An interpretable machine learning tool for in-home monitoring of agitation episodes in people living with dementia: a proof-of-concept studyResearch in context
Summary: Background: Agitation affects around 30% of people living with dementia (PLwD), increasing carer burden and straining care services. Agitation identification typically relies on subjective clinical scales and direct patient observation, which are resource-intensive and challenging to incor...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | EClinicalMedicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589537024006114 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592824434950144 |
|---|---|
| author | Marirena Bafaloukou Ann-Kathrin Schalkamp Nan Fletcher-Lloyd Alex Capstick Chloe Walsh Cynthia Sandor Samaneh Kouchaki Ramin Nilforooshan Payam Barnaghi |
| author_facet | Marirena Bafaloukou Ann-Kathrin Schalkamp Nan Fletcher-Lloyd Alex Capstick Chloe Walsh Cynthia Sandor Samaneh Kouchaki Ramin Nilforooshan Payam Barnaghi |
| author_sort | Marirena Bafaloukou |
| collection | DOAJ |
| description | Summary: Background: Agitation affects around 30% of people living with dementia (PLwD), increasing carer burden and straining care services. Agitation identification typically relies on subjective clinical scales and direct patient observation, which are resource-intensive and challenging to incorporate into routine care. Clinical applicability of data-driven methods for agitation monitoring is limited by constraints such as short observational periods, data granularity, and lack of interpretability and generalisation. Current interventions for agitation are primarily medication-based, which may lead to severe side effects and lack personalisation. Understanding how real-world factors interact with agitation within home settings offers a promising avenue towards identifying potential personalised non-pharmacological interventions. Methods: We used longitudinal data (32,896 person-days from n = 63 PLwD) collected using in-home monitoring devices between December 2020 and March 2023. Employing machine learning techniques, we developed a monitoring tool to identify the presence of agitation during the week. We incorporated a traffic-light system to stratify agitation probability estimates supporting clinical decision-making, and employed the SHapley Additive exPlanations (SHAP) framework to enhance interpretability. We designed an interactive tool that enables the exploration of personalised non-pharmacological interventions, such as modifying ambient light and temperature. Findings: Light Gradient-boosting Machine (LightGBM) achieved the highest performance in identifying agitation over an 8-day period with a sensitivity of 71.32% ± 7.38 and specificity of 75.28% ± 7.38. Implementing the traffic-light system for stratification increased specificity to 90.3% ± 7.55 and improved all metrics. Key features for identifying agitation included low nocturnal respiratory rate, heightened alertness during sleep, and increased indoor illuminance, as revealed by statistical and feature importance analysis. Using our interactive tool, we identified indoor lighting and temperature adjustments as the most promising and feasible intervention options within our cohort. Interpretation: Our interpretable framework for agitation monitoring, developed using data from a dementia care study, showcases significant clinical value. The accompanying interactive interface allows for the in-silico simulation of non-pharmacological interventions, facilitating the design of personalised interventions that can improve in-home dementia care. Funding: This study is funded by the UK Dementia Research Institute [award number UK DRI-7002] through UK DRI Ltd, principally funded by the Medical Research Council (MRC), and the UKRI Engineering and Physical Sciences Research Council (EPSRC) PROTECT Project (grant number: EP/W031892/1). Infrastructure support for this research was provided by the NIHR Imperial Biomedical Research Centre (BRC) and the UKRI Medical Research Council (MRC). P.B. is also funded by the Great Ormond Street Hospital and the Royal Academy of Engineering. C.S. is supported by the UK Dementia Research Institute [award number UK DRI-5209], a UKRI Future Leaders Fellowship [MR/MR/X032892/1] and the Edmond J. Safra Foundation. R.N. is funded by UK Dementia Research Institute [award number UK DRI-7002] and the UKRI Engineering and Physical Sciences Research Council (EPSRC) PROTECT Project (grant number: EP/W031892/1). M.B. and A.K.S. are funded by the UK Dementia Research Institute [award number UKDRI-7002 and UKDRI-5209]. N.F.L., A.C., C.W. and S.K. are funded by the UK Dementia Research Institute [award number UK DRI-7002]. |
| format | Article |
| id | doaj-art-eaf3dbc9899f431d998fd9d36369739d |
| institution | Kabale University |
| issn | 2589-5370 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EClinicalMedicine |
| spelling | doaj-art-eaf3dbc9899f431d998fd9d36369739d2025-01-21T04:13:17ZengElsevierEClinicalMedicine2589-53702025-02-0180103032An interpretable machine learning tool for in-home monitoring of agitation episodes in people living with dementia: a proof-of-concept studyResearch in contextMarirena Bafaloukou0Ann-Kathrin Schalkamp1Nan Fletcher-Lloyd2Alex Capstick3Chloe Walsh4Cynthia Sandor5Samaneh Kouchaki6Ramin Nilforooshan7Payam Barnaghi8Department of Brain Sciences, Imperial College London, UK; UK Dementia Research Institute at Care Research and Technology Centre, UK; UK Dementia Research Institute at Imperial College London, UK; Corresponding author. Department of Brain Sciences, Imperial College London, UK.Department of Brain Sciences, Imperial College London, UK; UK Dementia Research Institute at Care Research and Technology Centre, UK; UK Dementia Research Institute at Imperial College London, UKDepartment of Brain Sciences, Imperial College London, UK; UK Dementia Research Institute at Care Research and Technology Centre, UKDepartment of Brain Sciences, Imperial College London, UK; UK Dementia Research Institute at Care Research and Technology Centre, UKDepartment of Brain Sciences, Imperial College London, UK; UK Dementia Research Institute at Care Research and Technology Centre, UK; Surrey and Borders Partnership NHS Foundation Trust, Leatherhead, UKDepartment of Brain Sciences, Imperial College London, UK; UK Dementia Research Institute at Imperial College London, UKDepartment of Brain Sciences, Imperial College London, UK; UK Dementia Research Institute at Care Research and Technology Centre, UK; University of Surrey, UKDepartment of Brain Sciences, Imperial College London, UK; UK Dementia Research Institute at Care Research and Technology Centre, UK; Surrey and Borders Partnership NHS Foundation Trust, Leatherhead, UK; University of Surrey, UKDepartment of Brain Sciences, Imperial College London, UK; UK Dementia Research Institute at Care Research and Technology Centre, UK; Great Ormond Street Hospital NHS Foundation Trust, London, UK; Corresponding author. Department of Brain Sciences, Imperial College London, UK.Summary: Background: Agitation affects around 30% of people living with dementia (PLwD), increasing carer burden and straining care services. Agitation identification typically relies on subjective clinical scales and direct patient observation, which are resource-intensive and challenging to incorporate into routine care. Clinical applicability of data-driven methods for agitation monitoring is limited by constraints such as short observational periods, data granularity, and lack of interpretability and generalisation. Current interventions for agitation are primarily medication-based, which may lead to severe side effects and lack personalisation. Understanding how real-world factors interact with agitation within home settings offers a promising avenue towards identifying potential personalised non-pharmacological interventions. Methods: We used longitudinal data (32,896 person-days from n = 63 PLwD) collected using in-home monitoring devices between December 2020 and March 2023. Employing machine learning techniques, we developed a monitoring tool to identify the presence of agitation during the week. We incorporated a traffic-light system to stratify agitation probability estimates supporting clinical decision-making, and employed the SHapley Additive exPlanations (SHAP) framework to enhance interpretability. We designed an interactive tool that enables the exploration of personalised non-pharmacological interventions, such as modifying ambient light and temperature. Findings: Light Gradient-boosting Machine (LightGBM) achieved the highest performance in identifying agitation over an 8-day period with a sensitivity of 71.32% ± 7.38 and specificity of 75.28% ± 7.38. Implementing the traffic-light system for stratification increased specificity to 90.3% ± 7.55 and improved all metrics. Key features for identifying agitation included low nocturnal respiratory rate, heightened alertness during sleep, and increased indoor illuminance, as revealed by statistical and feature importance analysis. Using our interactive tool, we identified indoor lighting and temperature adjustments as the most promising and feasible intervention options within our cohort. Interpretation: Our interpretable framework for agitation monitoring, developed using data from a dementia care study, showcases significant clinical value. The accompanying interactive interface allows for the in-silico simulation of non-pharmacological interventions, facilitating the design of personalised interventions that can improve in-home dementia care. Funding: This study is funded by the UK Dementia Research Institute [award number UK DRI-7002] through UK DRI Ltd, principally funded by the Medical Research Council (MRC), and the UKRI Engineering and Physical Sciences Research Council (EPSRC) PROTECT Project (grant number: EP/W031892/1). Infrastructure support for this research was provided by the NIHR Imperial Biomedical Research Centre (BRC) and the UKRI Medical Research Council (MRC). P.B. is also funded by the Great Ormond Street Hospital and the Royal Academy of Engineering. C.S. is supported by the UK Dementia Research Institute [award number UK DRI-5209], a UKRI Future Leaders Fellowship [MR/MR/X032892/1] and the Edmond J. Safra Foundation. R.N. is funded by UK Dementia Research Institute [award number UK DRI-7002] and the UKRI Engineering and Physical Sciences Research Council (EPSRC) PROTECT Project (grant number: EP/W031892/1). M.B. and A.K.S. are funded by the UK Dementia Research Institute [award number UKDRI-7002 and UKDRI-5209]. N.F.L., A.C., C.W. and S.K. are funded by the UK Dementia Research Institute [award number UK DRI-7002].http://www.sciencedirect.com/science/article/pii/S2589537024006114Dementia careAgitationMachine learningRemote monitoringDigital health tools |
| spellingShingle | Marirena Bafaloukou Ann-Kathrin Schalkamp Nan Fletcher-Lloyd Alex Capstick Chloe Walsh Cynthia Sandor Samaneh Kouchaki Ramin Nilforooshan Payam Barnaghi An interpretable machine learning tool for in-home monitoring of agitation episodes in people living with dementia: a proof-of-concept studyResearch in context EClinicalMedicine Dementia care Agitation Machine learning Remote monitoring Digital health tools |
| title | An interpretable machine learning tool for in-home monitoring of agitation episodes in people living with dementia: a proof-of-concept studyResearch in context |
| title_full | An interpretable machine learning tool for in-home monitoring of agitation episodes in people living with dementia: a proof-of-concept studyResearch in context |
| title_fullStr | An interpretable machine learning tool for in-home monitoring of agitation episodes in people living with dementia: a proof-of-concept studyResearch in context |
| title_full_unstemmed | An interpretable machine learning tool for in-home monitoring of agitation episodes in people living with dementia: a proof-of-concept studyResearch in context |
| title_short | An interpretable machine learning tool for in-home monitoring of agitation episodes in people living with dementia: a proof-of-concept studyResearch in context |
| title_sort | interpretable machine learning tool for in home monitoring of agitation episodes in people living with dementia a proof of concept studyresearch in context |
| topic | Dementia care Agitation Machine learning Remote monitoring Digital health tools |
| url | http://www.sciencedirect.com/science/article/pii/S2589537024006114 |
| work_keys_str_mv | AT marirenabafaloukou aninterpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT annkathrinschalkamp aninterpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT nanfletcherlloyd aninterpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT alexcapstick aninterpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT chloewalsh aninterpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT cynthiasandor aninterpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT samanehkouchaki aninterpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT raminnilforooshan aninterpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT payambarnaghi aninterpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT marirenabafaloukou interpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT annkathrinschalkamp interpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT nanfletcherlloyd interpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT alexcapstick interpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT chloewalsh interpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT cynthiasandor interpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT samanehkouchaki interpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT raminnilforooshan interpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext AT payambarnaghi interpretablemachinelearningtoolforinhomemonitoringofagitationepisodesinpeoplelivingwithdementiaaproofofconceptstudyresearchincontext |