Federated Learning used for predicting outcomes in SARS-COV-2 patients.
Ontology highlight
ABSTRACT:
SUBMITTER: Flores M
PROVIDER: S-EPMC7805458 | biostudies-literature | 2021 Jan
REPOSITORIES: biostudies-literature
Publications
Federated Learning used for predicting outcomes in SARS-COV-2 patients.
Flores Mona M Dayan Ittai I Roth Holger H Zhong Aoxiao A Harouni Ahmed A Gentili Amilcare A Abidin Anas A Liu Andrew A Costa Anthony A Wood Bradford B Tsai Chien-Sung CS Wang Chih-Hung CH Hsu Chun-Nan CN Lee C K CK Ruan Colleen C Xu Daguang D Wu Dufan D Huang Eddie E Kitamura Felipe F Lacey Griffin G César de Antônio Corradi Gustavo G Shin Hao-Hsin HH Obinata Hirofumi H Ren Hui H Crane Jason J Tetreault Jesse J Guan Jiahui J Garrett John J Park Jung Gil JG Dreyer Keith K Juluru Krishna K Kersten Kristopher K Bezerra Cavalcanti Rockenbach Marcio Aloisio MA Linguraru Marius M Haider Masoom M AbdelMaseeh Meena M Rieke Nicola N Damasceno Pablo P Cruz E Silva Pedro Mario PM Wang Pochuan P Xu Sheng S Kawano Shuichi S Sriswasdi Sira S Park Soo Young SY Grist Thomas T Buch Varun V Jantarabenjakul Watsamon W Wang Weichung W Tak Won Young WY Li Xiang X Lin Xihong X Kwon Fred F Gilbert Fiona F Kaggie Josh J Li Quanzheng Q Quraini Abood A Feng Andrew A Priest Andrew A Turkbey Baris B Glicksberg Benjamin B Bizzo Bernardo B Kim Byung Seok BS Tor-Diez Carlos C Lee Chia-Cheng CC Hsu Chia-Jung CJ Lin Chin C Lai Chiu-Ling CL Hess Christopher C Compas Colin C Bhatia Deepi D Oermann Eric E Leibovitz Evan E Sasaki Hisashi H Mori Hitoshi H Yang Isaac I Sohn Jae Ho JH Keshava Murthy Krishna Nand KN Fu Li-Chen LC Furtado de Mendonça Matheus Ribeiro MR Fralick Mike M Kang Min Kyu MK Adil Mohammad M Gangai Natalie N Vateekul Peerapon P Elnajjar Pierre P Hickman Sarah S Majumdar Sharmila S McLeod Shelley S Reed Sheridan S Graf Stefan S Harmon Stephanie S Kodama Tatsuya T Puthanakit Thanyawee T Mazzulli Tony T de Lima Lavor Vitor V Rakvongthai Yothin Y Lee Yu Rim YR Wen Yuhong Y
Research square 20210108
'Federated Learning' (FL) is a method to train Artificial Intelligence (AI) models with data from multiple sources while maintaining anonymity of the data thus removing many barriers to data sharing. During the SARS-COV-2 pandemic, 20 institutes collaborated on a healthcare FL study to predict future oxygen requirements of infected patients using inputs of vital signs, laboratory data, and chest x-rays, constituting the "EXAM" (EMR CXR AI Model) model. EXAM achieved an average Area Under the Cur ...[more]
Similar Datasets
Project description:Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site's data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare.
| S-EPMC9157510 | biostudies-literature
Project description:BackgroundPregnant people are particularly vulnerable to SARS-CoV-2 infection and to ensuing severe illness. Predicting adverse maternal and perinatal outcomes could aid clinicians in deciding on hospital admission and early initiation of treatment in affected individuals, streamlining the triaging processes.MethodsAn international repository of 1501 SARS-CoV-2-positive cases in pregnancy was created, consisting of demographic variables, patient comorbidities, laboratory markers, respiratory parameters, and COVID-19-related symptoms. Data were filtered, preprocessed, and feature selection methods were used to obtain the optimal feature subset for training a variety of machine learning models to predict maternal or fetal/neonatal death or critical illness.ResultsThe Random Forest model demonstrated the best performance among the trained models, correctly identifying 83.3% of the high-risk patients and 92.5% of the low-risk patients, with an overall accuracy of 89.0%, an AUC of 0.90 (95% Confidence Interval 0.83 to 0.95), and a recall, precision, and F1 score of 0.85, 0.94, and 0.89, respectively. This was achieved using a feature subset of 25 features containing patient characteristics, symptoms, clinical signs, and laboratory markers. These included maternal BMI, gravidity, parity, existence of pre-existing conditions, nicotine exposure, anti-hypertensive medication administration, fetal malformations, antenatal corticosteroid administration, presence of dyspnea, sore throat, fever, fatigue, duration of symptom phase, existence of COVID-19-related pneumonia, need for maternal oxygen administration, disease-related inpatient treatment, and lab markers including sFLT-1/PlGF ratio, platelet count, and LDH.ConclusionsWe present the first COVID-19 prognostication pipeline specifically for pregnant patients while utilizing a large SARS-CoV-2 in pregnancy data repository. Our model accurately identifies those at risk of severe illness or clinical deterioration, presenting a promising tool for advancing personalized medicine in pregnant patients with COVID-19.
| S-EPMC10394879 | biostudies-literature
Project description:The relentless evolution of SARS-CoV-2 poses a significant threat to public health, as it adapts to immune pressure from vaccines and natural infections. Gaining insights into potential antigenic changes is critical but challenging due to the vast sequence space. Here, we introduce the Machine Learning-guided Antigenic Evolution Prediction (MLAEP), which combines structure modeling, multi-task learning, and genetic algorithms to predict the viral fitness landscape and explore antigenic evolution via in silico directed evolution. By analyzing existing SARS-CoV-2 variants, MLAEP accurately infers variant order along antigenic evolutionary trajectories, correlating with corresponding sampling time. Our approach identified novel mutations in immunocompromised COVID-19 patients and emerging variants like XBB1.5. Additionally, MLAEP predictions were validated through in vitro neutralizing antibody binding assays, demonstrating that the predicted variants exhibited enhanced immune evasion. By profiling existing variants and predicting potential antigenic changes, MLAEP aids in vaccine development and enhances preparedness against future SARS-CoV-2 variants.
| S-EPMC10261845 | biostudies-literature
Project description:PurposeTo address the contentious data sharing across hospitals, this study adopted a novel approach, federated learning (FL), to establish an aggregate model for acute kidney injury (AKI) prediction in critically ill patients in Taiwan.MethodsThis study used data from the Critical Care Database of Taichung Veterans General Hospital (TCVGH) from 2015 to 2020 and electrical medical records of the intensive care units (ICUs) between 2018 and 2020 of four referral centers in different areas across Taiwan. AKI prediction models were trained and validated thereupon. An FL-based prediction model across hospitals was then established.ResultsThe study included 16,732 ICU admissions from the TCVGH and 38,424 ICU admissions from the other four hospitals. The complete model with 60 features and the parsimonious model with 21 features demonstrated comparable accuracies using extreme gradient boosting, neural network (NN), and random forest, with an area under the receiver-operating characteristic (AUROC) curve of approximately 0.90. The Shapley Additive Explanations plot demonstrated that the selected features were the key clinical components of AKI for critically ill patients. The AUROC curve of the established parsimonious model for external validation at the four hospitals ranged from 0.760 to 0.865. NN-based FL slightly improved the model performance at the four centers.ConclusionA reliable prediction model for AKI in ICU patients was developed with a lead time of 24 h, and it performed better when the novel FL platform across hospitals was implemented.Supplementary informationThe online version contains supplementary material available at 10.1007/s13755-023-00248-5.
| S-EPMC10562351 | biostudies-literature
Project description:Drug sensitivity prediction plays a crucial role in precision cancer therapy. Collaboration among medical institutions can lead to better performance in drug sensitivity prediction. However, patient privacy and data protection regulation remain a severe impediment to centralized prediction studies. For the first time, we proposed a federated drug sensitivity prediction model with high generalization, combining distributed data sources while protecting private data. Cell lines are first classified into three categories using the waterfall method. Focal loss for solving class imbalance is then embedded into the horizontal federated deep learning framework, i.e., HFDL-fl is presented. Applying HFDL-fl to homogeneous and heterogeneous data, we obtained HFDL-Cross and HFDL-Within. Our comprehensive experiments demonstrated that (i) collaboration by HFDL-fl outperforms private model on local data, (ii) focal loss function can effectively improve model performance to classify cell lines in sensitive and resistant categories, and (iii) HFDL-fl is not significantly affected by data heterogeneity. To summarize, HFDL-fl provides a valuable solution to break down the barriers between medical institutions for privacy-preserving drug sensitivity prediction and therefore facilitates the development of cancer precision medicine and other privacy-related biomedical research.
| S-EPMC10427996 | biostudies-literature
Project description:Glioblastoma is a highly aggressive cancer associated with a dismal prognosis, with a mere 5% of patients surviving beyond five years post diagnosis. Current therapeutic modalities encompass surgical intervention, radiotherapy, chemotherapy, and immune checkpoint inhibitors (ICBs). However, the efficacy of ICBs remains limited in glioblastoma patients, necessitating a proactive approach to anticipate treatment response and resistance. In this comprehensive study, we conducted a rigorous analysis involving two distinct glioblastoma patient cohorts subjected to PD-1 blockade treatments. Our investigation revealed that a significant portion (60%) of patients exhibit persistent disease progression despite ICB intervention. To elucidate the underpinnings of resistance, we characterized the immune profiles of glioblastoma patients with continued cancer progression following anti-PD1 therapy. These profiles revealed multifaceted defects, encompassing compromised macrophage, monocyte, and T follicular helper responses, impaired antigen presentation, aberrant regulatory T cell (Tregs) responses, and heightened expression of immunosuppressive molecules (TGFB, IL2RA, and CD276). Building upon these resistance profiles, we leveraged cutting-edge machine learning algorithms to develop predictive models and accompanying software. This innovative computational tool achieved remarkable success, accurately forecasting the progression status of 82.82% of the glioblastoma patients in our study following ICBs, based on their unique immune characteristics. In conclusion, our pioneering approach advocates for the personalization of immunotherapy in glioblastoma patients. By harnessing patient-specific attributes and computational predictions, we offer a promising avenue for the enhancement of clinical outcomes in the realm of immunotherapy. This paradigm shift towards tailored therapies underscores the potential to revolutionize the management of glioblastoma, opening new horizons for improved patient care.
| S-EPMC10813889 | biostudies-literature
Project description:To accelerate the discovery of novel drug candidates for Coronavirus Disease 2019 (COVID-19) therapeutics, we reported a series of machine learning (ML)-based models to accurately predict the anti-SARS-CoV-2 activities of screening compounds. We explored 6 popular ML algorithms in combination with 15 molecular descriptors for molecular structures from 9 screening assays in the COVID-19 OpenData Portal hosted by NCATS. As a result, the models constructed by k-nearest neighbors (KNN) using the molecular descriptor GAFF+RDKit achieved the best overall performance with the highest average accuracy of 0.68 and relatively high average area under the receiver operating characteristic curve of 0.74, better than other ML algorithms. Meanwhile, The KNN model for all assays using GAFF+RDKit descriptor outperformed using other descriptors. The overall performance of our developed models was better than REDIAL-2020 (R). A web server (https://clickff.org/amberweb/covid-19-cp) was developed to enable users to predict anti-SARS-CoV-2 activities of arbitrary compounds using the COVID-19-CP (P) models. Besides the descriptor-based machine learning models, we also developed graph-based Attentive FP (A) models for the 9 assays. We found that the Attentive FP models achieved a comparable performance to that of COVID-19-CP and outperformed the REDIAL-2020 models. The consensus prediction utilizing both COVID-19-CP and Attentive FP can significantly boost the prediction accuracy as assessed by comparing its performance with other three individual models (R, P, A) utilizing the Wilcoxon signed-rank test, thus can ultimately improve the success rate of COVID-19 drug discovery.
| S-EPMC10715801 | biostudies-literature
Project description: Not available
| S-BSST379 | biostudies-other
Project description:SARS-CoV-2 is a newly emerged coronavirus that caused the global COVID-19 outbreak in early 2020. COVID-19 is primarily associated with lung injury, but many other clinical symptoms such as loss of smell and taste demonstrated broad tissue tropism of the virus. Early SARS-CoV-2-host cell interactions and entry mechanisms remain poorly understood. Investigating SARS-CoV-2 infection in tissue culture, we found that the protease TMPRSS2 determines the entry pathway used by the virus. In the presence of TMPRSS2, the proteolytic process of SARS-CoV-2 was completed at the plasma membrane, and the virus rapidly entered the cells within 10 min in a pH-independent manner. When target cells lacked TMPRSS2 expression, the virus was endocytosed and sorted into endolysosomes, from which SARS-CoV-2 entered the cytosol via acid-activated cathepsin L protease 40-60 min post infection. Overexpression of TMPRSS2 in non-TMPRSS2 expressing cells abolished the dependence of infection on the cathepsin L pathway and restored sensitivity to the TMPRSS2 inhibitors. Together, our results indicate that SARS-CoV-2 infects cells through distinct, mutually exclusive entry routes and highlight the importance of TMPRSS2 for SARS-CoV-2 sorting into either pathway.
| S-SCDT-EMBOJ-2021-107821 | biostudies-other
Project description:Federated learning (FL) enables edge devices, such as Internet of Things devices (e.g., sensors), servers, and institutions (e.g., hospitals), to collaboratively train a machine learning (ML) model without sharing their private data. FL requires devices to exchange their ML parameters iteratively, and thus the time it requires to jointly learn a reliable model depends not only on the number of training steps but also on the ML parameter transmission time per step. In practice, FL parameter transmissions are often carried out by a multitude of participating devices over resource-limited communication networks, for example, wireless networks with limited bandwidth and power. Therefore, the repeated FL parameter transmission from edge devices induces a notable delay, which can be larger than the ML model training time by orders of magnitude. Hence, communication delay constitutes a major bottleneck in FL. Here, a communication-efficient FL framework is proposed to jointly improve the FL convergence time and the training loss. In this framework, a probabilistic device selection scheme is designed such that the devices that can significantly improve the convergence speed and training loss have higher probabilities of being selected for ML model transmission. To further reduce the FL convergence time, a quantization method is proposed to reduce the volume of the model parameters exchanged among devices, and an efficient wireless resource allocation scheme is developed. Simulation results show that the proposed FL framework can improve the identification accuracy and convergence time by up to 3.6% and 87% compared to standard FL.
| S-EPMC8092601 | biostudies-literature