Sepsis online: learning while doing to understand biology and treatment

脓毒症在线：边做边学，了解生物学和治疗

• 批准号: 10636964
• 负责人: Christopher Warren Seymour
• 金额: $ 47.34万
• 依托单位: UNIVERSITY OF PITTSBURGH AT PITTSBURGH
• 依托单位国家: 美国
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-08-02 至 2026-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10636964
• 关键词: American; Artificial Intelligence; Award; Biological; Biological Markers; Biology; Blood; Cessation of life; Collection; Computational Biology; E-learning; Early treatment; Electronic Health Record; Ethers; Funding; Hospitalization; Immunology; Inflammation; Integrated Health Care Systems; Laboratories; Learning; Machine Learning; Mentorship; Methods; Molecular; National Institute of General Medical Sciences; Outcome; Patients; Policies; Psychological reinforcement; Science; Scientist; Sepsis; Systems Biology; Testing; Time; Uncertainty; Work; clinical decision-making; clinical translation; health information technology; improved; improved outcome; insight; machine learning method; microbiome; pathogen; personalized care; point of care; pressure; programs; targeted treatment; treatment optimization; treatment response

PROJECT SUMMARY / ABSTRACT More than 1 million Americans are hospitalized with sepsis each year, and nearly one in five don’t survive. Most efforts to reduce sepsis deaths begin with the premise that patients are largely similar, and that ether moving treatment earlier or targeting therapeutics to a single mechanism will improve outcomes. In prior work funded by a NIGMS R35 award, we derived sepsis endotypes using a suite of machine learning methods inside the electronic health records (EHR) in a large integrated health system. These endotypes differed in biology, outcomes, and treatment response, and were reproduced in thousands of patients. But how will they lead to precision care? In this Renewal, we will leverage our clinical translational laboratory and remnant blood collection to better understand the biology of sepsis endotypes and explore new domains related to pathogen, microbiome, and molecular mechanisms. We will use Bayesian causal networks and reinforcement learning to optimize treatment policies over endotypes in more than 10 million EHR encounters. Finally, we will move learning online and embed endotypes inside the EHR at the point-of-care. These steps will take the science of sepsis endotypes and inform clinical decisions made under time pressure and uncertainty. By testing endotype treatment policies at the “live-edge”, we will strengthen causal inference, mechanistic insight, and learn while doing. My program will be supervised by external advisory boards with expertise in machine learning, inflammation, immunology, computational and systems biology, causal methods, artificial intelligence, and health information technology. This work will further develop my clinical-translational laboratory and cross-cutting mentorship of junior scientists.

项目摘要/摘要

项目成果

Launching a comparative effectiveness adaptive platform trial of monoclonal antibodies for COVID-19 in 21 days.

• DOI: 10.1016/j.cct.2021.106652
• 发表时间: 2022-03
• 期刊: Contemporary clinical trials
• 影响因子: 2.2
• 作者: McCreary EK;Bariola JR;Minnier T;Wadas RJ;Shovel JA;Albin D;Marroquin OC;Schmidhofer M;Wisniewski MK;Nace DA;Sullivan C;Axe M;Meyers R;Khadem T;Garrard W;Collins K;Wells A;Bart RD;Linstrum K;Montgomery SK;Haidar G;Snyder GM;McVerry BJ;Seymour CW;Yealy DM;Huang DT;Angus DC
• 通讯作者: Angus DC

Arguing for Adaptive Clinical Trials in Sepsis.

• DOI: 10.3389/fimmu.2018.01502
• 发表时间: 2018
• 期刊: Frontiers in immunology
• 影响因子: 7.3
• 作者: Talisa VB;Yende S;Seymour CW;Angus DC
• 通讯作者: Angus DC

Hydrocortisone, Vitamin C, and Thiamine for Treatment of Sepsis: Making Evidence Matter.

氢化可的松、维生素 C 和硫胺素治疗脓毒症：让证据发挥作用。

• DOI: 10.1001/jama.2020.26029
• 发表时间: 2021
• 期刊: JAMA
• 作者: Walter,KristinL;Seymour,ChristopherW
• 通讯作者: Seymour,ChristopherW

Characterizing systematic challenges in sample size determination for sepsis trials.

描述脓毒症试验样本量确定中的系统挑战。

• DOI: 10.1007/s00134-022-06691-4
• 发表时间: 2022
• 期刊: Intensive care medicine
• 影响因子: 38.9
• 作者: Tran,Alexandre;Fernando,ShannonM;Rochwerg,Bram;Seymour,ChristopherW;Cook,DeborahJ
• 通讯作者: Cook,DeborahJ

Lopinavir-ritonavir and hydroxychloroquine for critically ill patients with COVID-19: REMAP-CAP randomized controlled trial.

• DOI: 10.1007/s00134-021-06448-5
• 发表时间: 2021-08
• 期刊: Intensive care medicine
• 影响因子: 38.9
• 作者: Arabi YM;Gordon AC;Derde LPG;Nichol AD;Murthy S;Beidh FA;Annane D;Swaidan LA;Beane A;Beasley R;Berry LR;Bhimani Z;Bonten MJM;Bradbury CA;Brunkhorst FM;Buxton M;Buzgau A;Cheng A;De Jong M;Detry MA;Duffy EJ;Estcourt LJ;Fitzgerald M;Fowler R;Girard TD;Goligher EC;Goossens H;Haniffa R;Higgins AM;Hills TE;Horvat CM;Huang DT;King AJ;Lamontagne F;Lawler PR;Lewis R;Linstrum K;Litton E;Lorenzi E;Malakouti S;McAuley DF;McGlothlin A;Mcguinness S;McVerry BJ;Montgomery SK;Morpeth SC;Mouncey PR;Orr K;Parke R;Parker JC;Patanwala AE;Rowan KM;Santos MS;Saunders CT;Seymour CW;Shankar-Hari M;Tong SYC;Turgeon AF;Turner AM;Van de Veerdonk FL;Zarychanski R;Green C;Berry S;Marshall JC;McArthur C;Angus DC;Webb SA;REMAP-CAP Investigators
• 通讯作者: REMAP-CAP Investigators