{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T06:10:16Z","timestamp":1758867016898,"version":"3.44.0"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T00:00:00Z","timestamp":1758844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Clinical monitoring of functional decline in amyotrophic lateral sclerosis (ALS) relies on periodic assessments, which may miss critical changes that occur between visits when timely interventions are most beneficial.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To address this gap, semi-supervised regression models with pseudo-labeling were developed; these models estimated rates of decline by targeting Revised Amyotrophic Lateral Sclerosis Functional Rating Scale (ALSFRS-R) trajectories with continuous in-home sensor data from a three-patient ALS case series. Three model paradigms were compared (individual batch learning and cohort-level batch vs. incremental fine-tuned transfer learning) across linear slope, cubic polynomial, and ensembled self-attention pseudo-label interpolations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Results showed cohort-level homogeneity across functional domains. For ALSFRS-R subscales, transfer learning reduced the prediction error in 28 of 34 contrasts [mean root mean square error (RMSE) = 0.20 (0.14\u20130.25)]. However, for composite ALSFRS-R scores, individual batch learning was optimal for two of three participants [mean RMSE = 3.15 (2.24\u20134.05)]. Self-attention interpolation best captured non-linear progression, providing the lowest subscale-level error [mean RMSE = 0.19 (0.15\u20130.23)], and outperformed linear and cubic interpolations in 21 of 34 contrasts. Conversely, linear interpolation produced more accurate composite predictions [mean RMSE = 3.13 (2.30\u20133.95)]. Distinct homogeneity-heterogeneity profiles were identified across domains, with respiratory and speech functions showing patient-specific progression patterns that improved with personalized incremental fine-tuning, while swallowing and dressing functions followed cohort-level trends suited for batch transfer modeling.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>These findings indicate that dynamically matching learning and pseudo-labeling techniques to functional domain-specific homogeneity-heterogeneity profiles enhances predictive accuracy in tracking ALS progression. As an exploratory pilot, these results reflect case-level observations rather than population-wide effects. Integrating adaptive model selection into sensor platforms may enable timely interventions as a method for scalable deployment in future multi-center studies.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fdgth.2025.1657749","type":"journal-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T05:34:44Z","timestamp":1758864884000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing ALS progression tracking with semi-supervised ALSFRS-R scores estimated from ambient home health monitoring"],"prefix":"10.3389","volume":"7","author":[{"given":"Noah","family":"Marchal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William E.","family":"Janes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheila","family":"Marushak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mihail","family":"Popescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,26]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1007\/s13311-014-0331-9","article-title":"Clinical measures of disease progression in amyotrophic lateral sclerosis","volume":"12","author":"Rutkove","year":"2015","journal-title":"Neurotherapeutics"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JTEHM.2015.2421499","article-title":"Automated health alerts using in-home sensor data for embedded health assessment","volume":"3","author":"Skubic","year":"2015","journal-title":"IEEE J Transl Eng Health Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"glad119","DOI":"10.1093\/gerona\/glad119","article-title":"Terminal decline in physical function in older adults","volume":"79","author":"Stolz","year":"2024","journal-title":"J Gerontol Ser A Biol Sci Med Sci"},{"key":"B4","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1016\/j.neurol.2022.03.019","article-title":"Changes in neuromuscular function in elders: Novel techniques for assessment of motor unit loss and motor unit remodeling with aging","volume":"178","author":"Verschueren","year":"2022","journal-title":"Rev Neurol (Paris)"},{"key":"B5","article-title":"Using wearable and environmental data to improve the prediction of amyotrophic lateral sclerosis and multiple sclerosis progression: an explorative study","author":"Marinello","year":""},{"key":"B6","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1080\/21678421.2020.1773501","article-title":"The use of biotelemetry to explore disease progression markers in amyotrophic lateral sclerosis","volume":"21","author":"Kelly","year":"2020","journal-title":"Amyotroph Later Scler Frontotemp Degener"},{"key":"B7","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1016\/j.mayocpiqo.2024.07.008","article-title":"Prognostic factors and epidemiology of amyotrophic lateral sclerosis in southeastern united states","volume":"8","author":"Engelberg-Cook","year":"2024","journal-title":"Mayo Clin Proc Innov Qual Outcom"},{"key":"B8","doi-asserted-by":"publisher","first-page":"ARTN 1623","DOI":"10.3390\/jcm10081623","article-title":"Clinical determinants of disease progression in amyotrophic lateral sclerosis\u2014a retrospective cohort study","volume":"10","author":"Requardt","year":"2021","journal-title":"J Clin Med"},{"key":"B9","doi-asserted-by":"publisher","first-page":"ARTN 103732","DOI":"10.1016\/j.ebiom.2021.103732","article-title":"Predictors of survival in patients with amyotrophic lateral sclerosis: a large meta-analysis","volume":"74","author":"Su","year":"2021","journal-title":"Ebiomedicine"},{"key":"B10","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1038\/s43588-022-00299-w","article-title":"Identifying patterns in amyotrophic lateral sclerosis progression from sparse longitudinal data","volume":"2","author":"Ramamoorthy","year":"2022","journal-title":"Nat Comput Sci"},{"key":"B11","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1080\/21678421.2024.2322549","article-title":"Longitudinal comparison of the self-administered ALSFRS-RSE and ALSFRS-R as functional outcome measures in ALS","volume":"25","author":"Erb","year":"2024","journal-title":"Amyotroph Later Scler Frontotemp Degener"},{"key":"B12","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1097\/WCO.0000000000000861","article-title":"Current trends in the clinical trial landscape for amyotrophic lateral sclerosis","volume":"33","author":"van Eijk","year":"2020","journal-title":"Curr Opin Neurol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1136\/jnnp-2012-304701","article-title":"Evidence of multidimensionality in the ALSFRS-R scale: a critical appraisal on its measurement properties using Rasch analysis","volume":"84","author":"Franchignoni","year":"2013","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e60437","DOI":"10.2196\/60437","article-title":"Integrating ambient in-home sensor data and electronic health record data for the prediction of outcomes in amyotrophic lateral sclerosis: Protocol for an exploratory feasibility study","volume":"14","author":"Janes","year":"2025","journal-title":"JMIR Res Protoc"},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1109\/IEMBS.2010.5627219","article-title":"Monitoring pulse and respiration with a non-invasive hydraulic bed sensor","author":"Heise","year":""},{"key":"B16","doi-asserted-by":"publisher","first-page":"193","DOI":"10.3233\/AIS-170423","article-title":"Heart rate monitoring using hydraulic bed sensor ballistocardiogram","volume":"9","author":"Rosales","year":"2017","journal-title":"J Ambient Intell Smart Environ"},{"key":"B17","doi-asserted-by":"publisher","first-page":"2925","DOI":"10.1109\/TBME.2013.2266341","article-title":"Unobtrusive, continuous, in-home gait measurement using the Microsoft Kinect","volume":"60","author":"Stone","year":"2013","journal-title":"IEEE Trans Biomed Eng"},{"key":"B18","doi-asserted-by":"crossref","DOI":"10.1145\/3154862.3154890","article-title":"Exploring clinical correlations in centroid-based gait metrics from depth data collected in the home","author":"Wallace","year":""},{"key":"B19","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1212\/CON.0000000000000911","article-title":"Amyotrophic lateral sclerosis and other motor neuron diseases","volume":"26","author":"Quinn","year":"2020","journal-title":"Continuum"},{"key":"B20","first-page":"788","article-title":"Integrating multi-sensor time-series data for ALSFRS-R clinical scale predictions in an ALS patient case study","volume":"2024","author":"Marchal","year":"2024","journal-title":"AMIA Annu Symp Proc"},{"key":"B21","article-title":"Time Series in Keras","author":"Heaton","year":""},{"key":"B22","doi-asserted-by":"publisher","first-page":"100254","DOI":"10.1016\/j.caeai.2024.100254","article-title":"XGBoost to enhance learner performance prediction","volume":"7","author":"Hakkal","year":"2024","journal-title":"Comput Educ Artif Intell"},{"key":"B23","doi-asserted-by":"publisher","first-page":"ARTN 48","DOI":"10.1186\/s12911-020-1063-x","article-title":"An evaluation of time series summary statistics as features for clinical prediction tasks","volume":"20","author":"Guo","year":"2020","journal-title":"BMC Med Inform Decis Mak"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1824","DOI":"10.1109\/JBHI.2020.3025049","article-title":"Wearables and deep learning classify fall risk from gait in multiple sclerosis","volume":"25","author":"Meyer","year":"2021","journal-title":"IEEE J Biomed Health Inform"},{"key":"B25","doi-asserted-by":"crossref","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen","year":""},{"key":"B26","doi-asserted-by":"publisher","first-page":"7183","DOI":"10.1029\/2000JD900719","article-title":"Summarizing multiple aspects of model performance in a single diagram","volume":"106","author":"Taylor","year":"2001","journal-title":"J Geophys Res Atmosph"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2025.1657749\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T05:34:45Z","timestamp":1758864885000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2025.1657749\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,26]]},"references-count":26,"alternative-id":["10.3389\/fdgth.2025.1657749"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2025.1657749","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,26]]},"article-number":"1657749"}}