medRxiv : the preprint server for health sciences最新文献

{"title":"Neuroimaging-AI endophenotypes reveal underlying mechanisms and genetic factors contributing to progression and development of four brain disorders.","authors":"Junhao Wen, Ioanna Skampardoni, Ye Ella Tian, Zhijian Yang, Yuhan Cui, Guray Erus, Gyujoon Hwang, Erdem Varol, Aleix Boquet-Pujadas, Ganesh B Chand, Ilya Nasrallah, Theodore D Satterthwaite, Haochang Shou, Li Shen, Arthur W Toga, Andrew Zalesky, Christos Davatzikos","doi":"10.1101/2023.08.16.23294179","DOIUrl":"10.1101/2023.08.16.23294179","url":null,"abstract":"<p><p>Recent work leveraging artificial intelligence has offered promise to dissect disease heterogeneity by identifying complex intermediate brain phenotypes, called dimensional neuroimaging endophenotypes (DNEs). We advance the argument that these DNEs capture the degree of expression of respective neuroanatomical patterns measured, offering a dimensional neuroanatomical representation for studying disease heterogeneity and similarities of neurologic and neuropsychiatric diseases. We investigate the presence of nine DNEs derived from independent yet harmonized studies on Alzheimer's disease, autism spectrum disorder, late-life depression, and schizophrenia in the UK Biobank study. Phenome-wide associations align with genome-wide associations, revealing 31 genomic loci (P-value<5×10^-8/9) associated with the nine DNEs.The nine DNEs, along with their polygenic risk scores, significantly enhanced the predictive accuracy for 14 systemic disease categories, particularly for conditions related to mental health and the central nervous system, as well as mortality outcomes. These findings underscore the potential of the nine DNEs to capture the expression of disease-related brain phenotypes in individuals of the general population and to relate such measures with genetics, lifestyle factors, and chronic diseases.</p>","PeriodicalId":18659,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/98/fa/nihpp-2023.08.16.23294179v1.PMC10473785.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10210814","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":"Nigral volume loss in prodromal, early, and moderate Parkinson's disease.","authors":"Jason Langley, Kristy S Hwang, Daniel E Huddleston, Xiaoping P Hu","doi":"10.1101/2023.08.19.23294281","DOIUrl":"10.1101/2023.08.19.23294281","url":null,"abstract":"<p><p>The loss of melanized neurons in the substantia nigra pars compacta (SNc) is a hallmark pathology in Parkinson's disease (PD). Melanized neurons in SNc can be visualized in vivo using magnetization transfer (MT) effects. Nigral volume was extracted in data acquired with a MT-prepared gradient echo sequence in 50 controls, 90 non-manifest carriers (46 LRRK2 and 44 GBA1 nonmanifest carriers), 217 prodromal hyposmic participants, 76 participants with rapid eye movement sleep behavior disorder (RBD), 194 de novo PD patients and 26 moderate PD patients from the Parkinson's Progressive Markers Initiative. No difference in nigral volume was seen between controls and LRRK2 and GBA1 non-manifest carriers ( <i>F</i> =0.732; <i>P</i> =0.483). A significant main effect in group was observed between controls, prodromal hyposmic participants, RBD participants, and overt PD patients ( <i>F</i> =9.882; <i>P</i> <10 ^-3 ). This study shows that nigral depigmentation can be robustly detected in prodromal and overt PD populations.</p>","PeriodicalId":18659,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10462207/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10148260","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":"Pharmacokinetic effects of a single-dose nutritional ketone ester supplement on brain glucose and ketone metabolism in alcohol use disorder.","authors":"Xinyi Li, Anthony J Young, Zhenhao Shi, Juliana Byanyima, Sianneh Vesslee, Rishika Reddy, Timothy Pond, Mark Elliott, Ravinder Reddy, Robert K Doot, Jan-Willem van der Veen, Henry R Kranzler, Ravi Prakash Reddy Nanga, Jacob G Dubroff, Corinde E Wiers","doi":"10.1101/2023.09.25.23296090","DOIUrl":"10.1101/2023.09.25.23296090","url":null,"abstract":"<p><p>Acute alcohol intake decreases brain glucose metabolism and increases brain uptake of acetate, a metabolite of alcohol. This shift in energy utilization persists beyond acute intoxication in individuals with alcohol use disorder (AUD), and may contribute to alcohol craving. We recently found that ketone therapies decrease alcohol withdrawal and alcohol craving in AUD. Here, we studied the effects of a single-dose ketone ester (KE) supplement on brain energy metabolism and alcohol craving. Five AUD and five healthy control (HC) participants underwent two ¹⁸ F-fluorodeoxyglucose positron emission tomography (PET) scans, after consumption of 395 mg/kg KE or without (baseline), in randomized order. In the AUD group, KE reduced alcohol craving scores compared to baseline. KE decreased blood glucose levels and elevated blood β-hydroxybutyrate (BHB) levels compared to baseline in both groups. Whole-brain voxel-wise maps of the cerebral metabolic rate of glucose (CMRglc) decreased by 17% in both groups, with the largest KE-induced CMRglc reductions in the frontal, occipital, and cingulate cortices, hippocampus, amygdala, and insula. There were no group differences between AUD and HC in blood or FDG measures, and no correlations between reductions in craving with CMRglc. Cingulate BHB levels, as assessed with ¹ H-magnetic resonance spectroscopy in 5 participant with AUD, increased 3-fold with KE compared to baseleline. In sum, administration of a single dose of KE rapidly shifted brain energetics from glucose to ketone metabolism in HC and AUD. KE also reduced ratings of alcohol craving, demonstrating its potential clinical effectiveness for supporting brain health and alcohol craving in AUD.</p>","PeriodicalId":18659,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10557835/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41167352","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":"Hemodynamics Indicates Differences Between Patients With And Without A Stroke Outcome After Left Ventricular Assist Device Implantation.","authors":"Akshita Sahni, Sreeparna Majee, Jay D Pal, Erin E McIntyre, Kelly Cao, Debanjan Mukherjee","doi":"10.1101/2023.08.03.23292572","DOIUrl":"10.1101/2023.08.03.23292572","url":null,"abstract":"<p><p>Stroke remains a leading cause of complications and mortality in heart failure patients treated with a Left Ventricular Assist Device (LVAD). Hemodynamics plays a central role underlying post-LVAD stroke risk and etiology. Yet, detailed quantitative assessment of hemodynamic variables and their relation to stroke outcomes in patients on LVAD support remains a challenge. Modalities for pre-implantation assessment of post-implantation hemodynamics can help address this challenge. We present an <i>in silico</i> hemodynamics analysis for a digital twin cohort 12 patients on LVAD support; 6 with reported stroke outcomes and 6 without. For each patient we created a post-implant twin with the LVAD outflow graft reconstructed from cardiac-gated CT images; and a pre-implant twin of an estimated baseline flow by removing the LVAD outflow graft and driving flow from the aortic valve opening. Hemodynamics was characterized using descriptors for helical flow, vortex generation, and wall shear stress. We observed higher average values for descriptors of positive helical flow, vortex generation, and wall shear stress, across the 6 cases with stroke outcomes when compared with cases without stroke. When the descriptors for LVAD-driven flow were compared against estimated pre-implantation flow, extent of positive helicity was higher, and vorticity and wall shear were lower in cases with stroke compared to those without. Our study suggests that quantitative analysis of hemodynamics after LVAD implantation; and hemodynamic alterations from a pre-implant flow scenario, can potentially reveal hidden information linked to stroke outcomes during LVAD support. This has broad implications on understanding stroke etiology; and using patient digital twins for LVAD treatment planning, surgical optimization, and efficacy assessment.</p>","PeriodicalId":18659,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10441504/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10042452","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":"Online Database of Clinical Algorithms with Race and Ethnicity.","authors":"Shyam Visweswaran, Eugene M Sadhu, Michele M Morris, Anushka R Vis, Malarkodi Jebathilagam Samayamuthu","doi":"10.1101/2023.07.04.23292231","DOIUrl":"10.1101/2023.07.04.23292231","url":null,"abstract":"<p><p>Some clinical algorithms incorporate an individual's race, ethnicity, or both as an input variable or predictor in determining diagnoses, prognoses, treatment plans, or risk assessments. Inappropriate use of race and ethnicity in clinical algorithms at the point of care may exacerbate health disparities and promote harmful practices of race-based medicine. We identified 42 risk calculators that use race as a predictor, five laboratory test results with different reference ranges recommended for different races, one therapy recommendation based on race, 15 medications with guidelines for initiation and monitoring based on race, and four medical devices with differential racial performance. Information on these clinical algorithms are freely available at http://www.clinical-algorithms-with-race-and-ethnicity.org. This resource aims to raise awareness about the use of race in clinical algorithms and to track the progress made toward eliminating its inappropriate use. The database will be actively updated to include clinical algorithms based on race that were missed, along with additional characteristics of these algorithms.</p>","PeriodicalId":18659,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/79/da/nihpp-2023.07.04.23292231v1.PMC10350134.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10250670","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":"A Linear Mixed Model with Measurement Error Correction (LMM-MEC): A Method for Summary-data-based Multivariable Mendelian Randomization.","authors":"Ming Ding, Fei Zou","doi":"10.1101/2023.04.25.23289099","DOIUrl":"10.1101/2023.04.25.23289099","url":null,"abstract":"<p><p>Summary-data-based multivariable Mendelian randomization (MVMR) methods, such as MVMR-Egger, MVMR-IVW, MVMR median-based, and MVMR-PRESSO, assess the causal effects of multiple risk factors on disease. However, accounting for variances in summary statistics related to risk factors remains a challenge. We propose a linear mixed model with measurement error correction (LMM-MEC) that accounts for the variance of summary statistics for both disease outcomes and risk factors. In step I, a linear mixed model is applied to account for the variance in disease summary statistics. Specifically, if heterogeneity is present in disease summary statistics, we treat it as a random effect and adopt an iteratively re-weighted least squares algorithm to estimate causal effects. In step II, we treat the variance in the summary statistics of risk factors as multiple measurement errors and apply a regression calibration method for simultaneous multiple measurement error correction. In a simulation study, when using independent genetic variants as instrumental variables (IV), our method showed comparable performance to existing MVMR methods under conditions of no pleiotropy or balanced pleiotropy with the outcome, and it exhibited higher coverage rates and power under directional pleiotropy. Similar findings were observed when using genetic variants with low to moderate linkage disequilibrium (LD) (0 < <i>ρ</i> ² ≤ 0.3) as IVs, although coverage rates reduced for all methods compared to using independent genetic variants as IVs. In the application study, we examined causal associations between correlated cholesterol biomarkers and longevity. By including 739 genetic variants selected based on P values <5×10 ^-5 from GWAS and allowing for low LD ( <i>ρ</i> ² ≤ 0.1), our method identified that large LDL-c were causally associated with lower likelihood of achieving longevity.</p>","PeriodicalId":18659,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10168515/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9789776","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":"After the Infection: A Survey of Pathogens and Non-communicable Human Disease.","authors":"Michael Lape, Daniel Schnell, Sreeja Parameswaran, Kevin Ernst, Shannon O'Connor, Nathan Salomonis, Lisa J Martin, Brett M Harnett, Leah C Kottyan, Matthew T Weirauch","doi":"10.1101/2023.09.14.23295428","DOIUrl":"10.1101/2023.09.14.23295428","url":null,"abstract":"<p><p>There are many well-established relationships between pathogens and human disease, but far fewer when focusing on non-communicable diseases (NCDs). We leverage data from The UK Biobank and TriNetX to perform a systematic survey across 20 pathogens and 426 diseases, primarily NCDs. To this end, we assess the association between disease status and infection history proxies. We identify 206 pathogen-disease pairs that replicate in both cohorts. We replicate many established relationships, including <i>Helicobacter pylori</i> with several gastroenterological diseases and connections between Epstein-Barr virus with multiple sclerosis and lupus. Overall, our approach identified evidence of association for 15 pathogens and 96 distinct diseases, including a currently controversial link between human cytomegalovirus (CMV) and ulcerative colitis (UC). We validate this connection through two orthogonal analyses, revealing increased CMV gene expression in UC patients and enrichment for UC genetic risk signal near human genes that have altered expression upon CMV infection. Collectively, these results form a foundation for future investigations into mechanistic roles played by pathogens in NCDs. All results are easily accessible on our website, https://tf.cchmc.org/pathogen-disease.</p>","PeriodicalId":18659,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/3d/2c/nihpp-2023.09.14.23295428v1.PMC10516055.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41104621","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 Extra-Islet Pancreas Supports Autoimmunity in Human Type 1 Diabetes.","authors":"G L Barlow, C M Schürch, S S Bhate, D Phillips, A Young, S Dong, H A Martinez, G Kaber, N Nagy, S Ramachandran, J Meng, E Korpos, J A Bluestone, G P Nolan, P L Bollyky","doi":"10.1101/2023.03.15.23287145","DOIUrl":"10.1101/2023.03.15.23287145","url":null,"abstract":"<p><p>In autoimmune Type 1 diabetes (T1D), immune cells infiltrate and destroy the islets of Langerhans - islands of endocrine tissue dispersed throughout the pancreas. However, the contribution of cellular programs outside islets to insulitis is unclear. Here, using CO-Detection by indEXing (CODEX) tissue imaging and cadaveric pancreas samples, we simultaneously examine islet and extra-islet inflammation in human T1D. We identify four sub-states of inflamed islets characterized by the activation profiles of CD8 ⁺ T cells enriched in islets relative to the surrounding tissue. We further find that the extra-islet space of lobules with extensive islet-infiltration differs from the extra-islet space of less infiltrated areas within the same tissue section. Finally, we identify lymphoid structures away from islets enriched in CD45RA ⁺ T cells - a population also enriched in one of the inflamed islet sub-states. Together, these data help define the coordination between islets and the extra-islet pancreas in the pathogenesis of human T1D.</p>","PeriodicalId":18659,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10055577/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9197159","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":"Keyphrase Identification Using Minimal Labeled Data with Hierarchical Contexts and Transfer Learning.","authors":"Rohan Goli, Keerthana Komatineni, Shailesh Alluri, Nina Hubig, Hua Min, Yang Gong, Dean F Sittig, Lior Rennert, David Robinson, Paul Biondich, Adam Wright, Christian Nøhr, Timothy Law, Arild Faxvaag, Aneesa Weaver, Ronald Gimbel, Xia Jing","doi":"10.1101/2023.01.26.23285060","DOIUrl":"10.1101/2023.01.26.23285060","url":null,"abstract":"<p><strong>Background: </strong>Interoperable clinical decision support system (CDSS) rules provide a pathway to interoperability, a well-recognized challenge in health information technology. Building an ontology facilitates creating interoperable CDSS rules, which can be achieved by identifying the keyphrases (KP) from the existing literature. Ontology construction is traditionally a manual effort by human domain experts, and the newly advanced natural language processing techniques, such as KP identification, can be a critical complementary automatic part of building ontology. However, KP identification requires human expertise, consensus, and contextual understanding for data labeling.</p><p><strong>Methods: </strong>This paper presents a semi-supervised KP identification framework (long short-term memory-based encoders and the conditional random fields -based decoder models, BiLSTM-CRF) using minimal human labeled data based on hierarchical attention (i.e., at word, sentence, and abstract levels) over the documents and domain adaptation. We created synthetic labels for initial training and human-labeled data for fine-tuning. We also tested different options during NLP preprocessing and ML training to optimize the ML pipeline.</p><p><strong>Results: </strong>Our method outperforms the prior neural architectures by learning through synthetic labels for initial training, document-level contextual learning, language modeling, and fine-tuning with limited gold standard label data. After comparison, we found that the BIO encoding schema performed slightly better than Blue, and domain adaptation techniques can improve the quality of synthetic labels. In addition, document-level context, pre-trained LM, and pre-trained WE all contributed to better model performance in our tasks. Add 2 to 4 human-labeled documents for every 100 synthetic labeled documents improves the model performance without exhausting human-labeled documents too quickly.</p><p><strong>Conclusions: </strong>To the best of our knowledge, this is the first functional framework for the CDSS sub-domain to identify KPs, which is trained on limited human labeled data. It contributes to the general natural language processing (NLP) architectures in areas such as clinical NLP, where manual data labeling is challenging, and light-weighted deep learning models play an important role in real-time KP identification as a complementary approach to human experts' effort.</p>","PeriodicalId":18659,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/b9/97/nihpp-2023.01.26.23285060v2.PMC10246160.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10009443","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":"Advancing Efficacy Prediction for EHR-based Emulated Trials in Repurposing Heart Failure Therapies.","authors":"Nansu Zong, Shaika Chowdhury, Shibo Zhou, Sivaraman Rajaganapathy, Yue Yu, Liewei Wang, Qiying Dai, Pengyang Li, Xiaoke Liu, Suzette J Bielinski, Jun Chen, Yongbin Chen, James R Cerhan","doi":"10.1101/2023.05.25.23290531","DOIUrl":"10.1101/2023.05.25.23290531","url":null,"abstract":"<p><strong>Introduction: </strong>The High mortality rates associated with heart failure (HF) have propelled the strategy of drug repurposing, which seeks new therapeutic uses for existing, approved drugs to enhance the management of HF symptoms effectively. An emerging trend focuses on utilizing real-world data, like EHR, to mimic randomized controlled trials (RCTs) for evaluating treatment outcomes through what are known as emulated trials (ET). Nonetheless, the intricacies inherent in EHR data-comprising detailed patient histories in databases, the omission of certain biomarkers or specific diagnostic tests, and partial records of symptoms-introduce notable discrepancies between EHR data and the stringent standards of RCTs. This gap poses a substantial challenge in conducting an ET to accurately predict treatment efficacy.</p><p><strong>Objective: </strong>The objective of this research is to predict the efficacy of drugs repurposed for HF in randomized trials by leveraging EHR in ET.</p><p><strong>Methods: </strong>We proposed an ET framework to predict drug efficacy, integrating target prediction based on biomedical databases with statistical analysis using EHR data. Specifically, we developed a novel target prediction model that learns low-dimensional representations of drug molecules, protein sequences, and diverse biomedical associations from a knowledge graph. Additionally, we crafted strategies to improve the prediction by considering the interactions between HF drugs and biological factors in the context of HF prognostic markers.</p><p><strong>Results: </strong>Our validation of the drug-target prediction model against the BETA benchmark demonstrated superior performance, with an average AUCROC of 97.7%, PRAUC of 97.4%, F1 score of 93.1%, and a General Score of 96.1%, surpassing existing baseline algorithms. Further analysis of our ET framework on identifying 17 repurposed drugs-derived from 266 phase 3 HF RCTs-using data from 59,000 patients at the Mayo Clinic highlighted the framework's remarkable predictive accuracy. This analysis took into account various factors such as biological variables (e.g., gender, age, ethnicity), HF medications (e.g., ACE inhibitors, Beta-blockers, ARBs, Loop Diuretics), types of HF (HFpEF and HFrEF), confounders, and prognostic markers (e.g., NT-proBNP, bUn, creatinine, and hemoglobin). The ET framework significantly improved the accuracy compared to the baseline efficacy analysis that utilized EHR data. Notably, the best results were improved in AUC-ROC from 75.71% to 93.57% and in PRAUC from 78.66% to 90.34%, compared to the baseline models.</p><p><strong>Conclusion: </strong>Our study presents an ET framework that significantly enhances drug efficacy emulation by integrating EHR-based analysis with target prediction. We demonstrated substantial success in predicting the efficacy of 17 HF drugs repurposed for phase 3 RCTs, showcasing the framework's potential in advancing HF treatment strategies.</p>","PeriodicalId":18659,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/b0/45/nihpp-2023.05.25.23290531v1.PMC10312819.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9754104","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}