ICU Data Science Lab
Matthew Churpek, MD, MPH, PhD, Majid Afshar, MD, MSCR, and Anoop Mayampurath, PhD, are pulmonary and critical care physicians and clinical informaticians. The ICU Data Science Lab is an integrated data science laboratory, with a research focus on using electronic health record data combined with epidemiology, biostatistics and machine learning (ML) methods to improve the care of hospitalized patients.
Machine Learning at the Bedside
Up to 5% of hospitalized patients on the medical-surgical wards develop clinical deterioration requiring intensive care. To prevent clinical deterioration and keep patients out of intensive care, the Churpek-Afshar Lab uses machine learning techniques, such as natural language processing (NLP) and deep learning, to identify patients at risk for sepsis, acute kidney injury (AKI), acute respiratory distress syndrome (ARDS) and other syndromes of critical illness, as well as substance misuse.
The long-term goal of each of our initiatives is to develop and implement clinically useful algorithms and decision support tools to assist in the delivery of early, personalized care to decrease preventable death.
Post-Doctoral Research Associate
Post-Doctoral Research Associate
- William Parker, MD, MS, collaborating PI, University of Chicago
- Kyle Carey, MPH, data manager, University of Chicago
- Mary Akel, MPH, program manager, University of Chicago
- Dana Edelson, MD, collaborating scientist, University of Chicago
- Jay Koyner, MD, collaborating PI, University of Chicago
- Niranjan Karnik, MD, PhD, collaborating PI, Rush University
- Dmitriy Dligach, PhD, collaborating PI, Loyola University Chicago
- Cara Joyce, PhD, statistician, Loyola University Chicago
- Talar Markossian, PhD, collaborating scientist, Loyola University Chicago
- Melanie C. Wright, PhD, collaborating scientist, Idaho State University
- Sushant Govindan, MD, MSc, collaborating scientist, Kansas City VA/University of Kansas School of Medicine
- R. Spencer Schaefer, PharmD, collaborating analyst, Kansas City VA
- Andrea S. Uhl, program manager, Kansas City VA
- Mark W Craven, PhD, collaborating scientist, UW-Madison
- Oguzhan Alagoz, PhD, collaborating scientist, UW-Madison
- Elizabeth Salisbury-Afshar, MD, MPH, collaborating scientist, UW-Madison
- Joshua E. Medow, MD, collaborating scientist, UW-Madison Department of Neurosurgery
- Jacqueline Kruser, MD, MS, collaborating scientist, UW-Madison
- Syed Nabeel Zafar, MD, MPH, collaborating scientist, UW-Madison
- Priti Jani, MD, MPH, collaborating scientist, University of Chicago
- L. Nelson Sanchez-Pinto MD, MBI, collaborating scientist, Northwestern University
Sepsis Early Predication and Subphenotype Illumination Study (SEPSIS)
This project uses data from detailed multicenter electronic health record (EHR), clinical trial, and biomarker data combined with machine learning approaches to improve the identification, risk stratification, and discover important subphenotypes of sepsis to decrease preventable death from infection. In the future, our models will be implemented for earlier identification of sepsis, accurate risk stratification, and to deliver personalized care at the bedside. SEPSIS is funded by the National Institutes of Health. Dr. Churpek is the PI.
The goal of the next five years is to build upon our successful research on sepsis and address key gaps in the field through three future directions:
- Using natural language processing and deep learning to improve the identification and risk stratification of infected patients
- Identifying important subphenotypes using research biomarkers
- Using machine learning to develop personalized treatment algorithms
- NIH/NIGMS, R01GM123193 (PI: Matthew Churpek) (04/15/2017 - 03/31/2022)
- NIH/NIGMS, R35GM145330 (PI: Matthew Churpek) (05/01/2022 –02/28/2027)
- Churpek MM, Snyder A, Han X, Sokol S, Pettit N, Howell MD, Edelson DP. Quick Sepsis-related Organ Failure Assessment, Systemic Inflammatory Response Syndrome, and Early Warning Scores for Detecting Clinical Deterioration in Infected Patients outside the Intensive Care Unit. Am J Respir Crit Care Med. 2017 Apr 1;195(7):906-911. doi: 10.1164/rccm.201604-0854OC. PMID: 27649072; PMCID: PMC5387705.
- Churpek MM, Dumanian J, Dussault N, Bhavani SV, Carey KA, Gilbert ER, Arain E, Ye C, Winslow CJ, Shah NS, Afshar M, Edelson DP. Determining the Electronic Signature of Infection in Electronic Health Record Data. Crit Care Med. 2021 Jul 1;49(7):e673-e682. doi: 10.1097/CCM.0000000000004968. PMID: 33861547; PMCID: PMC8217098.
- Han X, Spicer A, Carey KA, Gilbert ER, Laiteerapong N, Shah NS, Winslow C, Afshar M, Kashiouris MG, Churpek MM. Identifying High-Risk Subphenotypes and Associated Harms From Delayed Antibiotic Orders and Delivery. Crit Care Med. 2021 Oct 1;49(10):1694-1705. doi: 10.1097/CCM.0000000000005054. PMID: 33938715; PMCID: PMC8448901.
Using Machine Learning to Identify, Risk Stratify, and Guide Personalized Treatment of COVID-19 Patients
To provide life-saving interventions for patients with COVID-19, this project aims to improve the early identification and risk stratification by developing novel machine learning models to identify, risk stratify and provide personalized treatment recommendations.
- Aim 1: Develop novel machine learning models to identify, risk stratify, and provide personalized treatment recommendations for patients with COVID-19.
- Aim 2: Develop a CDS tool graphical user interface (GUI) and test it in a simulation study.
Funding: DOD USAMRAA W81XWH-21-1-0009, PRMRP-Technology/Therapeutic Development Award-COVID:, (PI: Matthew Churpek) (01/31/2021 – 12/31/2024)
- Churpek MM, Gupta S, Spicer AB, Parker WF, Fahrenbach J, Brenner SK, Leaf DE; STOP-COVID Investigators. Hospital-Level Variation in Death for Critically Ill Patients with COVID-19. Am J Respir Crit Care Med. 2021 Apr 23;204(4):403–11. doi: 10.1164/rccm.202012-4547OC. Epub ahead of print. PMID: 33891529; PMCID: PMC8480242.
- Bhavani SV, Huang ES, Verhoef PA, Churpek MM. Novel Temperature Trajectory Subphenotypes in COVID-19. Chest. 2020 Dec;158(6):2436-2439. doi: 10.1016/j.chest.2020.07.027. Epub 2020 Jul 21. PMID: 32707182; PMCID: PMC7373058.
- Alagoz O, Sethi AK, Patterson BW, Churpek M, Safdar N. Effect of Timing of and Adherence to Social Distancing Measures on COVID-19 Burden in the United States: A Simulation Modeling Approach. Ann Intern Med. 2021 Jan;174(1):50-57. doi: 10.7326/M20-4096. Epub 2020 Oct 27. PMID: 33105091; PMCID: PMC7598093.
Developing a clinical decision support tool for the identification, diagnosis, and treatment of critical illness in hospitalized patients
Clinical deterioration is characterized as the physiological decompensation that occurs when a patient experiences worsening conditions or acute onset of a serious physiological disturbance. Our goal is to develop and implement a clinical decision support tool for the identification, diagnosis, and treatment of patients at high risk of deterioration to decrease preventable death.
- Aim 1: Develop machine learning models to identify patients at high risk of deterioration using both structured data and unstructured clinical notes.
- Aim 2: Develop models to predict the diagnosis that is causing the deterioration event and the potentially life-saving treatments that should be provided to high-risk patients.
- Aim 3: Develop a clinical decision support tool with a graphical user interface incorporating the models from Aims 1 and 2 via user-centered design principles and then test its effectiveness, efficiency, and user satisfaction in a case-based simulation study.
Funding: NIH/NHLBI, 1R01HL157262 (PI: Matthew Churpek) (08/01/2021 – 07/31/2025)
- Churpek MM, Yuen TC, Winslow C, Meltzer DO, Kattan MW, Edelson DP. Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards. Crit Care Med. 2016 Feb;44(2):368-74. doi: 10.1097/CCM.0000000000001571. PMID: 26771782; PMCID: PMC4736499.
- Churpek MM, Yuen TC, Winslow C, Robicsek AA, Meltzer DO, Gibbons RD, Edelson DP. Multicenter development and validation of a risk stratification tool for ward patients. Am J Respir Crit Care Med. 2014 Sep 15;190(6):649-55. doi: 10.1164/rccm.201406-1022OC. PMID: 25089847; PMCID: PMC4214112.
- Kang MA, Churpek MM, Zadravecz FJ, Adhikari R, Twu NM, Edelson DP. Real-Time Risk Prediction on the Wards: A Feasibility Study. Crit Care Med. 2016 Aug;44(8):1468-73. doi: 10.1097/CCM.0000000000001716. PMID: 27075140; PMCID: PMC4949091.
Using Machine Learning for Early Recognition and Personalized Treatment of Acute Kidney Injury
Up to 20% of hospitalized patients develop acute kidney injury, which is associated with an increased risk of readmission, morbidity, and mortality. This project will use advanced machine learning methods and biomarkers to improve the identification and treatment of patients at risk of acute kidney injury, and will result in novel tools and personalized treatment algorithms that can be implemented to improve patient outcomes.
- Aim 1: To develop and validate a novel AKI risk stratification tool using NLP and deep learning.
- Aim 2: To identify the gaps in care for patients at high risk of severe AKI and their association with patient outcomes
- Aim 3: To determine the additive value of renal biomarkers to EHR-based machine learning algorithms for detecting patients at high risk for severe AKI.
Funding: NIH/ NIDDK, 1R01DK126933-01A1 (MPIs: Jay Koyner and Matthew Churpek) (08/01/2021 –07/31/2026)
- Koyner JL, Adhikari R, Edelson DP, Churpek MM. Development of a Multicenter Ward-Based AKI Prediction Model. Clin J Am Soc Nephrol. 2016 Nov 7;11(11):1935-1943. doi: 10.2215/CJN.00280116. Epub 2016 Sep 15. PMID: 27633727; PMCID: PMC5108182.
- Churpek MM, Carey KA, Edelson DP, Singh T, Astor BC, Gilbert ER, Winslow C, Shah N, Afshar M, Koyner JL. Internal and External Validation of a Machine Learning Risk Score for Acute Kidney Injury. JAMA Netw Open. 2020 Aug 3;3(8):e2012892. doi: 10.1001/jamanetworkopen.2020.12892. PMID: 32780123; PMCID: PMC7420241.
- Koyner JL, Carey KA, Edelson DP, Churpek MM. The Development of a Machine Learning Inpatient Acute Kidney Injury Prediction Model. Crit Care Med. 2018 Jul;46(7):1070-1077. doi: 10.1097/CCM.0000000000003123. PMID: 29596073.
Data-Driven Strategies for Substance Misuse Identification in Hospitalized Patients (SMART-AI)
Substance misuse screening in hospitalized patients is inconsistent and not standardized. The goal of this project is to provide novel and critically important tools in artificial intelligence for the detection of substance misuse from the electronic health record (EHR), which would enable daily substance misuse screenings.
- Aim 1: Using clinical notes from the EHR, we will train and test a natural language processing (NLP) substance misuse classifier in a cohort of adult hospitalized patients.
- Aim 2: Externally validate our NLP substance misuse classifier from Aim 1 in an independent cohort of hospitalized patients at a separate health system (UW) without current screening for substance misuse.
- Aim 3: Evaluate the effectiveness of the substance misuse classifier in increasing the proportion of patients who receive an intervention compared to usual care (Rush), which involves interviewer administered screening.
Funding: NIH/NIDA, 1R01DA051464 (PI: Majid Afshar) (09/30/2020 – 07/31/2025)
- Afshar M, Dligach D, Sharma B, Cai X, Boyda J, Birch S, Valdez D, Zelisko S, Joyce C, Modave F, Price R. Development and application of a high throughput natural language processing architecture to convert all clinical documents in a clinical data warehouse into standardized medical vocabularies. J Am Med Inform Assoc. 2019 Nov 1;26(11):1364-1369. doi: 10.1093/jamia/ocz068. PMID: 31145455; PMCID: PMC7647210.
- Sharma B, Dligach D, Swope K, Salisbury-Afshar E, Karnik NS, Joyce C, Afshar M. Publicly available machine learning models for identifying opioid misuse from the clinical notes of hospitalized patients. BMC Med Inform Decis Mak. 2020 Apr 29;20(1):79. doi: 10.1186/s12911-020-1099-y. PMID: 32349766; PMCID: PMC7191715.
- Afshar M, Baker K, Corral J, Ross E, Lowery E, Gonzalez R, Burnham EL, Callcut RA, Kornblith LZ, Hendrickson C, Kovacs EJ, Joyce C. Internal and External Validation of an Alcohol Biomarker for Screening in Trauma. Ann Surg. 2021 Mar 10:10.1097/SLA.0000000000004770. doi: 10.1097/SLA.0000000000004770. Epub ahead of print. PMID: 33534233; PMCID: PMC8429522.
Using Machine Learning to Predict Clinical Deterioration in Hospitalized Children
Children who are admitted to the hospital and experience deterioration have a high risk of mortality and poor long-term health. Current warning early scores indicating risk of deterioration are subjectively derived and have not reduced in-hospital mortality. The long-term goal is to implement a validated risk-prediction algorithm in hospitals for better detection of clinical deterioration in admitted children. This holds the promise of improving their survival and preventing long-term complications.
- Aim 1: Develop and validate models to improve the prediction of clinical deterioration in hospitalized children using structured EHR data.
- Aim 2: Develop and validate models predicting clinical deterioration in hospitalized children using unstructured pediatric clinical notes.
- Aim 3: Determine the impact of hospital-level environmental factors for predicting clinical deterioration in hospitalized children.
Funding: NIH/ NHLBI K01HL148390 (PI: Anoop Mayampurath) (07/15/2019 - 5/31/2022)
- Mayampurath A, Hagopian R, Venable LR, Carey C, Edelson D, Churpek M. Comparison of Machine Learning Methods for Predicting Outcomes After In-Hospital Cardiac Arrest. Crit. Care Med. 2021 Aug.
- Mayampurath A, Jani P, Dai Y, Gibbons R, Edelson D, Churpek MM. A Vital Sign-Based Model to Predict Clinical Deterioration in Hospitalized Children. Pediatric Crit Care Med. 2020 Sep;21(9):820-826.
- Mayampurath A, Sanchez-Pinto LN, Carey KA, Venable LR, Churpek M. Combining patient visual timelines with deep learning to predict mortality. PLoS One. 2019;14(7).
Building a Substance Use Data Commons for Public Health Informatics
We aim to foster an academic-public-private collaboration to build a data ecosystem that will harmonize data across a Wisconsin regional hospital, pre-hospital agencies like fire, and public health agencies for the first time. We will build a cohort with substance misuse with linked data that are engineered as an AI/ML-ready data commons. During our one-year timeline, we will train and test an AI/ML model that can prioritize those at the highest risk for poor outcomes and uncover important biases in our data sources with input by health equity experts.
- Aim 1: Build a Substance Misuse Data Commons across a major hospital system and Wisconsin agencies;
- Aim 2: Develop and validate a machine learning tool for substance use-related health outcomes;
- Aim 3: Examine model performance across health disparate groups (race/ethnic groups as well as neighborhoods).
Funding: NIH/NIDA 3R01DA051464-02S1 (PI: Majid Afshar) (8/1/2021 - 7/31/2022)
- Bhavani SV, Lonjers Z, Carey KA, Afshar M, Gilbert ER, Shah NS, Huang ES, Churpek MM. The Development and Validation of a Machine Learning Model to Predict Bacteremia and Fungemia in Hospitalized Patients Using Electronic Health Record Data. Crit Care Med. 2020 Nov;48(11):e1020-e1028. PMID: 32796184. PMCID: PMC7554143.
- Bhavani SV, Carey KA, Gilbert ER, Afshar M, Verhoef PA, Churpek MM. Identifying Novel Sepsis Subphenotypes Using Temperature Trajectories. Am J Respir Crit Care Med. 2019 Aug 1;200(3):327-335. PMID: 30789749. PMCID: PMC6680307.
- Mayampurath A, Sanchez-Pinto LN, Carey KA, Venable LR, Churpek MM. Combining Patient Visual Timelines with Deep Learning to Predict Mortality. PLoS One. 2019 Jul 31;14(7):e0220640. PMID: 31365580. PMCID: PMC6668841
- Kulshrestha S, Dligach D, Joyce C, Gonzalez R, O'Rourke AP, Glazer JM, Stey A, Kruser JM, Churpek MM, Afshar M. Comparison and Interpretability of Machine Learning Models to Predict Severity of Chest Injury. JAMIA Open. 2021 Mar 1;4(1):ooab015. PMID: 33709067. PMCID: PMC7935500.
- Sharma B, Dligach D, Swope K, Salisbury-Afshar E, Karnik NS, Joyce C, Afshar M. Publicly available machine learning models for identifying opioid misuse from the clinical notes of hospitalized patients. BMC Med Inform Decis Mak. 2020 Apr 29;20(1):79. PMCID: PMC7191715.
- Afshar M, Sharma B, Bhalla S, Thompson HM, Dligach D, Boley RA, Kishen E, Simmons A, Perticone K, Karnik NS. External validation of an opioid misuse machine learning classifier in hospitalized adult patients. Addict Sci Clin Pract. 2021 Mar 17;16(1):19. doi: 10.1186/s13722-021-00229-7. PubMed PMID: 33731210; PubMed Central PMCID: PMC7967783.
Make A Gift
Help support research by making a gift to the Department of Medicine's Pulmonary Research and Education Fund.