medRxiv : the preprint server for health sciences最新文献

{"title":"A qualitative study of music-based intervention use for Alzheimer's disease in elder care communities.","authors":"Benjamin J Hess, Ava Zatloukal, Jasmine M Taylor, Michelle Neidens, Kristine N Williams, Rebecca J Lepping","doi":"10.1101/2025.03.18.25324196","DOIUrl":"https://doi.org/10.1101/2025.03.18.25324196","url":null,"abstract":"<p><strong>Background: </strong>Because Music Based Interventions (MBIs) are not standard of care for Alzheimer's disease and Alzheimer's disease related dementias (AD/ADRD), it is likely that the application of them in different care communities differs widely. Additionally, there is no standardized use of personalized music listening and group music activities.</p><p><strong>Objective: </strong>The purpose of this study was to assess the current use of music in long-term care communities, to identify trends and patterns of music use and record the observed benefits that music use provides.</p><p><strong>Methods: </strong>This study utilized a qualitative research approach using semi-structured interviews with care community staff and care community observations to examine the role that music played as a therapeutic tool for individuals with AD/ADRD living in care communities.</p><p><strong>Results: </strong>Five different communities were visited and observed. Of the five communities visited, interviews were conducted at four communities. One community did not participate in the interviews due to scheduling conflicts. Two staff members were interviewed at each participating community resulting in eight total interviews.</p><p><strong>Conclusions: </strong>The results of this qualitative survey of care communities suggests that staff members believe that music use has beneficial effects for residents living with AD/ADRD. Music is economical, easily accessible, and very adaptable. Music can be used in a broad range of situations to improve the quality of life for both residents and staff in care communities. Music use can be active or passive, it can be used by an individual or a group to excite and engage or to calm and soothe.</p>","PeriodicalId":94281,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957097/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143757119","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":"Point-of-Care Ultrasound as a Prognostic Tool in Critically Ill Patients: Insights Beyond Core Muscle Mass.","authors":"Rachel Skoczynski, Jonathan Hansen, Sanjib Das Adhikary, Erik Lehman, Anthony S Bonavia","doi":"10.1101/2025.03.19.25324253","DOIUrl":"https://doi.org/10.1101/2025.03.19.25324253","url":null,"abstract":"<p><strong>Background: </strong>Muscle wasting is a major concern in ICUs, contributing to morbidity, mortality, and prolonged rehabilitation. While CT-derived L3 Skeletal Muscle Index (L3SMI) assesses core muscle mass, it may not capture peripheral muscle atrophy or fluid-based changes. Point-of-care ultrasound (POCUS) offers a rapid, non-invasive alternative. This study evaluated the prognostic value of POCUS-based muscle measurements compared with L3SMI in predicting mortality, frailty, and functional outcomes.</p><p><strong>Methods: </strong>In this prospective study, 50 critically ill adults meeting Sepsis-3 criteria or requiring respiratory/vasopressor support underwent POCUS assessments of biceps brachii, rectus femoris, and vastus intermedius thickness at days 1, 7, and 14 post-ICU admission. Twenty-eight patients also had CT scans within seven days for L3SMI calculation. The primary outcome was 90-day mortality; secondary outcomes included in-hospital and 30-day mortality, Clinical Frailty Score, and Zubrod/ECOG performance status. Muscle measurements were analyzed both raw and indexed to body surface area, with predictive performance assessed via correlation and ROC analysis.</p><p><strong>Results: </strong>Day 1 biceps brachii thickness strongly predicted in-hospital mortality (AUC 0.84; sensitivity 1.0, specificity 0.67) and retained predictive value for 30-day and 90-day mortality. Vastus intermedius thickness on day 1 was moderately predictive (AUC 0.79). At later time points, larger vastus intermedius measurements correlated negatively with ICU-and ventilator-free days, suggesting edema-related pseudohypertrophy. L3SMI did not significantly correlate with ultrasound-based muscle measurements or clinical outcomes. POCUS-derived peripheral muscle indexing was associated with frailty indices, highlighting its role in capturing meaningful functional deficits.</p><p><strong>Conclusion: </strong>POCUS-based muscle assessments, particularly of the biceps brachii and vastus intermedius, provide valuable prognostic insights beyond conventional L3SMI. While L3SMI remains a core muscle measure, fluid shifts and localized muscle wasting in critical illness may be better captured by ultrasound.</p>","PeriodicalId":94281,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957184/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756929","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 long-term risk of tuberculosis among individuals with Xpert Ultra \"trace\" screening results: a longitudinal follow-up study.","authors":"Joowhan Sung, Mariam Nantale, Annet Nalutaaya, Patrick Biché, James Mukiibi, Joab Akampurira, Rogers Kiyonga, Francis Kayondo, Michael Mukiibi, Caitlin Visek, Caleb E Kamoga, David W Dowdy, Achilles Katamba, Emily A Kendall","doi":"10.1101/2025.03.20.25324205","DOIUrl":"https://doi.org/10.1101/2025.03.20.25324205","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Systematic screening for tuberculosis using Xpert Ultra generates \"trace\" results of uncertain significance. Additional microbiological testing in this context is often negative, but individuals with trace results might have early disease or elevated risk of tuberculosis.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We screened for tuberculosis with Xpert Ultra in Uganda, enrolling individuals with trace-positive results and Ultra-negative controls. Participants without tuberculosis on extensive initial evaluation were followed, with repeat testing at 1, 3, and 6 months after trace results, and at 12 and 24 months for all participants. We estimated cumulative cause-specific hazards of incident tuberculosis, considering a definition of tuberculosis that included clinician judgment and one based strictly on microbiological results. We compared participants with Ultra-trace versus Ultra-negative sputum, and subgroups of participants with Ultra-trace sputum.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Findings: &lt;/strong&gt;Of 129 participants with trace-positive screening results, 45 (35%) were recommended for treatment upon enrollment, and eight were lost to follow-up within three months. Of 76 remaining participants followed for median 697 (interquartile range 179-714) days, 20 (26%) were recommended for tuberculosis treatment. The cumulative hazard of clinician-defined incident tuberculosis was 26% (95% confidence interval: 14-38%) at one year and 35% (19-52%) at two years, versus 2% (0-5%) at two years for controls. Hazards were similar for microbiologically defined incident tuberculosis. Incident tuberculosis was strongly associated with abnormal baseline chest X-ray (hazard ratio 15.0 [3.4-65.1]) but not with baseline symptoms.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Interpretation: &lt;/strong&gt;Individuals with trace-positive sputum during screening, particularly those with abnormal chest imaging, are at substantial risk of incident tuberculosis over the subsequent two years.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Funding: &lt;/strong&gt;National Institutes of Health.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Research in context: &lt;/strong&gt;&lt;b&gt;Evidence before this study:&lt;/b&gt; Recent advances in tuberculosis research have shifted the disease framework from a binary classification of latent versus active tuberculosis to a continuum of disease states. They have also led to a better understanding of the dynamic disease course of early tuberculosis, which can either progress to culture-positive disease or regress spontaneously over time. \"Trace\" results from Xpert MTB/RIF Ultra (\"Ultra\") are sometimes perceived as false positives in individuals who subsequently test negative on additional diagnostic assays. However, some of these individuals may have early tuberculosis that falls below the detection threshold of existing diagnostic tests and could progress to microbiologically detectable disease over time. To investigate this, we searched PubMed for studies published up to February 7, 2025, using the terms \"tuberculosis\" AND (\"Xpert OR \"Xpert Ultra\" OR","PeriodicalId":94281,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957171/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143757183","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":"Genetic Determinants Of Major Depressive Disorder (MDD) Among Adult Persons Living With HIV In Uganda.","authors":"Olga Nsangi Tendo, Ronald Galiwango, Eugene Kinyanda, Martha Sajatovic, Mark Kaddumukasa, Martin Kaddumukasa, Elly Katabira, Catherine Nabbumba, Seedat Soraya, Sian Hemmings, Allan Kalungi","doi":"10.1101/2025.03.19.25324246","DOIUrl":"https://doi.org/10.1101/2025.03.19.25324246","url":null,"abstract":"<p><strong>Background: </strong>Major Depressive Disorder (MDD) has a heritable component, with estimates of heritability ranging from 30% to 40%. Depression is a significant comorbidity in people living with HIV (PLWHIV), increasing the risk of suicide-related behaviors. This study investigated the genetic risk loci associated with MDD among adults living with HIV in Uganda, where limited data exist on this relationship.</p><p><strong>Methods: </strong>The case-control study analyzed 282 samples (139 MDD cases and 143 controls), assessed for MDD at baseline, six months, and one year using the Mini International Neuropsychiatric Interview. Blood samples were collected at these intervals, with DNA genotyping conducted in South Africa using the H3Africa array. Data were analyzed using PLINK2 and GEMMA for quality control and genome-wide association analysis respectively, followed by functional mapping with FUMA.</p><p><strong>Results: </strong>While no significant single nucleotide polymorphisms (SNPs) were identified at the genome-wide threshold, six SNPs were found to be suggestively associated with MDD. These SNPs, which have been associated with other psychiatric conditions like Alzheimer's, alcohol use disorder, and bipolar disorder and have not previously been linked to MDD.</p><p><strong>Conclusion: </strong>The study suggests the potential for novel MDD genetic risk loci discovery in PLWHIV and people of African ancestry, especially with larger sample sizes.</p>","PeriodicalId":94281,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957178/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143757062","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":"Image-based Mandibular and Maxillary Parcellation and Annotation using Computer Tomography (IMPACT): A Deep Learning-based Clinical Tool for Orodental Dose Estimation and Osteoradionecrosis Assessment.","authors":"Laia Humbert-Vidan, Austin H Castelo, Renjie He, Lisanne V van Dijk, Dong Joo Rhee, Congjun Wang, He C Wang, Kareem A Wahid, Sonali Joshi, Parshan Gerafian, Natalie West, Zaphanlene Kaffey, Sarah Mirbahaeddin, Jaqueline Curiel, Samrina Acharya, Amal Shekha, Praise Oderinde, Alaa M S Ali, Andrew Hope, Erin Watson, Ruth Wesson-Aponte, Steven J Frank, Carly E A Barbon, Kristy K Brock, Mark S Chambers, Muhammad Walji, Katherine A Hutcheson, Stephen Y Lai, Clifton D Fuller, Mohamed A Naser, Amy C Moreno","doi":"10.1101/2025.03.18.25324199","DOIUrl":"https://doi.org/10.1101/2025.03.18.25324199","url":null,"abstract":"<p><strong>Background: </strong>Accurate delineation of orodental structures on radiotherapy CT images is essential for dosimetric assessments and dental decisions. We propose a deep-learning auto-segmentation framework for individual teeth and mandible/maxilla sub-volumes aligned with the ClinRad ORN staging system.</p><p><strong>Methods: </strong>Mandible and maxilla sub-volumes were manually defined, differentiating between alveolar and basal regions, and teeth were labelled individually. For each task, a DL segmentation model was independently trained. A Swin UNETR-based model was used for the mandible sub-volumes. For the smaller structures (e.g., teeth and maxilla sub-volumes) a two-stage segmentation model first used the ResUNet to segment the entire teeth and maxilla regions as a single ROI that was then used to crop the image input of the Swin UNETR. In addition to segmentation accuracy and geometric precision, a dosimetric comparison was made between manual and model-predicted segmentations.</p><p><strong>Results: </strong>Segmentation performance varied across sub-volumes - mean Dice values of 0.85 (mandible basal), 0.82 (mandible alveolar), 0.78 (maxilla alveolar), 0.80 (upper central teeth), 0.69 (upper premolars), 0.76 (upper molars), 0.76 (lower central teeth), 0.70 (lower premolars), 0.71 (lower molars) - and exhibited limited applicability in segmenting teeth and sub-volumes often absent in the data. Only the maxilla alveolar central sub-volume showed a statistically significant dosimetric difference (Bonferroni-adjusted p-value = 0.02).</p><p><strong>Conclusion: </strong>We present a novel DL-based auto-segmentation framework of orodental structures, enabling spatial localization of dose-related differences in the jaw. This tool enhances image-based bone injury detection, including ORN, and improves clinical decision-making in radiation oncology and dental care for head and neck cancer patients.</p>","PeriodicalId":94281,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957087/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756930","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":"Choice of Epilepsy Anti-Seizure Medications and Associated Outcomes in Medicare Beneficiaries.","authors":"Julianne D Brooks, Rafaella Cazé de Medeiros, Shuo Sun, Madhav Sankaranarayanan, M Brandon Westover, Lee H Schwamm, Joseph P Newhouse, Sebastien Haneuse, Lidia M V R Moura","doi":"10.1101/2025.03.18.25324227","DOIUrl":"https://doi.org/10.1101/2025.03.18.25324227","url":null,"abstract":"<p><strong>Background: </strong>The lack of specific guidelines for seizure treatment after acute ischemic stroke (AIS), makes the choice of an appropriate anti-seizure medication choice a challenge for providers because each drug may have different adverse effects and outcomes.</p><p><strong>Methods: </strong>In this retrospective matched cohort study, we analyzed a 20% sample of U.S. Medicare beneficiaries aged 65 and over hospitalized for a first acute ischemic stroke (AIS) between 2009-2021 who were discharged home. We included individuals who were enrolled in Medicare hospital, medical and prescription drug insurance for 12 months prior to hospitalization and were not taking epilepsy-specific anti-seizure medication (ESM) prior to hospitalization. We matched individuals on days from discharge to ESM initiation. Individuals who initiated ESMs other than Levetiracetam, i.e. Lamotrigine, Carbamazepine, Oxcarbazepine within 30 days of discharge (N = 229) were matched to Levetiracetam initiators (N =687). We investigated the time to seizure-like events, emergency department (ED) visits, and re-hospitalizations with a follow-up of 180 days after initiation using a semi-competing risk framework. We estimated the average treatment effect among the treated i.e. those who received other ESMs.</p><p><strong>Results: </strong>The matched cohort of 916 ESM initiators had a median age of 74 (IQR 69, 82) and was 57% female and 71% Non-Hispanic White. Using the semi-competing risk framework, those who received other ESM had a 37% lower hazard of seizure-like events compared to receiving LEV, given that death had not occurred, hazard ratio 0.63 (95% CI: 0.43, 0.91). Among those who initiated ESMs other than Levetiracetam, the hazard of ED visits and hospitalizations, given that death had not occurred, did not different significantly from initiating Levetiracetam; hazard ratios 1.00 (95% CI: 0.80, 1.25) and 0.98 (95% CI: 0.75, 1.28), respectively.</p><p><strong>Conclusion: </strong>In a sample of Medicare beneficiaries hospitalized for acute ischemic stroke and discharged home, initiating Levetiracetam in the outpatient setting was associated with a higher risk of seizure-like events compared to other ESMs. However, no significant differences were observed in the incidence of ED visits or hospitalizations, suggesting comparable safety profiles in these broader clinical outcomes.</p>","PeriodicalId":94281,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957074/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143757121","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":"Brain Aging in Specific Phobia: An ENIGMA-Anxiety Mega-Analysis.","authors":"Kimberly V Blake, Kevin Hilbert, Jonathan C Ipser, Laura K M Han, Janna Marie Bas-Hoogendam, Fredrik Åhs, Jochen Bauer, Katja Beesdo-Baum, Johannes Björkstrand, Laura Blanco-Hinojo, Joscha Böhnlein, Robin Bülow, Marta Cano, Narcis Cardoner, Xavier Caseras, Udo Dannlowski, Mats Fredrikson, Liesbet Goossens, Hans J Grabe, Dominik Grotegerd, Tim Hahn, Alfons Hamm, Ingmar Heinig, Martin J Herrmann, David Hofmann, Hamidreza Jamalabadi, Andreas Jansen, Merel Kindt, Tilo Kircher, Anna L Klahn, Katja Koelkebeck, Axel Krug, Elisabeth J Leehr, Martin Lotze, Juergen Margraf, Markus Muehlhan, Igor Nenadić, Wenceslao Peñate, Andre Pittig, Jens Plag, Jesús Pujol, Jan Richter, Isabelle C Ridderbusch, Francisco Rivero, Axel Schäfer, Judith Schäfer, Anne Schienle, Elisabeth Schrammen, Koen Schruers, Esther Seidl, Rudolf M Stark, Benjamin Straube, Thomas Straube, Andreas Ströhle, Lea Teutenberg, Sophia I Thomopoulos, Carlos Ventura-Bort, Renee M Visser, Henry Völzke, Albert Wabnegger, Julia Wendt, Hans-Ulrich Wittchen, Katharina Wittfeld, Yunbo Yang, Anna Zilverstand, Peter Zwanzger, Lianne Schmaal, Moji Aghajani, Daniel S Pine, Paul M Thompson, Nic J A van der Wee, Dan J Stein, Ulrike Lueken, Nynke A Groenewold","doi":"10.1101/2025.03.19.25323474","DOIUrl":"https://doi.org/10.1101/2025.03.19.25323474","url":null,"abstract":"<p><strong>Introduction: </strong>Specific phobia (SPH) is a prevalent anxiety disorder and may involve advanced biological aging. However, brain age research in psychiatry has primarily examined mood and psychotic disorders. This mega-analysis investigated brain aging in SPH participants within the ENIGMA-Anxiety Working Group.</p><p><strong>Methods: </strong>3D brain <b>s</b> tructural MRI scans from 17 international samples (600 SPH individuals, of whom 504 formally diagnosed and 96 questionnaire-based cases; 1,134 controls; age range: 22-75 years) were processed with FreeSurfer. Brain age was estimated from 77 subcortical and cortical regions with a publicly available ENIGMA brain age model. The brain-predicted age difference (brain-PAD) was calculated as brain age minus chronological age. Linear mixed-effect models examined group differences in brain-PAD and moderation by age.</p><p><strong>Results: </strong>No significant group difference in brain-PAD manifested ( <b>β</b> _diagnosis (SE)=0.37 years (0.43), <i>p</i> =0.39). A negative diagnosis-by-age interaction was identified, which was most pronounced in formally diagnosed SPH ( <b>β</b> _{diagnosis-by-age} =-0.08 (0.03), <i>pFDR</i> =0.02). This interaction remained significant when excluding participants with anxiety comorbidities, depressive comorbidities, and medication use. Post-hoc analyses revealed a group difference for formal SPH diagnosis in younger participants (22-35 years; <b>β</b> _diagnosis =1.20 (0.60), <i>p</i> <0.05, mixed-effects <i>d</i> (95% confidence interval)=0.14 (0.00-0.28)), but not older participants (36-75 years; <b>β</b> _diagnosis =0.07 (0.65), <i>p</i> =0.91).</p><p><strong>Conclusions: </strong>Brain aging did not relate to SPH in the full sample. However, a diagnosis-by-age interaction was observed across analyses, and was strongest in formally diagnosed SPH. Post-hoc analyses showed a subtle advanced brain aging in young adults with formally diagnosed SPH. Taken together, these findings indicate the importance of clinical severity, impairment and persistence, and may suggest a slightly earlier end to maturational processes or subtle decline of brain structure in SPH.</p>","PeriodicalId":94281,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957081/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756838","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":"Precise perivascular space segmentation on magnetic resonance imaging from Human Connectome Project-Aging.","authors":"Yaqiong Chai, Hedong Zhang, Carlos Robles, Andrew Shinho Kim, Nada Janhanshad, Paul M Thompson, Ysbrand van der Werf, Eva M van Heese, Jiyoung Kim, Eun Yeon Joo, Leon Aksman, Kyung-Wook Kang, Jung-Won Shin, Abigail Trang, Jongmok Ha, Emily Lee, Yeonsil Moon, Hosung Kim","doi":"10.1101/2025.03.19.25324269","DOIUrl":"https://doi.org/10.1101/2025.03.19.25324269","url":null,"abstract":"<p><p>Perivascular spaces (PVS) are cerebrospinal fluid-filled tunnels around brain blood vessels, crucial for the functions of the glymphatic system. Changes in PVS have been linked to vascular diseases and aging, necessitating accurate segmentation for further study. PVS segmentation poses challenges due to their small size, varying MRI appearances, and the scarcity of annotated data. We present a finely segmented PVS dataset from T2-weighted MRI scans, sourced from the Human Connectome Project Aging (HCP-Aging), encompassing 200 subjects aged 30 to 100. Our approach utilizes a combination of unsupervised and deep learning techniques with manual corrections to ensure high accuracy. This dataset aims to facilitate research on PVS dynamics across different ages and to explore their link to cognitive decline. It also supports the development of advanced image segmentation algorithms, contributing to improved medical imaging automation and the early detection of neurodegenerative diseases.</p>","PeriodicalId":94281,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957161/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756985","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":"Leveraging Temporal Learning with Dynamic Range (TLDR) for Enhanced Prediction of Outcomes in Recurrent Exposure and Treatment Settings in Electronic Health Records.","authors":"Jingya Cheng, Jonas Hügel, Jiazi Tian, Alaleh Azhir, Shawn N Murphy, Jeffrey G Klann, Hossein Estiri","doi":"10.1101/2025.03.19.25324272","DOIUrl":"https://doi.org/10.1101/2025.03.19.25324272","url":null,"abstract":"<p><strong>Background: </strong>The temporal sequence of clinical events is crucial in outcomes research, yet standard machine learning (ML) approaches often overlook this aspect in electronic health records (EHRs), limiting predictive accuracy.</p><p><strong>Methods: </strong>We introduce Temporal Learning with Dynamic Range (TLDR), a time-sensitive ML framework, to identify risk factors for post-acute sequelae of SARS-CoV-2 infection (PASC). Using longitudinal EHR data from over 85,000 patients in the Precision PASC Research Cohort (P2RC) from a large integrated academic medical center, we compare TLDR against a conventional atemporal ML model.</p><p><strong>Results: </strong>TLDR demonstrated superior predictive performance, achieving a mean AUROC of 0.791 compared to 0.668 for the benchmark, marking an 18.4% improvement. Additionally, TLDR's mean PRAUC of 0.590 significantly outperformed the benchmark's 0.421, a 40.14% increase. The framework exhibited improved generalizability with a lower mean overfitting index (-0.028), highlighting its robustness. Beyond predictive gains, TLDR's use of time-stamped features enhanced interpretability, offering a more precise characterization of individual patient records.</p><p><strong>Discussion: </strong>TLDR effectively captures exposure-outcome associations and offers flexibility in time-stamping strategies to suit diverse clinical research needs.</p><p><strong>Conclusion: </strong>TLDR provides a simple yet effective approach for integrating dynamic temporal windows into predictive modeling. It is available within the MLHO R package to support further exploration of recurrent treatment and exposure patterns in various clinical settings.</p>","PeriodicalId":94281,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957182/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143757103","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":"Artificial intelligence automation of echocardiographic measurements.","authors":"Yuki Sahashi, Hirotaka Ieki, Victoria Yuan, Matthew Christensen, Milos Vukadinovic, Christina Binder-Rodriguez, Justin Rhee, James Y Zou, Bryan He, Paul Cheng, David Ouyang","doi":"10.1101/2025.03.18.25324215","DOIUrl":"https://doi.org/10.1101/2025.03.18.25324215","url":null,"abstract":"<p><strong>Background: </strong>Accurate measurement of echocardiographic parameters is crucial for the diagnosis of cardiovascular disease and tracking of change over time, however manual assessment is time-consuming and can be imprecise. Artificial intelligence (AI) has the potential to reduce clinician burden by automating the time-intensive task of comprehensive measurement of echocardiographic parameters.</p><p><strong>Methods: </strong>We developed and validated open-sourced deep learning semantic segmentation models for the automated measurement of 18 anatomic and Doppler measurements in echocardiography. The outputs of segmentation models were compared to sonographer measurements from two institutions to access accuracy and precision.</p><p><strong>Results: </strong>We utilized 877,983 echocardiographic measurements from 155,215 studies from Cedars-Sinai Medical Center (CSMC) to develop EchoNet-Measurements, an open-source deep learning model for echocardiographic annotation. The models demonstrated a good correlation when compared with sonographer measurements from held-out data from CSMC and an independent external validation dataset from Stanford Healthcare (SHC). Measurements across all nine B-mode and nine Doppler measurements had high accuracy (an overall R ² of 0.967 (0.965 - 0.970) in the held-out CSMC dataset and 0.987 (0.984 - 0.989) in the SHC dataset). When evaluated end-to-end on a temporally distinct 2,103 studies at CSMC, EchoNet-Measurements performed well an overall R2 of 0.981 (0.976 - 0.984). Performance was consistent across patient characteristics including sex and atrial fibrillation status.</p><p><strong>Conclusion: </strong>EchoNet-Measurement achieves high accuracy in automated echocardiographic measurement that is comparable to expert sonographers. This open-source model provides the foundation for future developments in AI applied to echocardiography.</p><p><strong>Clinical perspective: </strong><b>What Is New?:</b> We developed EchoNet-Measurements, the first publicly available deep learning framework for comprehensive automated echocardiographic measurements.We assessed the performance of EchoNet-Measurements, showing good precision and accuracy compared to human sonographers and cardiologists across multiple healthcare systems.<b>What Are the Clinical Implications?:</b> Deep-learning automated echocardiographic measurements can be conducted in a fraction of a second, reducing the time burden on sonographers and standardizing measurements, and potentially enhance reproducibility and diagnostic reliability.This open-source model provides broad opportunities for widespread adoption in both clinical use and research, including in resource-limited settings.</p>","PeriodicalId":94281,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957091/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143757037","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}