Posts by Amir Safavi
Assessment of prescribed vs. achieved fluid balance during continuous renal replacement therapy and mortality outcome.
Link: https://doi.org/10.1371/journal.pone.0272913 Authors: Neyra, Javier A; Lambert, Joshua; Ortiz-Soriano, Victor; Cleland, Daniel; Colquitt, Jon; Adams, Paul; Bissell, Brittany D; Chan, Lili; Nadkarni, Girish N; Tolwani, Ashita; Goldstein, Stuart L Abstract: Fluid management during continuous renal replacement therapy (CRRT) requires accuracy in the prescription of desired patient fluid balance (FBGoal) and precision in the attainable patient…
Read MoreEnhancing convolutional neural network predictions of electrocardiograms with left ventricular dysfunction using a novel sub-waveform representation.
Link: https://doi.org/10.1016/j.cvdhj.2022.07.074 Authors: Honarvar, Hossein; Agarwal, Chirag; Somani, Sulaiman; Vaid, Akhil; Lampert, Joshua; Wanyan, Tingyi; Reddy, Vivek Y; Nadkarni, Girish N; Miotto, Riccardo; Zitnik, Marinka; Wang, Fei; Glicksberg, Benjamin S Abstract: Electrocardiogram (ECG) deep learning (DL) has promise to improve the outcomes of patients with cardiovascular abnormalities. In ECG DL, researchers often use convolutional neural…
Read MoreMachine learning for risk stratification in kidney disease.
Link: https://doi.org/10.1097/MNH.0000000000000832 Authors: Gulamali, Faris F; Sawant, Ashwin S; Nadkarni, Girish N Abstract: Risk stratification for chronic kidney is becoming increasingly important as a clinical tool for both treatment and prevention measures. The goal of this review is to identify how machine learning tools contribute and facilitate risk stratification in the clinical setting. The two…
Read MoreA first update on mapping the human genetic architecture of COVID-19.
Link: https://doi.org/10.1038/s41586-022-04826-7 Authors: , Abstract:
Read MoreFederated Learning in Risk Prediction: A Primer and Application to COVID-19-Associated Acute Kidney Injury.
Link: https://doi.org/10.1159/000525645 Authors: Gulamali, Faris F; Nadkarni, Girish N Abstract: Modern machine learning and deep learning algorithms require large amounts of data; however, data sharing between multiple healthcare institutions is limited by privacy and security concerns. Federated learning provides a functional alternative to the single-institution approach while avoiding the pitfalls of data sharing. In cross-silo…
Read MoreStudyU: A Platform for Designing and Conducting Innovative Digital N-of-1 Trials.
Link: https://doi.org/10.2196/35884 Authors: Konigorski, Stefan; Wernicke, Sarah; Slosarek, Tamara; Zenner, Alexander M; Strelow, Nils; Ruether, Darius F; Henschel, Florian; Manaswini, Manisha; Pottbäcker, Fabian; Edelman, Jonathan A; Owoyele, Babajide; Danieletto, Matteo; Golden, Eddye; Zweig, Micol; Nadkarni, Girish N; Böttinger, Erwin Abstract: N-of-1 trials are the gold standard study design to evaluate individual treatment effects and derive…
Read MoreClinical predictors of response to methotrexate in patients with rheumatoid arthritis: a machine learning approach using clinical trial data.
Link: https://doi.org/10.1186/s13075-022-02851-5 Authors: Duong, Stephanie Q; Crowson, Cynthia S; Athreya, Arjun; Atkinson, Elizabeth J; Davis, John M; Warrington, Kenneth J; Matteson, Eric L; Weinshilboum, Richard; Wang, Liewei; Myasoedova, Elena Abstract: Methotrexate is the preferred initial disease-modifying antirheumatic drug (DMARD) for rheumatoid arthritis (RA). However, clinically useful tools for individualized prediction of response to methotrexate treatment…
Read MoreCOVID-19 Vaccine Uptake Among Patients With Systemic Lupus Erythematosus in the American Midwest: The Lupus Midwest Network (LUMEN).
Link: https://doi.org/10.3899/jrheum.220220 Authors: Chevet, Baptiste; Figueroa-Parra, Gabriel; Yang, Jeffrey X; Hulshizer, Cassondra A; Gunderson, Tina M; Duong, Stephanie Q; Putman, Michael S; Barbour, Kamil E; Crowson, Cynthia S; Duarte-García, Alí Abstract: Patients with systemic lupus erythematosus (SLE) are at higher risk of poor outcomes from coronavirus disease 2019 (COVID-19). The vaccination rate among such patients…
Read MoreIntegration of feature vectors from raw laboratory, medication and procedure names improves the precision and recall of models to predict postoperative mortality and acute kidney injury.
Link: https://doi.org/10.1038/s41598-022-13879-7 Authors: Hofer, Ira S; Kupina, Marina; Laddaran, Lori; Halperin, Eran Abstract: Manuscripts that have successfully used machine learning (ML) to predict a variety of perioperative outcomes often use only a limited number of features selected by a clinician. We hypothesized that techniques leveraging a broad set of features for patient laboratory results, medications,…
Read MoreEpigenomic and transcriptomic analyses define core cell types, genes and targetable mechanisms for kidney disease.
Link: https://doi.org/10.1038/s41588-022-01097-w Authors: Liu, Hongbo; Doke, Tomohito; Guo, Dong; Sheng, Xin; Ma, Ziyuan; Park, Joseph; Vy, Ha My T; Nadkarni, Girish N; Abedini, Amin; Miao, Zhen; Palmer, Matthew; Voight, Benjamin F; Li, Hongzhe; Brown, Christopher D; Ritchie, Marylyn D; Shu, Yan; Susztak, Katalin Abstract: More than 800 million people suffer from kidney disease, yet the…
Read More