Communications medicine最新文献

{"title":"Data linkage multiplies research insights across diverse healthcare sectors.","authors":"T S Karin Eisinger-Mathason, Jonah Leshin, Varun Lahoti, Doug B Fridsma, Vera Mucaj, Abel N Kho","doi":"10.1038/s43856-025-00769-y","DOIUrl":"10.1038/s43856-025-00769-y","url":null,"abstract":"<p><p>In all fields of study, as well as government and commerce, high-quality data enables informed decision-making. Linking data from disparate sources multiplies the opportunities for novel insights and evidence-based decision-making for an increasingly large range of administrative, clinical, research, and population health use cases. In recent years, novel methods, including privacy-preserving record linkage methods, have emerged. However, regardless of the method, successful data linkage is highly dependent on data quality and completeness and has to be balanced by the increased risk of re-identification of the subsequently linked data. Opportunities for the future include sharing tools for responsible linkage across silos, enhancing data to improve quality and completeness, and ensuring linkage leverages inclusive and representative datasets to ensure a balance between individual privacy and representation in research and novel discoveries. Here we provide a brief overview of the history and current state of data linkage, highlight the opportunities created by linked population data across critical research sectors, and describe the technology and policies that govern its usage.</p>","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":"5 1","pages":"58"},"PeriodicalIF":5.4,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11880312/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Metformin-regulated glucose flux from the circulation to the intestinal lumen.","authors":"Kazuhiko Sakaguchi, Kenji Sugawara, Yusei Hosokawa, Jun Ito, Yasuko Morita, Hiroshi Mizuma, Yasuyoshi Watanabe, Yuichi Kimura, Shunsuke Aburaya, Masatomo Takahashi, Yoshihiro Izumi, Takeshi Bamba, Hisako Komada, Tomoko Yamada, Yushi Hirota, Masaru Yoshida, Munenobu Nogami, Takamichi Murakami, Wataru Ogawa","doi":"10.1038/s43856-025-00755-4","DOIUrl":"10.1038/s43856-025-00755-4","url":null,"abstract":"<p><strong>Background: </strong>Through a retrospective analysis of existing FDG PET-MRI images, we recently demonstrated that metformin increases the accumulation of FDG in the intestinal lumen, suggesting that metformin stimulates glucose excretion into the intestine. However, the details of this phenomenon remain unclear. We here investigate the detailed dynamics of intestinal glucose excretion, including the rate of excretion and the metabolism of excreted glucose, in both the presence and absence of metformin.</p><p><strong>Methods: </strong>We quantified intestinal glucose excretion using newly developed FDG PET-MRI-based bioimaging in individuals with type 2 diabetes, both treated and untreated with metformin. The metabolism of excreted glucose was analyzed through mass spectrometry of fecal samples from mice intravenously injected with ¹³C-labeled glucose.</p><p><strong>Results: </strong>Continuous FDG PET/MRI image taking reveals that FDG is initially observed in the jejunum, suggesting its involvement in FDG excretion. Metformin-treated individuals excrete a significant amount of glucose (~1.65 g h^-1 per body) into the intestinal lumen. In individuals not receiving metformin, a certain amount of glucose (~0.41 g h^-1per body) is also excreted into the intestinal lumen, indicating its physiological importance. Intravenous injection of ¹³C-labeled glucose in mice increases the content of ¹³C in short-chain fatty acids (SCFAs) extracted from feces, and metformin increased the incorporation of ¹³C into SCFAs.</p><p><strong>Conclusions: </strong>A previously unrecognized, substantial flux of glucose from the circulation to the intestinal lumen exists, which likely contributes to the symbiosis between gut microbiota and the host. This flux represents a potential target of metformin's action in humans.</p>","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":"5 1","pages":"44"},"PeriodicalIF":5.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11876595/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143544750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep proteome profiling of metabolic dysfunction-associated steatotic liver disease.","authors":"Felix Boel, Vyacheslav Akimov, Mathias Teuchler, Mike Krogh Terkelsen, Charlotte Wilhelmina Wernberg, Frederik Tibert Larsen, Philip Hallenborg, Mette Munk Lauridsen, Aleksander Krag, Susanne Mandrup, Kim Ravnskjær, Blagoy Blagoev","doi":"10.1038/s43856-025-00780-3","DOIUrl":"10.1038/s43856-025-00780-3","url":null,"abstract":"<p><strong>Background: </strong>Metabolic dysfunction-associated steatotic liver disease (MASLD) affects roughly 1 in 3 adults and is a leading cause of liver transplants and liver related mortality. A deeper understanding of disease pathogenesis is essential to assist in developing blood-based biomarkers.</p><p><strong>Methods: </strong>Here, we use data-independent acquisition mass spectrometry to assess disease-state associated protein profiles in human liver, blood plasma, and white adipose tissue (WAT).</p><p><strong>Results: </strong>In liver, we find that MASLD is associated with an increased abundance of proteins involved in immune response and extracellular matrix (ECM) and a decrease in proteins involved in metabolism. Cell type deconvolution of the proteome indicates liver endothelial and hepatic stellate cells are the main source of ECM rearrangements, and hepatocytes are the major contributor to the changes in liver metabolism. In the blood, profiles of several MASLD-associated proteins correlate with expression in WAT rather than liver and so could serve as suitable liver disease predictors in a multi-protein panel marker. Moreover, our proteomics-based logistic regression models perform better than existing methods for predicting MASLD and liver fibrosis from human blood samples.</p><p><strong>Conclusions: </strong>Our comprehensive proteomic analysis deepens the understanding of liver function and MASLD pathology by elucidating key cellular mechanisms and multi-organ interactions, and demonstrates the robustness of a proteomics-based biomarker panel to enhance diagnosis of MASLD and significant fibrosis.</p>","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":"5 1","pages":"56"},"PeriodicalIF":5.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11876662/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143544749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The radiogenomic and spatiogenomic landscapes of glioblastoma and their relationship to oncogenic drivers.","authors":"Anahita Fathi Kazerooni, Hamed Akbari, Xiaoju Hu, Vikas Bommineni, Dimitris Grigoriadis, Erik Toorens, Chiharu Sako, Elizabeth Mamourian, Dominique Ballinger, Robyn Sussman, Ashish Singh, Ioannis I Verginadis, Nadia Dahmane, Constantinos Koumenis, Zev A Binder, Stephen J Bagley, Suyash Mohan, Artemis Hatzigeorgiou, Donald M O'Rourke, Tapan Ganguly, Subhajyoti De, Spyridon Bakas, MacLean P Nasrallah, Christos Davatzikos","doi":"10.1038/s43856-025-00767-0","DOIUrl":"10.1038/s43856-025-00767-0","url":null,"abstract":"<p><strong>Background: </strong>Glioblastoma is a highly heterogeneous brain tumor, posing challenges for precision therapies and patient stratification in clinical trials. Understanding how genetic mutations influence tumor imaging may improve patient management and treatment outcomes. This study investigates the relationship between imaging features, spatial patterns of tumor location, and genetic alterations in IDH-wildtype glioblastoma, as well as the likely sequence of mutational events.</p><p><strong>Methods: </strong>We conducted a retrospective analysis of 357 IDH-wildtype glioblastomas with pre-operative multiparametric MRI and targeted genetic sequencing data. Radiogenomic signatures and spatial distribution maps were generated for key mutations in genes such as EGFR, PTEN, TP53, and NF1 and their corresponding pathways. Machine and deep learning models were used to identify imaging biomarkers and stratify tumors based on their genetic profiles and molecular heterogeneity.</p><p><strong>Results: </strong>Here, we show that glioblastoma mutations produce distinctive imaging signatures, which are more pronounced in tumors with less molecular heterogeneity. These signatures provide insights into how mutations affect tumor characteristics such as neovascularization, cell density, invasion, and vascular leakage. We also found that tumor location and spatial distribution correlate with genetic profiles, revealing associations between tumor regions and specific oncogenic drivers. Additionally, imaging features reflect the cross-sectionally inferred evolutionary trajectories of glioblastomas.</p><p><strong>Conclusions: </strong>This study establishes clinically accessible imaging biomarkers that capture the molecular composition and oncogenic drivers of glioblastoma. These findings have potential implications for noninvasive tumor profiling, personalized therapies, and improved patient stratification in clinical trials.</p>","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":"5 1","pages":"55"},"PeriodicalIF":5.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11873127/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143538059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Medical ontology learning framework to investigate daytime impairment in insomnia disorder and treatment effects.","authors":"Alexander J Büsser, Renato Durrer, Moritz Freidank, Matteo Togninalli, Antonio Olivieri, Michael A Grandner, William V McCall","doi":"10.1038/s43856-024-00698-2","DOIUrl":"10.1038/s43856-024-00698-2","url":null,"abstract":"<p><strong>Background: </strong>Specificity challenges frequently arise in medical ontology used for the representation of real-world data, particularly in defining mental health disorders within widely used classification systems such as the International Classification of Diseases (ICD). This study aims to address these challenges by introducing the Disease-Specific Medical Ontology Learning (DiSMOL) framework, designed to generate precise disease representations from clinical physician notes, with a focus on daytime impairment in insomnia disorder.</p><p><strong>Methods: </strong>The study applied the Disease-Specific Medical Ontology Learning framework to clinical notes to better represent daytime impairment. The framework's performance was compared to insomnia expert-selected codes from ICD. Key statistical methods included sensitivity and F1-score comparisons, as well as analysis of symptom changes after the use of various medications, including benzodiazepines, non-benzodiazepine receptor agonists, and trazodone.</p><p><strong>Results: </strong>The DiSMOL framework significantly enhances the identification of daytime impairment in people with insomnia. Sensitivity increases from 17% to 98%, and the F1-score improves from 28% to 86%, compared with expert-selected ICD codes. Additionally, the framework reveals significant increases in daytime impairment symptoms following benzodiazepine use (18.9%), while traditional ICD codes do not detect any significant change.</p><p><strong>Conclusions: </strong>The study demonstrates that DiSMOL offers a more accurate method for identifying specific disease aspects, such as daytime impairment in insomnia, than traditional coding systems. These findings highlight the potential of specialized ontologies to enhance the representation and analysis of real-world clinical data, with important implications for healthcare policy and personalized medicine.</p>","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":"5 1","pages":"54"},"PeriodicalIF":5.4,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11871003/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143532125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Urinary metabolite model to predict the dying process in lung cancer patients.","authors":"Séamus Coyle, Elinor Chapman, David M Hughes, James Baker, Rachael Slater, Andrew S Davison, Brendan P Norman, Ivayla Roberts, Amara C Nwosu, James A Gallagher, Lakshminarayan R Ranganath, Mark T Boyd, Catriona R Mayland, Douglas B Kell, Stephen Mason, John Ellershaw, Chris Probert","doi":"10.1038/s43856-025-00764-3","DOIUrl":"10.1038/s43856-025-00764-3","url":null,"abstract":"<p><strong>Background: </strong>Accurately recognizing that a person may be dying is central to improving their experience of care at the end-of-life. However, predicting dying is frequently inaccurate and often occurs only hours or a few days before death.</p><p><strong>Methods: </strong>We performed urinary metabolomics analysis on patients with lung cancer to create a metabolite model to predict dying over the last 30 days of life.</p><p><strong>Results: </strong>Here we show a model, using only 7 metabolites, has excellent accuracy in the Training cohort n = 112 (AUC = 0·85, 0·85, 0·88 and 0·86 on days 5, 10, 20 and 30) and Validation cohort n = 49 (AUC = 0·86, 0·83, 0·90, 0·86 on days 5, 10, 20 and 30). These results are more accurate than existing validated prognostic tools, and uniquely give accurate predictions over a range of time points in the last 30 days of life. Additionally, we present changes in 125 metabolites during the final four weeks of life, with the majority exhibiting statistically significant changes within the last week before death.</p><p><strong>Conclusions: </strong>These metabolites identified offer insights into previously undocumented pathways involved in or affected by the dying process. They not only imply cancer's influence on the body but also illustrate the dying process. Given the similar dying trajectory observed in individuals with cancer, our findings likely apply to other cancer types. Prognostic tests, based on the metabolites we identified, could aid clinicians in the early recognition of people who may be dying and thereby influence clinical practice and improve the care of dying patients.</p>","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":"5 1","pages":"49"},"PeriodicalIF":5.4,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11868640/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143525239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Alzheimer's disease biological PET staging using plasma p217+tau.","authors":"Azadeh Feizpour, Vincent Doré, Natasha Krishnadas, Pierrick Bourgeat, James D Doecke, Ziad S Saad, Gallen Triana-Baltzer, Simon M Laws, Rosita Shishegar, Kun Huang, Christopher Fowler, Larry Ward, Colin L Masters, Jurgen Fripp, Hartmuth C Kolb, Victor L Villemagne, Christopher C Rowe","doi":"10.1038/s43856-025-00768-z","DOIUrl":"10.1038/s43856-025-00768-z","url":null,"abstract":"<p><strong>Background: </strong>Plasma phospho-tau biomarkers, such as p217+tau, excel at identifying Alzheimer's disease (AD) neuropathology. However, their ability to substitute for tau PET to identify AD biological stage is unclear.</p><p><strong>Methods: </strong>Participants included 248 cognitively unimpaired (CU) and 227 cognitively impaired (CI) individuals, with Janssen plasma p217+tau Simoa® assay, ¹⁸F-NAV4694 Aβ-PET (A) and ¹⁸F-MK6240 tau-PET (T) data. Biological PET stages were defined according to the Revised Criteria for Diagnosis and Staging of Alzheimer's Disease (2024): Initial (A + T-), Early (A + T_MTL + ), Intermediate (A + T_MOD + ), and Advanced (A + T_HIGH + ). The threshold for A+ was 25 Centiloid and for T_HIGH + , the 75th percentile SUVR_{temporo-parietal} in A + CI. Sixty percent were A + , 36% Intermediate/Advanced, and 9% Advanced. The performance of p217+tau in discriminating AD stages was assessed using Receiver Operating Characteristic (ROC) analysis and logistic regression.</p><p><strong>Results: </strong>Plasma p217+tau concentrations increase across the AD biological PET stages, except between Initial and Early stages. Screening for all AD stages (vs. A-T-), combined Intermediate/Advanced stages, or Advanced stage yields AUC of 0.92, 0.92, and 0.91, respectively (CI only: AUC 0.93, 0.89, 0.83). Plasma p217+tau Youden threshold provides sensitivity of 0.77 [0.73-0.90], specificity 0.91 [0.80-0.95], PPV 0.84 [0.71-0.89], and NPV 0.88 [0.85-0.93] for combined Intermediate/Advanced stages. For the Advanced stage alone, sensitivity is 0.89 [0.79-0.97], specificity 0.82 [0.75-0.9], NPV 0.99 [0.98-1.0], but PPV is only 0.33 [0.25-0.47].</p><p><strong>Conclusions: </strong>In addition to accurately screening for A+ individuals, plasma p217+tau is useful for identifying a combined Intermediate/Advanced stage AD cohort or pre-screening to reduce the tau-PET required to identify Advanced stage AD individuals.</p>","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":"5 1","pages":"53"},"PeriodicalIF":5.4,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11868538/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143525223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Disparities in telemedicine use and payment policies in the United States between 2019 and 2023.","authors":"Anna D Gage, Megan A Knight, Corinne Bintz, Robert W Aldridge, Olivia Angelino, Joseph L Dieleman, M Ashworth Dirac, Laura Dwyer-Lindgren, Simon I Hay, Rafael Lozano, Ali H Mokdad, Annie Haakenstad","doi":"10.1038/s43856-025-00757-2","DOIUrl":"10.1038/s43856-025-00757-2","url":null,"abstract":"<p><strong>Background: </strong>The COVID-19 pandemic induced an increase in telemedicine use in the American health care system. We assess disparities in telemedicine usage, the diseases and conditions it is used for, and the association of payment parity policies with telemedicine use for January 2019-March 2023.</p><p><strong>Methods: </strong>We include health systems which reported electronic health record data to the Healthjump database. The outcomes of interest are the percentage of outpatient consultations conducted via telemedicine in each health system and the distribution of outpatient and telemedicine consultations across 31 diseases and conditions. We use a difference-in-difference observational design to assess the association of state level payment parity mandates with telemedicine use.</p><p><strong>Results: </strong>We show telemedicine use grew from less than 0.05% of outpatient consultations in 2019 to 25% in April 2020 and 4% in March 2023. Health systems in urban areas used telemedicine 2.4 times more than health systems in rural areas since April 2020 at the median. In March 2023, 29% of all mental health care visits and 21% of substance use disorder care were provided via telemedicine. Payment parity mandates are associated with a 2.5 percentage point increase in telemedicine use in the first quarter of 2023 compared to states without mandates.</p><p><strong>Conclusions: </strong>The pandemic resulted in a sustained change in the use of telemedicine. The predominance of mental health care in telemedicine suggests that this mode of service delivery could be instrumental to increasing access to mental health services in the United States.</p>","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":"5 1","pages":"52"},"PeriodicalIF":5.4,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11865567/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143517580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LRP5 promotes adipose progenitor cell fitness and adipocyte insulin sensitivity.","authors":"Nellie Y Loh, Senthil K Vasan, Daniel B Rosoff, Emile Roberts, Andrea D van Dam, Manu Verma, Daniel Phillips, Agata Wesolowska-Andersen, Matt J Neville, Raymond Noordam, David W Ray, Jonathan H Tobias, Celia L Gregson, Fredrik Karpe, Constantinos Christodoulides","doi":"10.1038/s43856-025-00774-1","DOIUrl":"10.1038/s43856-025-00774-1","url":null,"abstract":"<p><strong>Background: </strong>WNT signaling plays a key role in postnatal bone formation. Individuals with gain-of-function mutations in the WNT co-receptor LRP5 exhibit increased lower-body fat mass and potentially enhanced glucose metabolism, alongside high bone mass. However, the mechanisms by which LRP5 regulates fat distribution and its effects on systemic metabolism remain unclear. This study aims to explore the role of LRP5 in adipose tissue biology and its impact on metabolism.</p><p><strong>Methods: </strong>Metabolic assessments and imaging were conducted on individuals with gain- and loss-of-function LRP5 mutations, along with age- and BMI-matched controls. Mendelian randomization analyses were used to investigate the relationship between bone, fat distribution, and systemic metabolism. Functional studies and RNA sequencing were performed on abdominal and gluteal adipose cells with LRP5 knockdown.</p><p><strong>Results: </strong>Here we show that LRP5 promotes lower-body fat distribution and enhances systemic and adipocyte insulin sensitivity through cell-autonomous mechanisms, independent of its bone-related functions. LRP5 supports adipose progenitor cell function by activating WNT/β-catenin signaling and preserving valosin-containing protein (VCP)-mediated proteostasis. LRP5 expression in adipose progenitors declines with age, but gain-of-function LRP5 variants protect against age-related fat loss in the lower body.</p><p><strong>Conclusions: </strong>Our findings underscore the critical role of LRP5 in regulating lower-body fat distribution and insulin sensitivity, independent of its effects on bone. Pharmacological activation of LRP5 in adipose tissue may offer a promising strategy to prevent age-related fat redistribution and metabolic disorders.</p>","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":"5 1","pages":"51"},"PeriodicalIF":5.4,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11862225/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143506485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using wearable sensors and machine learning to assess upper limb function in Huntington's disease.","authors":"Adonay S Nunes, İlkay Yıldız Potter, Ram Kinker Mishra, Jose Casado, Nima Dana, Andrew Geronimo, Christopher G Tarolli, Ruth B Schneider, E Ray Dorsey, Jamie L Adams, Ashkan Vaziri","doi":"10.1038/s43856-025-00770-5","DOIUrl":"10.1038/s43856-025-00770-5","url":null,"abstract":"<p><strong>Background: </strong>Huntington's disease, a neurodegenerative disorder, impairs both upper and lower limb function, typically assessed in clinical settings. However, wearable sensors offer the opportunity to monitor real-world data that complements clinical assessments, providing a more comprehensive understanding of disease symptoms.</p><p><strong>Methods: </strong>In this study, we monitor upper limb function in individuals with Huntington's disease (HD, n = 16), prodromal HD (pHD, n = 7), and controls (CTR, n = 16) using a wrist-worn wearable sensor over a 7-day period. Goal-directed hand movements are detected through a deep learning model, and kinematic features of each movement are analyzed. The collected data is used to predict disease groups and clinical scores using statistical and machine learning models.</p><p><strong>Results: </strong>Here we show that significant differences in goal-directed movement features exist between the groups. Additionally, several of these features strongly correlate with clinical scores. Classification models accurately distinguish between HD, pHD, and CTR individuals, achieving a balanced accuracy of 67% and a recall of 0.72 for the HD group. Regression models effectively predict clinical scores.</p><p><strong>Conclusions: </strong>This study demonstrates the potential of wearable sensors and machine learning to monitor upper limb function in Huntington's disease, offering a tool for early detection, remote monitoring, and assessing treatment efficacy in clinical trials.</p>","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":"5 1","pages":"50"},"PeriodicalIF":5.4,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11861259/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143506487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}