FOR COMPUTER SCIENCES, SOCIAL INFORMATICS AND TELECOMMUNICATIONS ENGINEERING, vol. 612, pp. 159-169. Heraklion, Crete, Greece, 17–18/09/2024
DOI: 10.1007/978-3-031-85575-7_9
Metrics:
See at:
CNR IRIS | link.springer.com | CNR IRIS | CNR IRIS
2025
Conference article
Open Access
Automated Timed Up and Go test segmentation via pose detection
Algilani A. S., Aguilar S. V., Salvi D., Palumbo F.
The Timed Up and Go test is commonly used for assessing gait, balance and function in people with limited mobility or low functional mobility. The test consists in measuring the time it takes for a subject to stand up, walk 3 meters, come back and sit down. Computer vision and pose estimation allows measuring the subject's performance more reliably than a human observer and to extract additional parameters that are potentially more sensitive for the assessment of symptoms than the total duration. We show an algorithmic approach for multi-camera settings and present accuracy results obtained in a pilot study with 13 older adults, establishing the methodology for larger studies.DOI: 10.1109/metroxraine66377.2025.11340128
Project(s): Tuscany Health Ecosystem
Metrics:
Algilani A. S., Aguilar S. V., Salvi D., Palumbo F.
The Timed Up and Go test is commonly used for assessing gait, balance and function in people with limited mobility or low functional mobility. The test consists in measuring the time it takes for a subject to stand up, walk 3 meters, come back and sit down. Computer vision and pose estimation allows measuring the subject's performance more reliably than a human observer and to extract additional parameters that are potentially more sensitive for the assessment of symptoms than the total duration. We show an algorithmic approach for multi-camera settings and present accuracy results obtained in a pilot study with 13 older adults, establishing the methodology for larger studies.DOI: 10.1109/metroxraine66377.2025.11340128
Project(s): Tuscany Health Ecosystem
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | CNR IRIS | CNR IRIS
2024
Conference article
Open Access
A novel architectural schema for constant monitoring and assessment of older adults’ health status at home
Barsocchi P., Belli D., Gabrielli E., La Rosa D., Miori V., Palumbo F., Russo D., Tolomei G.
In recent years the demand for health care among older adults, along with requests for hospitalization and related costs, has increased at an unprecedented rate. In the coming decades, this trend is likely to worsen. This detrimental tendency can be mitigated by addressing the problem with a proactive approach. The goal is to ensure continuous monitoring of the older’s health status to promptly detect worsening and disease onsets. The paper extends the mid-term results of the Project ChAALenge, by detailing the sensors and the framework underlying the high-level predictive techniques, as well as by reporting qualitative results in terms of physiological measurements from a 4-month data collection campaign in a nursing home.Source: LECTURE NOTES OF THE INSTITUTE FOR COMPUTER SCIENCES, SOCIAL INFORMATICS AND TELECOMMUNICATIONS ENGINEERING, vol. 572, pp. 501-511. Malmö, Sweden, 27-29/11/2023
DOI: 10.1007/978-3-031-59717-6_33
Metrics:
Barsocchi P., Belli D., Gabrielli E., La Rosa D., Miori V., Palumbo F., Russo D., Tolomei G.
In recent years the demand for health care among older adults, along with requests for hospitalization and related costs, has increased at an unprecedented rate. In the coming decades, this trend is likely to worsen. This detrimental tendency can be mitigated by addressing the problem with a proactive approach. The goal is to ensure continuous monitoring of the older’s health status to promptly detect worsening and disease onsets. The paper extends the mid-term results of the Project ChAALenge, by detailing the sensors and the framework underlying the high-level predictive techniques, as well as by reporting qualitative results in terms of physiological measurements from a 4-month data collection campaign in a nursing home.Source: LECTURE NOTES OF THE INSTITUTE FOR COMPUTER SCIENCES, SOCIAL INFORMATICS AND TELECOMMUNICATIONS ENGINEERING, vol. 572, pp. 501-511. Malmö, Sweden, 27-29/11/2023
DOI: 10.1007/978-3-031-59717-6_33
Metrics:
See at:
CNR IRIS | link.springer.com | doi.org | Archivio della ricerca- Università di Roma La Sapienza | CNR IRIS | CNR IRIS
2024
Conference article
Open Access
Design of postural analysis and indoor localization services in AAL scenarios
Barsocchi P., Girolami M., Palumbo F.
Advancements in Ambient Assisted Living (AAL) technology have enabled innovative solutions to enhance the quality of life for older adults. The AA@THE project focuses on personalized coaching and monitoring systems to prevent risky conditions and promote healthy ageing. Two crucial domains, sedentariness and stability, are addressed through advanced technologies such as proximity detection and postural analysis services. By analyzing these specific health and behavioural aspects, personalized feedback is provided to improve overall well-being.Source: LECTURE NOTES IN BIOENGINEERING, pp. 157-160. Bari, Italy, 14-16/06/2023
DOI: 10.1007/978-3-031-63913-5_14
Project(s): Tuscany Health Ecosystem
Metrics:
Barsocchi P., Girolami M., Palumbo F.
Advancements in Ambient Assisted Living (AAL) technology have enabled innovative solutions to enhance the quality of life for older adults. The AA@THE project focuses on personalized coaching and monitoring systems to prevent risky conditions and promote healthy ageing. Two crucial domains, sedentariness and stability, are addressed through advanced technologies such as proximity detection and postural analysis services. By analyzing these specific health and behavioural aspects, personalized feedback is provided to improve overall well-being.Source: LECTURE NOTES IN BIOENGINEERING, pp. 157-160. Bari, Italy, 14-16/06/2023
DOI: 10.1007/978-3-031-63913-5_14
Project(s): Tuscany Health Ecosystem
Metrics:
See at:
CNR IRIS | link.springer.com | doi.org | CNR IRIS | CNR IRIS
2024
Contribution to journal
Open Access
3P Evaluating conversational generative pre-trained transformer (ChatGPT) as a tool in early breast cancer (eBC) cases
Patanè F., Palumbo F., Lorenzini G., Bargagna I., Cinacchi P., Albanese I., Bilancio D., Pantaleo F., Acconci G., Bianchini G., Baldacci E., La Commare M., Fratini B., Fontana A.
Background ChatGPT is a web interface chatbot based on a large language model with the aim to mimic human conversation tuned with machine learning and supervised techniques, that have gained scientific attention wondering if it can be a tool in medical decision. Methods We tasked ChatGPT 4.0 with creating a multidisciplinary team (MDT) chat and provided it with clinical data from patients (pts) diagnosed with hormone receptor (HR)-positive, human epidermal growth factor receptor 2-negative eBC with an intermediate clinico-pathological risk. These pts were candidates for the Oncotype DX® genomic test. Our goal was to compare our MDT recommendations with those generated by ChatGPT’s and assess the consistency of its responses. Results We gathered data from 100 consecutive pts: median age 57, evenly split between stages I and II, 35 premenopausal. By supplying clinical details (age, stage, menopausal status, HR expression, grading, ki67, comorbidity), we asked ChatGPT to assess the need for Oncotype DX®. Each case was presented 9 times in varied chats to test repeatability, yielding a modal vector with a mean variation ratio of 0.181. Only in 31 pts it always recommended a genomic test. Summarizing ChatGPT's most frequent advices for each patient, it recommended genomic test for 61 pts. Next, we provided Recurrence Scores of the 61 pts, asking for chemotherapy (CT) recommendations. The mean variation ratio in responses was 0.069. The Cohen's kappa coefficient for inter-rater agreement between ChatGPT's and actual CT recommendations was 0.62. ChatGPT did not consider clinical risk but only menopausal status for endocrine therapy: tamoxifen if premenopausal, aromatase inhibitor if postmenopausal. When asked for concurrent CT and genomic test advice, its responses were inconsistent, offering CT for almost all pts regardless of genomic testing recommendation. Conclusions ChatGPT is a generative model capable of producing data that attempts to capture the statistical distribution of its training dataset, but without reasoning abilities. Its low repeatability, along with suboptimal inter-rater agreement, mean it cannot yet replace an MDT. Effective clinical integration requires identifying areas where ChatGPT's knowledge is beneficial.Source: ESMO OPEN, vol. 9 (issue Supplement 1)
DOI: 10.1016/j.esmoop.2024.102258
Metrics:
Patanè F., Palumbo F., Lorenzini G., Bargagna I., Cinacchi P., Albanese I., Bilancio D., Pantaleo F., Acconci G., Bianchini G., Baldacci E., La Commare M., Fratini B., Fontana A.
Background ChatGPT is a web interface chatbot based on a large language model with the aim to mimic human conversation tuned with machine learning and supervised techniques, that have gained scientific attention wondering if it can be a tool in medical decision. Methods We tasked ChatGPT 4.0 with creating a multidisciplinary team (MDT) chat and provided it with clinical data from patients (pts) diagnosed with hormone receptor (HR)-positive, human epidermal growth factor receptor 2-negative eBC with an intermediate clinico-pathological risk. These pts were candidates for the Oncotype DX® genomic test. Our goal was to compare our MDT recommendations with those generated by ChatGPT’s and assess the consistency of its responses. Results We gathered data from 100 consecutive pts: median age 57, evenly split between stages I and II, 35 premenopausal. By supplying clinical details (age, stage, menopausal status, HR expression, grading, ki67, comorbidity), we asked ChatGPT to assess the need for Oncotype DX®. Each case was presented 9 times in varied chats to test repeatability, yielding a modal vector with a mean variation ratio of 0.181. Only in 31 pts it always recommended a genomic test. Summarizing ChatGPT's most frequent advices for each patient, it recommended genomic test for 61 pts. Next, we provided Recurrence Scores of the 61 pts, asking for chemotherapy (CT) recommendations. The mean variation ratio in responses was 0.069. The Cohen's kappa coefficient for inter-rater agreement between ChatGPT's and actual CT recommendations was 0.62. ChatGPT did not consider clinical risk but only menopausal status for endocrine therapy: tamoxifen if premenopausal, aromatase inhibitor if postmenopausal. When asked for concurrent CT and genomic test advice, its responses were inconsistent, offering CT for almost all pts regardless of genomic testing recommendation. Conclusions ChatGPT is a generative model capable of producing data that attempts to capture the statistical distribution of its training dataset, but without reasoning abilities. Its low repeatability, along with suboptimal inter-rater agreement, mean it cannot yet replace an MDT. Effective clinical integration requires identifying areas where ChatGPT's knowledge is beneficial.Source: ESMO OPEN, vol. 9 (issue Supplement 1)
DOI: 10.1016/j.esmoop.2024.102258
Metrics:
See at:
ESMO Open | CNR IRIS | www.esmoopen.com | IRIS Cnr | IRIS Cnr | CNR IRIS
2023
Other
Restricted
THE D.3.2.1 - AA@THE User needs, technical requirements and specifications
Pratali L, Campana M G, Delmastro F, Di Martino F, Pescosolido L, Barsocchi P, Broccia G, Ciancia V, Gennaro C, Girolami M, Lagani G, La Rosa D, Latella D, Magrini M, Manca M, Massink M, Mattioli A, Moroni D, Palumbo F, Paradisi P, Paternò F, Santoro C, Sebastiani L, Vairo C
Deliverable D3.2.1 del progetto PNRR Ecosistemi ed innovazione - THE
Pratali L, Campana M G, Delmastro F, Di Martino F, Pescosolido L, Barsocchi P, Broccia G, Ciancia V, Gennaro C, Girolami M, Lagani G, La Rosa D, Latella D, Magrini M, Manca M, Massink M, Mattioli A, Moroni D, Palumbo F, Paradisi P, Paternò F, Santoro C, Sebastiani L, Vairo C
Deliverable D3.2.1 del progetto PNRR Ecosistemi ed innovazione - THE
2023
Conference article
Open Access
IoT smart shoe solution for neuromuscular disease monitoring
La Rosa D, Palumbo F, Ronca A, Sansone F, Tesconi M, Tonacci A, Conte R
Recent advances in sensing, processing, and learning of physiological parameters, make the development of non-invasive health monitoring systems increasingly effective, especially in those situations that need particular attention to the usability of devices and software solutions due to the frailty of the target population. In this context, we developed a sensorized shoe that detects significant features in subjects' gait and monitors variations related to an intervention protocol in people affected by Neuromuscular Disorders (NMDs). This paper outlines the challenges in the field and summarizes the approach used to overcome the technological barriers related to connectivity, deployment, and usability that are typical in a medical setting. The proposed solution adopts the new paradigm offered by Web Bluetooth based on Bluetooth WebSocket. We show the architectural and deployment choices and how this solution can be easily adapted to different devices and scenarios.Source: LECTURE NOTES OF THE INSTITUTE FOR COMPUTER SCIENCES, SOCIAL INFORMATICS AND TELECOMMUNICATIONS ENGINEERING (INTERNET), pp. 104-115. Thessaloniki, Greece, 12-14/12/2022
DOI: 10.1007/978-3-031-34586-9_8
Metrics:
La Rosa D, Palumbo F, Ronca A, Sansone F, Tesconi M, Tonacci A, Conte R
Recent advances in sensing, processing, and learning of physiological parameters, make the development of non-invasive health monitoring systems increasingly effective, especially in those situations that need particular attention to the usability of devices and software solutions due to the frailty of the target population. In this context, we developed a sensorized shoe that detects significant features in subjects' gait and monitors variations related to an intervention protocol in people affected by Neuromuscular Disorders (NMDs). This paper outlines the challenges in the field and summarizes the approach used to overcome the technological barriers related to connectivity, deployment, and usability that are typical in a medical setting. The proposed solution adopts the new paradigm offered by Web Bluetooth based on Bluetooth WebSocket. We show the architectural and deployment choices and how this solution can be easily adapted to different devices and scenarios.Source: LECTURE NOTES OF THE INSTITUTE FOR COMPUTER SCIENCES, SOCIAL INFORMATICS AND TELECOMMUNICATIONS ENGINEERING (INTERNET), pp. 104-115. Thessaloniki, Greece, 12-14/12/2022
DOI: 10.1007/978-3-031-34586-9_8
Metrics:
See at:
CNR IRIS | link.springer.com | ISTI Repository | CNR IRIS | CNR IRIS
2023
Journal article
Open Access
Enerduino-pro: smart meter led probe using Arduino
Potortì F., La Rosa D., Palumbo F.
Non-intrusive load monitoring of domestic appliances has received steady interest in the last twenty years, first because of interest from energy companies interested in usage statistics for power balancing and, more recently, in order to assist users in tuning their habits for reduced power consumption. This has increased the need for accurate and economic methods of power measurement that can be efficiently implemented on cheap and easy-to-install platforms. To this end, we present a cheap and efficient device based on Arduino to monitor the usage of domestic appliances in real-time: Enerduino-pro. The design uses low-cost easy-to-assemble open-source electronic components and consists of four main parts: an Arduino UNO microcontroller, one photoresistor to measure instantaneous power absorption plus one optional additional one to measure reactive power, a WiFi shield, and an LED (for debugging purposes only). We describe the device, complete with open software and hardware specifications, and different use cases with proof-of-concept solutions.Source: HARDWAREX, vol. 15
DOI: 10.1016/j.ohx.2023.e00461
Metrics:
Potortì F., La Rosa D., Palumbo F.
Non-intrusive load monitoring of domestic appliances has received steady interest in the last twenty years, first because of interest from energy companies interested in usage statistics for power balancing and, more recently, in order to assist users in tuning their habits for reduced power consumption. This has increased the need for accurate and economic methods of power measurement that can be efficiently implemented on cheap and easy-to-install platforms. To this end, we present a cheap and efficient device based on Arduino to monitor the usage of domestic appliances in real-time: Enerduino-pro. The design uses low-cost easy-to-assemble open-source electronic components and consists of four main parts: an Arduino UNO microcontroller, one photoresistor to measure instantaneous power absorption plus one optional additional one to measure reactive power, a WiFi shield, and an LED (for debugging purposes only). We describe the device, complete with open software and hardware specifications, and different use cases with proof-of-concept solutions.Source: HARDWAREX, vol. 15
DOI: 10.1016/j.ohx.2023.e00461
Metrics:
See at:
CNR IRIS | ISTI Repository | www.sciencedirect.com | CNR IRIS
2023
Journal article
Open Access
Connectivity standards alliance matter: state of the art and opportunities
Belli D, Barsocchi P, Palumbo F
Matter is an open-source, royalty-free connectivity standard developed by the Connectivity Standards Alliance (CSA-IoT). It aims to unify smart home devices and increase their compatibility across various ecosystems. Backed by major tech companies like Apple, Google, Amazon, and the Zigbee Alliance, Matter simplifies the development of IoT devices by providing a unified approach to connectivity. It offers a secure, reliable, and seamless way for devices to communicate and interact, regardless of the manufacturer.This paper aims to present the current state of adoption of the Matter specification by devices available on the market, and the certification process by the available software. It describes the main characteristics of Matter in its Specification 1.0 state, reviewing the features and functionalities of the Matter protocol, as well as the opportunities for its use and the challenges for its large-scale adoption in Matter-compliant IoT devices.We discuss the impact of Matter on IoT technologies and ecosystems, providing guidance for manufacturers and consumers. We analyze the emerging research challenges in its adoption and propose our recommendations on how to improve and extend this protocol for better use in the future.Source: INTERNET OF THINGS, vol. 25
DOI: 10.1016/j.iot.2023.101005
Metrics:
Belli D, Barsocchi P, Palumbo F
Matter is an open-source, royalty-free connectivity standard developed by the Connectivity Standards Alliance (CSA-IoT). It aims to unify smart home devices and increase their compatibility across various ecosystems. Backed by major tech companies like Apple, Google, Amazon, and the Zigbee Alliance, Matter simplifies the development of IoT devices by providing a unified approach to connectivity. It offers a secure, reliable, and seamless way for devices to communicate and interact, regardless of the manufacturer.This paper aims to present the current state of adoption of the Matter specification by devices available on the market, and the certification process by the available software. It describes the main characteristics of Matter in its Specification 1.0 state, reviewing the features and functionalities of the Matter protocol, as well as the opportunities for its use and the challenges for its large-scale adoption in Matter-compliant IoT devices.We discuss the impact of Matter on IoT technologies and ecosystems, providing guidance for manufacturers and consumers. We analyze the emerging research challenges in its adoption and propose our recommendations on how to improve and extend this protocol for better use in the future.Source: INTERNET OF THINGS, vol. 25
DOI: 10.1016/j.iot.2023.101005
Metrics:
See at:
CNR IRIS | ISTI Repository | www.sciencedirect.com | CNR IRIS
2023
Other
Restricted
ChAALenge D6.3 - Integrazione in laboratorio e analisi delle prestazioni
Bacco F. M., Baronti P., Barsocchi P., Belli D., Crivello A., Furfari F., Girolami M., La Rosa D., Mavilia F., Miori V., Palumbo F., Potortì F., Russo D.
Report di laboratorio di analisi dei risultati dell’integrazione e indagine prestazionale sul framework integrato contenente: (i) Risultati attinenti alla validità dei dati acquisiti dal framework, al fine del loro efficiente utilizzo da parte degli algoritmi sviluppati; (ii) Risultati riguardanti la correttezza, completezza e affidabilità dell’esito della sperimentazione sia in laboratorio sia sul campo e relativi alla valutazione prestazionale del software di sistema.Project(s): ChAALenge
Bacco F. M., Baronti P., Barsocchi P., Belli D., Crivello A., Furfari F., Girolami M., La Rosa D., Mavilia F., Miori V., Palumbo F., Potortì F., Russo D.
Report di laboratorio di analisi dei risultati dell’integrazione e indagine prestazionale sul framework integrato contenente: (i) Risultati attinenti alla validità dei dati acquisiti dal framework, al fine del loro efficiente utilizzo da parte degli algoritmi sviluppati; (ii) Risultati riguardanti la correttezza, completezza e affidabilità dell’esito della sperimentazione sia in laboratorio sia sul campo e relativi alla valutazione prestazionale del software di sistema.Project(s): ChAALenge
2023
Other
Open Access
D3.2.1: AA@THE User needs, technical requirements and specifications
Lorenza Pratali, Franca Delmastro, Mattia Campana, Flavio Di Martino, Loreto Pescosolido, Paolo Barsocchi, Giovanna Broccia, Vincenzo Ciancia, Claudio Gennaro, Michele Girolami, Gabriele Lagani, Diego Latella, Massimo Magrini, Marco Manca, Mieke Massink, Andrea Mattioli, Davide Moroni, Filippo Palumbo, Paolo Paradisi, Fabio Paternò, Laura Sebastiani, Claudio Vairo, Carmelina Santoro, Davide La Rosa
The objective of this deliverable is to compile a comprehensive report that describes the user needs, requirements, and technical specifications necessary to successfully implement the pilot study. To achieve this, it is crucial to establish contacts with specific associations and medical experts, which, collaboratively, will help to establish exclusion and inclusion criteria for the target population of healthy adults. Furthermore, another related objective is to define the different categories of users that will interact with the system and their specific needs. This holistic approach will ensure that the system is designed and developed to satisfy the diverse needs of the users and be aligned with the goals of the project. To achieve the milestone M3.2.1, we made significant progresses in the definition of the pilot study for the AA@THE subproject. One of our key achievements is the successful description of users’ needs, requirements, and technical specifications necessary for the study. We worked closely with both a specialized association of personal trainers for Adapted Physical Activity (APA) for older adults, already active in the area of Pisa, and the medical partner who played a crucial role in providing valuable insights and expertise to establish exclusion and inclusion criteria for the target population of healthy adults. In this milestone, we also defined the activities and services that we intend to offer. Specifically, we plan to provide technological systems aimed at monitoring physical and cognitive training processes, as well as stability evaluations, by instrumenting a gym dedicated to active and healthy ageing, which is located within the CNR research area in Pisa. Additionally, we will conduct sleep, nutrition, and sedentary assessments at the volunteers' homes. Furthermore, we successfully defined the different user categories involved in the study. To facilitate the recruitment process and people engagement, on January 17th 2023, we organized an open day in collaboration with the gym association where we presented the overall objectives of the project and we collected feedbacks from a group of healthy adults over 65, already involved in APA training. This allowed us to gain a comprehensive understanding of the users' specific needs in terms of system interactions, thus establishing the system requirements and technical specifications of the AA@THE ecosystem. In parallel, a specific action on “Automatic Support of Medical Image Analysis” has been initiated by members of the “Formal Methods and Tools” group at CNR-ISTI. Such an action aims at leveraging Formal Methods in Computer Science, Logic and Model Checking to augment state-of-the-art machine learning techniques for automatic medical image analysis, enabling end-users to make specific assumptions on the level of accountability and affordability of the system. The methodology is based on a strict intertwining between theory and experimentation, with the development of new theoretical foundations for model reduction and efficient model checking, and experimentation and finalization of a graphical user interface that is being evaluated from the points of view of usability and of cognitive load. Moreover, the design and implementation of a suitable GUI able to support the analysis of medical images has been conducted and tested with small groups of people derived from the hospital in Lucca. The proposed GUI prototype has been evaluated from a cognitive point of view in order to allow easy employment with little training, for general practitioners and caregivers who may lack the technical skills required to use fully-fledged medical imaging programs.Project(s): Tuscany Health Ecosystem
Lorenza Pratali, Franca Delmastro, Mattia Campana, Flavio Di Martino, Loreto Pescosolido, Paolo Barsocchi, Giovanna Broccia, Vincenzo Ciancia, Claudio Gennaro, Michele Girolami, Gabriele Lagani, Diego Latella, Massimo Magrini, Marco Manca, Mieke Massink, Andrea Mattioli, Davide Moroni, Filippo Palumbo, Paolo Paradisi, Fabio Paternò, Laura Sebastiani, Claudio Vairo, Carmelina Santoro, Davide La Rosa
The objective of this deliverable is to compile a comprehensive report that describes the user needs, requirements, and technical specifications necessary to successfully implement the pilot study. To achieve this, it is crucial to establish contacts with specific associations and medical experts, which, collaboratively, will help to establish exclusion and inclusion criteria for the target population of healthy adults. Furthermore, another related objective is to define the different categories of users that will interact with the system and their specific needs. This holistic approach will ensure that the system is designed and developed to satisfy the diverse needs of the users and be aligned with the goals of the project. To achieve the milestone M3.2.1, we made significant progresses in the definition of the pilot study for the AA@THE subproject. One of our key achievements is the successful description of users’ needs, requirements, and technical specifications necessary for the study. We worked closely with both a specialized association of personal trainers for Adapted Physical Activity (APA) for older adults, already active in the area of Pisa, and the medical partner who played a crucial role in providing valuable insights and expertise to establish exclusion and inclusion criteria for the target population of healthy adults. In this milestone, we also defined the activities and services that we intend to offer. Specifically, we plan to provide technological systems aimed at monitoring physical and cognitive training processes, as well as stability evaluations, by instrumenting a gym dedicated to active and healthy ageing, which is located within the CNR research area in Pisa. Additionally, we will conduct sleep, nutrition, and sedentary assessments at the volunteers' homes. Furthermore, we successfully defined the different user categories involved in the study. To facilitate the recruitment process and people engagement, on January 17th 2023, we organized an open day in collaboration with the gym association where we presented the overall objectives of the project and we collected feedbacks from a group of healthy adults over 65, already involved in APA training. This allowed us to gain a comprehensive understanding of the users' specific needs in terms of system interactions, thus establishing the system requirements and technical specifications of the AA@THE ecosystem. In parallel, a specific action on “Automatic Support of Medical Image Analysis” has been initiated by members of the “Formal Methods and Tools” group at CNR-ISTI. Such an action aims at leveraging Formal Methods in Computer Science, Logic and Model Checking to augment state-of-the-art machine learning techniques for automatic medical image analysis, enabling end-users to make specific assumptions on the level of accountability and affordability of the system. The methodology is based on a strict intertwining between theory and experimentation, with the development of new theoretical foundations for model reduction and efficient model checking, and experimentation and finalization of a graphical user interface that is being evaluated from the points of view of usability and of cognitive load. Moreover, the design and implementation of a suitable GUI able to support the analysis of medical images has been conducted and tested with small groups of people derived from the hospital in Lucca. The proposed GUI prototype has been evaluated from a cognitive point of view in order to allow easy employment with little training, for general practitioners and caregivers who may lack the technical skills required to use fully-fledged medical imaging programs.Project(s): Tuscany Health Ecosystem
2023
Conference article
Open Access
Intelligent environments for longevity and active aging. The role of technology solutions in revolutionizing healthcare
Palumbo F.
The rapid increase in the aging population has brought about the need for new solutions in healthcare. Intelligent environments offer a promising approach for promoting longevity and active aging through the use of technology solutions. In this paper, following the author's journey in the field, we explore the role of intelligent environments in revolutionizing healthcare, and we discuss their potential to enhance the quality of life for older adults. We also provide an overview of some of the key technological solutions that are being developed to support intelligent environments for longevity and active aging.Source: AMBIENT INTELLIGENCE AND SMART ENVIRONMENTS, vol. 32, pp. 176-185. Mauritius, 27-30/06/2023
DOI: 10.3233/aise230030
Metrics:
Palumbo F.
The rapid increase in the aging population has brought about the need for new solutions in healthcare. Intelligent environments offer a promising approach for promoting longevity and active aging through the use of technology solutions. In this paper, following the author's journey in the field, we explore the role of intelligent environments in revolutionizing healthcare, and we discuss their potential to enhance the quality of life for older adults. We also provide an overview of some of the key technological solutions that are being developed to support intelligent environments for longevity and active aging.Source: AMBIENT INTELLIGENCE AND SMART ENVIRONMENTS, vol. 32, pp. 176-185. Mauritius, 27-30/06/2023
DOI: 10.3233/aise230030
Metrics:
2022
Conference article
Open Access
Trends in smartphone-based indoor localisation
Potortì F., Crivello A., Palumbo F., Girolami M., Barsocchi P.
Indoor localisation is a thriving field, whose progresses are mainly led by innovations in sensor technology, both hardware and software. With a focus on smartphone-based personal navigation, we examine the evolution of sensing technologies in eleven leading applications. In order to select applications we choose among independently-tested prototypes, as opposed to simulation or laboratory-only experiments. To this end, we look at the best performers in the smartphone-based Tracks of IPIN competitions. This selection is particularly severe and significant, as this competition Track is performed live, without an opportunity for competitors to instrument or prepare the site or to know the path in advance and with only two attempts allowed, of which the best result is taken. An independent actor holds in hand the smartphone running the competing system, and results are downloaded from the phone immediately after the competition path is completed, without any post-processing. We show how sensing technologies have evolved from 2014 to 2019 and show a trend towards improving accuracy performance. Last, we provide insight in the role that sensors and algorithms play in the evolution of smartphone-based indoor localisation solutions.DOI: 10.1109/ipin51156.2021.9662530
Metrics:
Potortì F., Crivello A., Palumbo F., Girolami M., Barsocchi P.
Indoor localisation is a thriving field, whose progresses are mainly led by innovations in sensor technology, both hardware and software. With a focus on smartphone-based personal navigation, we examine the evolution of sensing technologies in eleven leading applications. In order to select applications we choose among independently-tested prototypes, as opposed to simulation or laboratory-only experiments. To this end, we look at the best performers in the smartphone-based Tracks of IPIN competitions. This selection is particularly severe and significant, as this competition Track is performed live, without an opportunity for competitors to instrument or prepare the site or to know the path in advance and with only two attempts allowed, of which the best result is taken. An independent actor holds in hand the smartphone running the competing system, and results are downloaded from the phone immediately after the competition path is completed, without any post-processing. We show how sensing technologies have evolved from 2014 to 2019 and show a trend towards improving accuracy performance. Last, we provide insight in the role that sensors and algorithms play in the evolution of smartphone-based indoor localisation solutions.DOI: 10.1109/ipin51156.2021.9662530
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | ISTI Repository | CNR IRIS | CNR IRIS
2022
Journal article
Open Access
The NESTORE e-coach: designing a multi-domain pathway to well-being in older age
Angelini L., El Kamali M., Mugellini E., Abou Khaled O., Roecke C., Porcelli S., Mastropietro A., Rizzo G., Boque N., Del Bas J. M., Palumbo F., Girolami M., Crivello A., Ziylan C., Subias-Beltran P., Orte S., Standoli C. E., Fernandez Maldonado L., Caon M., Sykora M., Elayan S., Guye S., Andreoni G.
This article describes the coaching strategies of the NESTORE e-coach, a virtual coach for promoting healthier lifestyles in older age. The novelty of the NESTORE project is the definition of a multi-domain personalized pathway where the e-coach accompanies the user throughout different structured and non-structured coaching activities and recommendations. The article also presents the design process of the coaching strategies, carried out including older adults from four European countries and experts from the different health domains, and the results of the tests carried out with 60 older adults in Italy, Spain and The Netherlands.Source: TECHNOLOGIES, vol. 10 (issue 2)
DOI: 10.3390/technologies10020050
Project(s): NESTORE
Metrics:
Angelini L., El Kamali M., Mugellini E., Abou Khaled O., Roecke C., Porcelli S., Mastropietro A., Rizzo G., Boque N., Del Bas J. M., Palumbo F., Girolami M., Crivello A., Ziylan C., Subias-Beltran P., Orte S., Standoli C. E., Fernandez Maldonado L., Caon M., Sykora M., Elayan S., Guye S., Andreoni G.
This article describes the coaching strategies of the NESTORE e-coach, a virtual coach for promoting healthier lifestyles in older age. The novelty of the NESTORE project is the definition of a multi-domain personalized pathway where the e-coach accompanies the user throughout different structured and non-structured coaching activities and recommendations. The article also presents the design process of the coaching strategies, carried out including older adults from four European countries and experts from the different health domains, and the results of the tests carried out with 60 older adults in Italy, Spain and The Netherlands.Source: TECHNOLOGIES, vol. 10 (issue 2)
DOI: 10.3390/technologies10020050
Project(s): NESTORE
Metrics:
See at:
CNR IRIS | ISTI Repository | www.mdpi.com | CNR IRIS