Search

Your search keyword '"Churpek, Matthew"' showing total 750 results
Start Over Author "Churpek, Matthew"
750 results on '"Churpek, Matthew"'

1. When Raw Data Prevails: Are Large Language Model Embeddings Effective in Numerical Data Representation for Medical Machine Learning Applications?

Author

Gao, Yanjun, Myers, Skatje, Chen, Shan, Dligach, Dmitriy, Miller, Timothy A, Bitterman, Danielle, Churpek, Matthew, and Afshar, Majid

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

The introduction of Large Language Models (LLMs) has advanced data representation and analysis, bringing significant progress in their use for medical questions and answering. Despite these advancements, integrating tabular data, especially numerical data pivotal in clinical contexts, into LLM paradigms has not been thoroughly explored. In this study, we examine the effectiveness of vector representations from last hidden states of LLMs for medical diagnostics and prognostics using electronic health record (EHR) data. We compare the performance of these embeddings with that of raw numerical EHR data when used as feature inputs to traditional machine learning (ML) algorithms that excel at tabular data learning, such as eXtreme Gradient Boosting. We focus on instruction-tuned LLMs in a zero-shot setting to represent abnormal physiological data and evaluating their utilities as feature extractors to enhance ML classifiers for predicting diagnoses, length of stay, and mortality. Furthermore, we examine prompt engineering techniques on zero-shot and few-shot LLM embeddings to measure their impact comprehensively. Although findings suggest the raw data features still prevails in medical ML tasks, zero-shot LLM embeddings demonstrate competitive results, suggesting a promising avenue for future research in medical applications., Comment: Under review

Published
2024

3. Leveraging A Medical Knowledge Graph into Large Language Models for Diagnosis Prediction

Author

Gao, Yanjun, Li, Ruizhe, Caskey, John, Dligach, Dmitriy, Miller, Timothy, Churpek, Matthew M., and Afshar, Majid

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

Electronic Health Records (EHRs) and routine documentation practices play a vital role in patients' daily care, providing a holistic record of health, diagnoses, and treatment. However, complex and verbose EHR narratives overload healthcare providers, risking diagnostic inaccuracies. While Large Language Models (LLMs) have showcased their potential in diverse language tasks, their application in the healthcare arena needs to ensure the minimization of diagnostic errors and the prevention of patient harm. In this paper, we outline an innovative approach for augmenting the proficiency of LLMs in the realm of automated diagnosis generation, achieved through the incorporation of a medical knowledge graph (KG) and a novel graph model: Dr.Knows, inspired by the clinical diagnostic reasoning process. We derive the KG from the National Library of Medicine's Unified Medical Language System (UMLS), a robust repository of biomedical knowledge. Our method negates the need for pre-training and instead leverages the KG as an auxiliary instrument aiding in the interpretation and summarization of complex medical concepts. Using real-world hospital datasets, our experimental results demonstrate that the proposed approach of combining LLMs with KG has the potential to improve the accuracy of automated diagnosis generation. More importantly, our approach offers an explainable diagnostic pathway, edging us closer to the realization of AI-augmented diagnostic decision support systems., Comment: Under review

Published
2023

4. Overview of the Problem List Summarization (ProbSum) 2023 Shared Task on Summarizing Patients' Active Diagnoses and Problems from Electronic Health Record Progress Notes

Author

Gao, Yanjun, Dligach, Dmitriy, Miller, Timothy, Churpek, Matthew M., and Afshar, Majid

Subjects
Computer Science - Computation and Language
Abstract

The BioNLP Workshop 2023 initiated the launch of a shared task on Problem List Summarization (ProbSum) in January 2023. The aim of this shared task is to attract future research efforts in building NLP models for real-world diagnostic decision support applications, where a system generating relevant and accurate diagnoses will augment the healthcare providers decision-making process and improve the quality of care for patients. The goal for participants is to develop models that generated a list of diagnoses and problems using input from the daily care notes collected from the hospitalization of critically ill patients. Eight teams submitted their final systems to the shared task leaderboard. In this paper, we describe the tasks, datasets, evaluation metrics, and baseline systems. Additionally, the techniques and results of the evaluation of the different approaches tried by the participating teams are summarized., Comment: To appear in the Proceedings of the 5th BioNLP Workshop at ACL

Published
2023

5. Multi-Task Training with In-Domain Language Models for Diagnostic Reasoning

Author

Sharma, Brihat, Gao, Yanjun, Miller, Timothy, Churpek, Matthew M., Afshar, Majid, and Dligach, Dmitriy

Subjects
Computer Science - Computation and Language, Computer Science - Machine Learning
Abstract

Generative artificial intelligence (AI) is a promising direction for augmenting clinical diagnostic decision support and reducing diagnostic errors, a leading contributor to medical errors. To further the development of clinical AI systems, the Diagnostic Reasoning Benchmark (DR.BENCH) was introduced as a comprehensive generative AI framework, comprised of six tasks representing key components in clinical reasoning. We present a comparative analysis of in-domain versus out-of-domain language models as well as multi-task versus single task training with a focus on the problem summarization task in DR.BENCH (Gao et al., 2023). We demonstrate that a multi-task, clinically trained language model outperforms its general domain counterpart by a large margin, establishing a new state-of-the-art performance, with a ROUGE-L score of 28.55. This research underscores the value of domain-specific training for optimizing clinical diagnostic reasoning tasks., Comment: Accepted to the Proceedings of the 5th Clinical NLP Workshop at ACL

Published
2023

6. Progress Note Understanding -- Assessment and Plan Reasoning: Overview of the 2022 N2C2 Track 3 Shared Task

Author

Gao, Yanjun, Dligach, Dmitriy, Miller, Timothy, Churpek, Matthew M, Uzuner, Ozlem, and Afshar, Majid

Subjects
Computer Science - Artificial Intelligence, Computer Science - Computation and Language
Abstract

Daily progress notes are common types in the electronic health record (EHR) where healthcare providers document the patient's daily progress and treatment plans. The EHR is designed to document all the care provided to patients, but it also enables note bloat with extraneous information that distracts from the diagnoses and treatment plans. Applications of natural language processing (NLP) in the EHR is a growing field with the majority of methods in information extraction. Few tasks use NLP methods for downstream diagnostic decision support. We introduced the 2022 National NLP Clinical Challenge (N2C2) Track 3: Progress Note Understanding - Assessment and Plan Reasoning as one step towards a new suite of tasks. The Assessment and Plan Reasoning task focuses on the most critical components of progress notes, Assessment and Plan subsections where health problems and diagnoses are contained. The goal of the task was to develop and evaluate NLP systems that automatically predict causal relations between the overall status of the patient contained in the Assessment section and its relation to each component of the Plan section which contains the diagnoses and treatment plans. The goal of the task was to identify and prioritize diagnoses as the first steps in diagnostic decision support to find the most relevant information in long documents like daily progress notes. We present the results of 2022 n2c2 Track 3 and provide a description of the data, evaluation, participation and system performance., Comment: To appear in Journal of Biomedical Informatics

Published
2023

8. DR.BENCH: Diagnostic Reasoning Benchmark for Clinical Natural Language Processing

Author

Gao, Yanjun, Dligach, Dmitriy, Miller, Timothy, Caskey, John, Sharma, Brihat, Churpek, Matthew M, and Afshar, Majid

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

The meaningful use of electronic health records (EHR) continues to progress in the digital era with clinical decision support systems augmented by artificial intelligence. A priority in improving provider experience is to overcome information overload and reduce the cognitive burden so fewer medical errors and cognitive biases are introduced during patient care. One major type of medical error is diagnostic error due to systematic or predictable errors in judgment that rely on heuristics. The potential for clinical natural language processing (cNLP) to model diagnostic reasoning in humans with forward reasoning from data to diagnosis and potentially reduce the cognitive burden and medical error has not been investigated. Existing tasks to advance the science in cNLP have largely focused on information extraction and named entity recognition through classification tasks. We introduce a novel suite of tasks coined as Diagnostic Reasoning Benchmarks, DR.BENCH, as a new benchmark for developing and evaluating cNLP models with clinical diagnostic reasoning ability. The suite includes six tasks from ten publicly available datasets addressing clinical text understanding, medical knowledge reasoning, and diagnosis generation. DR.BENCH is the first clinical suite of tasks designed to be a natural language generation framework to evaluate pre-trained language models. Experiments with state-of-the-art pre-trained generative language models using large general domain models and models that were continually trained on a medical corpus demonstrate opportunities for improvement when evaluated in DR. BENCH. We share DR. BENCH as a publicly available GitLab repository with a systematic approach to load and evaluate models for the cNLP community., Comment: Under review

Published
2022
Full Text
View/download PDF

9. Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models

Author

Gao, Yanjun, Dligach, Dmitriy, Miller, Timothy, Xu, Dongfang, Churpek, Matthew M., and Afshar, Majid

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

Automatically summarizing patients' main problems from daily progress notes using natural language processing methods helps to battle against information and cognitive overload in hospital settings and potentially assists providers with computerized diagnostic decision support. Problem list summarization requires a model to understand, abstract, and generate clinical documentation. In this work, we propose a new NLP task that aims to generate a list of problems in a patient's daily care plan using input from the provider's progress notes during hospitalization. We investigate the performance of T5 and BART, two state-of-the-art seq2seq transformer architectures, in solving this problem. We provide a corpus built on top of progress notes from publicly available electronic health record progress notes in the Medical Information Mart for Intensive Care (MIMIC)-III. T5 and BART are trained on general domain text, and we experiment with a data augmentation method and a domain adaptation pre-training method to increase exposure to medical vocabulary and knowledge. Evaluation methods include ROUGE, BERTScore, cosine similarity on sentence embedding, and F-score on medical concepts. Results show that T5 with domain adaptive pre-training achieves significant performance gains compared to a rule-based system and general domain pre-trained language models, indicating a promising direction for tackling the problem summarization task., Comment: Paper is accepted to COLING 2022

Published
2022

10. Hierarchical Annotation for Building A Suite of Clinical Natural Language Processing Tasks: Progress Note Understanding

Author

Gao, Yanjun, Dligach, Dmitriy, Miller, Timothy, Tesch, Samuel, Laffin, Ryan, Churpek, Matthew M., and Afshar, Majid

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Computers and Society
Abstract

Applying methods in natural language processing on electronic health records (EHR) data is a growing field. Existing corpus and annotation focus on modeling textual features and relation prediction. However, there is a paucity of annotated corpus built to model clinical diagnostic thinking, a process involving text understanding, domain knowledge abstraction and reasoning. This work introduces a hierarchical annotation schema with three stages to address clinical text understanding, clinical reasoning, and summarization. We created an annotated corpus based on an extensive collection of publicly available daily progress notes, a type of EHR documentation that is collected in time series in a problem-oriented format. The conventional format for a progress note follows a Subjective, Objective, Assessment and Plan heading (SOAP). We also define a new suite of tasks, Progress Note Understanding, with three tasks utilizing the three annotation stages. The novel suite of tasks was designed to train and evaluate future NLP models for clinical text understanding, clinical knowledge representation, inference, and summarization., Comment: To appear in 13th Language Resources and Evaluation Conference (LREC 2022)

Published
2022

11. A Scoping Review of Publicly Available Language Tasks in Clinical Natural Language Processing

Author

Gao, Yanjun, Dligach, Dmitriy, Christensen, Leslie, Tesch, Samuel, Laffin, Ryan, Xu, Dongfang, Miller, Timothy, Uzuner, Ozlem, Churpek, Matthew M, and Afshar, Majid

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

Objective: to provide a scoping review of papers on clinical natural language processing (NLP) tasks that use publicly available electronic health record data from a cohort of patients. Materials and Methods: We searched six databases, including biomedical research and computer science literature database. A round of title/abstract screening and full-text screening were conducted by two reviewers. Our method followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines. Results: A total of 35 papers with 47 clinical NLP tasks met inclusion criteria between 2007 and 2021. We categorized the tasks by the type of NLP problems, including name entity recognition, summarization, and other NLP tasks. Some tasks were introduced with a topic of clinical decision support applications, such as substance abuse, phenotyping, cohort selection for clinical trial. We summarized the tasks by publication and dataset information. Discussion: The breadth of clinical NLP tasks keeps growing as the field of NLP evolves with advancements in language systems. However, gaps exist in divergent interests between general domain NLP community and clinical informatics community, and in generalizability of the data sources. We also identified issues in data selection and preparation including the lack of time-sensitive data, and invalidity of problem size and evaluation. Conclusions: The existing clinical NLP tasks cover a wide range of topics and the field will continue to grow and attract more attention from both general domain NLP and clinical informatics community. We encourage future work to incorporate multi-disciplinary collaboration, reporting transparency, and standardization in data preparation., Comment: Paper submitted to Journal of American Medical Informatics Association (JAMIA)

Published
2021

13. ASO Visual Abstract: Association of Neighborhood Disadvantage with Short- and Long-Term Outcomes After Pancreatectomy for Pancreatic Ductal Adenocarcinoma

Author

Marcinak, Clayton T., Praska, Corinne E., Vidri, Roberto J., Taylor, Amy K., Krebsbach, John K., Ahmed, Kaleem S., LoConte, Noelle K., Varley, Patrick R., Afshar, Majid, Weber, Sharon M., Abbott, Daniel E., Mathew, Jomol, Murtaza, Muhammed, Burkard, Mark E., Churpek, Matthew M., and Zafar, Syed Nabeel

Published
2024
Full Text
View/download PDF

14. Validation and utility of ARDS subphenotypes identified by machine-learning models using clinical data: an observational, multicohort, retrospective analysis

Author

Maddali, Manoj V, Churpek, Matthew, Pham, Tai, Rezoagli, Emanuele, Zhuo, Hanjing, Zhao, Wendi, He, June, Delucchi, Kevin L, Wang, Chunxue, Wickersham, Nancy, McNeil, J Brennan, Jauregui, Alejandra, Ke, Serena, Vessel, Kathryn, Gomez, Antonio, Hendrickson, Carolyn M, Kangelaris, Kirsten N, Sarma, Aartik, Leligdowicz, Aleksandra, Liu, Kathleen D, Matthay, Michael A, Ware, Lorraine B, Laffey, John G, Bellani, Giacomo, Calfee, Carolyn S, Sinha, Pratik, Rios, Fernando, Van Haren, Frank, Sottiaux, T, Lora, Fredy S, Azevedo, Luciano C, Depuydt, P, Fan, Eddy, Bugedo, Guillermo, Qiu, Haibo, Gonzalez, Marcos, Silesky, Juan, Cerny, Vladimir, Nielsen, Jonas, Jibaja, Manuel, Pham, Tài, Wrigge, Hermann, Matamis, Dimitrios, Ranero, Jorge Luis, Hashemian, SM, Amin, Pravin, Clarkson, Kevin, Kurahashi, Kiyoyasu, Villagomez, Asisclo, Zeggwagh, Amine Ali, Heunks, Leo M, Laake, Jon Henrik, Palo, Jose Emmanuel, do Vale Fernandes, Antero, Sandesc, Dorel, Arabi, Yaasen, Bumbasierevic, Vesna, Nin, Nicolas, Lorente, Jose A, Larsson, Anders, Piquilloud, Lise, Abroug, Fekri, McAuley, Daniel F, McNamee, Lia, Hurtado, Javier, Bajwa, Ed, Démpaire, Gabriel, Francois, Guy M, Sula, Hektor, Nunci, Lordian, Cani, Alma, Zazu, Alan, Dellera, Christian, Insaurralde, Carolina S, Alejandro, Risso V, Daldin, Julio, Vinzio, Mauricio, Fernandez, Ruben O, Cardonnet, Luis P, Bettini, Lisandro R, Bisso, Mariano Carboni, Osman, Emilio M, Setten, Mariano G, Lovazzano, Pablo, Alvarez, Javier, Villar, Veronica, Milstein, Cesar, Pozo, Norberto C, Grubissich, Nicolas, Plotnikow, Gustavo A, Vasquez, Daniela N, Ilutovich, Santiago, Tiribelli, Norberto, Chena, Ariel, Pellegrini, Carlos A, Saenz, María G, Estenssoro, Elisa, Brizuela, Matias, and Gianinetto, Hernan

Subjects
Lung, Clinical Research, Acute Respiratory Distress Syndrome, Rare Diseases, Respiratory, Good Health and Well Being, Acute Lung Injury, Humans, Machine Learning, Positive-Pressure Respiration, Respiratory Distress Syndrome, Retrospective Studies, LUNG SAFE Investigators and the ESICM Trials Group, Clinical Sciences, Public Health and Health Services, Other Medical and Health Sciences
Abstract

BackgroundTwo acute respiratory distress syndrome (ARDS) subphenotypes (hyperinflammatory and hypoinflammatory) with distinct clinical and biological features and differential treatment responses have been identified using latent class analysis (LCA) in seven individual cohorts. To facilitate bedside identification of subphenotypes, clinical classifier models using readily available clinical variables have been described in four randomised controlled trials. We aimed to assess the performance of these models in observational cohorts of ARDS.MethodsIn this observational, multicohort, retrospective study, we validated two machine-learning clinical classifier models for assigning ARDS subphenotypes in two observational cohorts of patients with ARDS: Early Assessment of Renal and Lung Injury (EARLI; n=335) and Validating Acute Lung Injury Markers for Diagnosis (VALID; n=452), with LCA-derived subphenotypes as the gold standard. The primary model comprised only vital signs and laboratory variables, and the secondary model comprised all predictors in the primary model, with the addition of ventilatory variables and demographics. Model performance was assessed by calculating the area under the receiver operating characteristic curve (AUC) and calibration plots, and assigning subphenotypes using a probability cutoff value of 0·5 to determine sensitivity, specificity, and accuracy of the assignments. We also assessed the performance of the primary model in EARLI using data automatically extracted from an electronic health record (EHR; EHR-derived EARLI cohort). In Large Observational Study to Understand the Global Impact of Severe Acute Respiratory Failure (LUNG SAFE; n=2813), a multinational, observational ARDS cohort, we applied a custom classifier model (with fewer variables than the primary model) to determine the prognostic value of the subphenotypes and tested their interaction with the positive end-expiratory pressure (PEEP) strategy, with 90-day mortality as the dependent variable.FindingsThe primary clinical classifier model had an area under receiver operating characteristic curve (AUC) of 0·92 (95% CI 0·90-0·95) in EARLI and 0·88 (0·84-0·91) in VALID. Performance of the primary model was similar when using exclusively EHR-derived predictors compared with manually curated predictors (AUC=0·88 [95% CI 0·81-0·94] vs 0·92 [0·88-0·97]). In LUNG SAFE, 90-day mortality was higher in patients assigned the hyperinflammatory subphenotype than in those with the hypoinflammatory phenotype (414 [57%] of 725 vs 694 [33%] of 2088; p

Published
2022

18. Comparison of machine learning clustering algorithms for detecting heterogeneity of treatment effect in acute respiratory distress syndrome: A secondary analysis of three randomised controlled trials

Author

Sinha, Pratik, Spicer, Alexandra, Delucchi, Kevin L, McAuley, Daniel F, Calfee, Carolyn S, and Churpek, Matthew M

Subjects
Biomedical and Clinical Sciences, Clinical Sciences, Lung, Clinical Research, Rare Diseases, Clinical Trials and Supportive Activities, Good Health and Well Being, Algorithms, Bayes Theorem, Cluster Analysis, Humans, Randomized Controlled Trials as Topic, Respiratory Distress Syndrome, Supervised Machine Learning, Treatment Outcome, Unsupervised Machine Learning, ARDS, RCTs, Clustering, machine learning, LCA, Heterogeneity of treatment effect, Public Health and Health Services, Clinical sciences, Epidemiology
Abstract

BackgroundHeterogeneity in Acute Respiratory Distress Syndrome (ARDS), as a consequence of its non-specific definition, has led to a multitude of negative randomised controlled trials (RCTs). Investigators have sought to identify heterogeneity of treatment effect (HTE) in RCTs using clustering algorithms. We evaluated the proficiency of several commonly-used machine-learning algorithms to identify clusters where HTE may be detected.MethodsFive unsupervised: Latent class analysis (LCA), K-means, partition around medoids, hierarchical, and spectral clustering; and four supervised algorithms: model-based recursive partitioning, Causal Forest (CF), and X-learner with Random Forest (XL-RF) and Bayesian Additive Regression Trees were individually applied to three prior ARDS RCTs. Clinical data and research protein biomarkers were used as partitioning variables, with the latter excluded for secondary analyses. For a clustering schema, HTE was evaluated based on the interaction term of treatment group and cluster with day-90 mortality as the dependent variable.FindingsNo single algorithm identified clusters with significant HTE in all three trials. LCA, XL-RF, and CF identified HTE most frequently (2/3 RCTs). Important partitioning variables in the unsupervised approaches were consistent across algorithms and RCTs. In supervised models, important partitioning variables varied between algorithms and across RCTs. In algorithms where clusters demonstrated HTE in the same trial, patients frequently interchanged clusters from treatment-benefit to treatment-harm clusters across algorithms. LCA aside, results from all other algorithms were subject to significant alteration in cluster composition and HTE with random seed change. Removing research biomarkers as partitioning variables greatly reduced the chances of detecting HTE across all algorithms.InterpretationMachine-learning algorithms were inconsistent in their abilities to identify clusters with significant HTE. Protein biomarkers were essential in identifying clusters with HTE. Investigations using machine-learning approaches to identify clusters to seek HTE require cautious interpretation.FundingNIGMS R35 GM142992 (PS), NHLBI R35 HL140026 (CSC); NIGMS R01 GM123193, Department of Defense W81XWH-21-1-0009, NIA R21 AG068720, NIDA R01 DA051464 (MMC).

Published
2021

22. Analysis of Protein Biomarkers From Hospitalized COVID-19 Patients Reveals Severity-Specific Signatures and Two Distinct Latent Profiles With Differential Responses to Corticosteroids*

Author

Verhoef, Philip A., Spicer, Alexandra B., Lopez-Espina, Carlos, Bhargava, Akhil, Schmalz, Lee, Sims, Matthew D., Palagiri, Ashok V., Iyer, Karthik V., Crisp, Matthew J., Halalau, Alexandra, Maddens, Nicholas, Gosai, Falgun, Syed, Anwaruddin, Azad, Saleem, Espinosa, Aimee, Davila, Francisco, Davila, Hugo, Evans, Neil R., Smith, Scott, Reddy, Bobby, Sinha, Pratik, and Churpek, Matthew M.

Published
2023
Full Text
View/download PDF

23. Machine Learning Prediction of Death in Critically Ill Patients With Coronavirus Disease 2019.

Author

Churpek, Matthew, Gupta, Shruti, Spicer, Alexandra, Hayek, Salim, Srivastava, Anand, Chan, Lili, Melamed, Michal, Brenner, Samantha, Radbel, Jared, Madhani-Lovely, Farah, Bhatraju, Pavan, Bansal, Anip, Green, Adam, Goyal, Nitender, Shaefi, Shahzad, Parikh, Chirag, Semler, Matthew, and Leaf, David

Subjects
artificial intelligence, coronavirus disease 2019, intensive care unit, machine learning
Abstract

OBJECTIVES: Critically ill patients with coronavirus disease 2019 have variable mortality. Risk scores could improve care and be used for prognostic enrichment in trials. We aimed to compare machine learning algorithms and develop a simple tool for predicting 28-day mortality in ICU patients with coronavirus disease 2019. DESIGN: This was an observational study of adult patients with coronavirus disease 2019. The primary outcome was 28-day inhospital mortality. Machine learning models and a simple tool were derived using variables from the first 48 hours of ICU admission and validated externally in independent sites and temporally with more recent admissions. Models were compared with a modified Sequential Organ Failure Assessment score, National Early Warning Score, and CURB-65 using the area under the receiver operating characteristic curve and calibration. SETTING: Sixty-eight U.S. ICUs. PATIENTS: Adults with coronavirus disease 2019 admitted to 68 ICUs in the United States between March 4, 2020, and June 29, 2020. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The study included 5,075 patients, 1,846 (36.4%) of whom died by day 28. eXtreme Gradient Boosting had the highest area under the receiver operating characteristic curve in external validation (0.81) and was well-calibrated, while k-nearest neighbors were the lowest performing machine learning algorithm (area under the receiver operating characteristic curve 0.69). Findings were similar with temporal validation. The simple tool, which was created using the most important features from the eXtreme Gradient Boosting model, had a significantly higher area under the receiver operating characteristic curve in external validation (0.78) than the Sequential Organ Failure Assessment score (0.69), National Early Warning Score (0.60), and CURB-65 (0.65; p < 0.05 for all comparisons). Age, number of ICU beds, creatinine, lactate, arterial pH, and Pao2/Fio2 ratio were the most important predictors in the eXtreme Gradient Boosting model. CONCLUSIONS: eXtreme Gradient Boosting had the highest discrimination overall, and our simple tool had higher discrimination than a modified Sequential Organ Failure Assessment score, National Early Warning Score, and CURB-65 on external validation. These models could be used to improve triage decisions and clinical trial enrichment.

Published
2021

27. Identifying molecular phenotypes in sepsis: an analysis of two prospective observational cohorts and secondary analysis of two randomised controlled trials

Author

Sinha, Pratik, Kerchberger, V Eric, Willmore, Andrew, Chambers, Julia, Zhuo, Hanjing, Abbott, Jason, Jones, Chayse, Wickersham, Nancy, Wu, Nelson, Neyton, Lucile, Langelier, Charles R, Mick, Eran, He, June, Jauregui, Alejandra, Churpek, Matthew M, Gomez, Antonio D, Hendrickson, Carolyn M, Kangelaris, Kirsten N, Sarma, Aartik, Leligdowicz, Aleksandra, Delucchi, Kevin L, Liu, Kathleen D, Russell, James A, Matthay, Michael A, Walley, Keith R, Ware, Lorraine B, and Calfee, Carolyn S

Published
2023
Full Text
View/download PDF

28. Development and validation of novel sepsis subphenotypes using trajectories of vital signs

Author

Bhavani, Sivasubramanium V., Semler, Matthew, Qian, Edward T., Verhoef, Philip A., Robichaux, Chad, Churpek, Matthew M., and Coopersmith, Craig M.

Subjects
Chronic kidney failure -- Health aspects -- Analysis, Mortality -- Analysis, Heart beat -- Analysis -- Health aspects, Infection -- Health aspects -- Analysis, Hospital patients -- Analysis -- Health aspects, Hypertension -- Analysis -- Health aspects, Health care industry, Emory University. School of Medicine
Abstract

Purpose Sepsis is a heterogeneous syndrome and identification of sub-phenotypes is essential. This study used trajectories of vital signs to develop and validate sub-phenotypes and investigated the interaction of sub-phenotypes with treatment using randomized controlled trial data. Methods All patients with suspected infection admitted to four academic hospitals in Emory Healthcare between 2014-2017 (training cohort) and 2018-2019 (validation cohort) were included. Group-based trajectory modeling was applied to vital signs from the first 8 h of hospitalization to develop and validate vitals trajectory sub-phenotypes. The associations between sub-phenotypes and outcomes were evaluated in patients with sepsis. The interaction between sub-phenotype and treatment with balanced crystalloids versus saline was tested in a secondary analysis of SMART (Isotonic Solutions and Major Adverse Renal Events Trial). Results There were 12,473 patients with suspected infection in training and 8256 patients in validation cohorts, and 4 vitals trajectory sub-phenotypes were found. Group A (N = 3483, 28%) were hyperthermic, tachycardic, tachypneic, and hypotensive. Group B (N = 1578, 13%) were hyperthermic, tachycardic, tachypneic (not as pronounced as Group A) and hypertensive. Groups C (N = 4044, 32%) and D (N = 3368, 27%) had lower temperatures, heart rates, and respiratory rates, with Group C normotensive and Group D hypotensive. In the 6,919 patients with sepsis, Groups A and B were younger while Groups C and D were older. Group A had the lowest prevalence of congestive heart failure, hypertension, diabetes mellitus, and chronic kidney disease, while Group B had the highest prevalence. Groups A and D had the highest vasopressor use (p < 0.001 for all analyses above). In logistic regression, 30-day mortality was significantly higher in Groups A and D (p < 0.001 and p = 0.03, respectively). In the SMART trial, sub-phenotype significantly modified treatment effect (p = 0.03). Group D had significantly lower odds of mortality with balanced crystalloids compared to saline (odds ratio (OR) 0.39, 95% confidence interval (CI) 0.23-0.67, p < 0.001). Conclusion Sepsis sub-phenotypes based on vital sign trajectory were consistent across cohorts, had distinct outcomes, and different responses to treatment with balanced crystalloids versus saline., Author(s): Sivasubramanium V. Bhavani [sup.1] [sup.2] [sup.10], Matthew Semler [sup.3], Edward T. Qian [sup.3], Philip A. Verhoef [sup.4] [sup.5], Chad Robichaux [sup.6], Matthew M. Churpek [sup.7] [sup.8], Craig M. Coopersmith [...]

Published
2022
Full Text
View/download PDF

33. Multicenter Development and Prospective Validation of eCARTv5: A Gradient Boosted Machine Learning Early Warning Score

Author

Churpek, Matthew M., primary, Carey, Kyle A., additional, Snyder, Ashley, additional, Winslow, Christopher J., additional, Gilbert, Emily R., additional, Shah, Nirav S., additional, Patterson, Brian W., additional, Afshar, Majid, additional, Weiss, Alan, additional, Amin, Devendra N., additional, Rhodes, Deborah J., additional, and Edelson, Dana P., additional

Published
2024
Full Text
View/download PDF

36. Resuscitation Quality in the ICU: A Retrospective Analysis

Author

Grossestreuer, Anne, Moskowitz, Ari, Edelson, Dana, Ornato, Joseph, Peberdy, Mary Ann, Churpek, Matthew, Kurz, Michael, Starks, Monique Anderson, Chan, Paul, Girotra, Saket, Perman, Sarah, Goldberger, Zachary, Roessler, Lara L., Holmberg, Mathias J., Pawar, Rahul D., and Lassen, Annmarie T.

Published
2022
Full Text
View/download PDF

38. Validation and utility of ARDS subphenotypes identified by machine-learning models using clinical data: an observational, multicohort, retrospective analysis

Author

Rios, Fernando, Van Haren, Frank, Sottiaux, T, Lora, Fredy S, Azevedo, Luciano C, Depuydt, P, Fan, Eddy, Bugedo, Guillermo, Qiu, Haibo, Gonzalez, Marcos, Silesky, Juan, Cerny, Vladimir, Nielsen, Jonas, Jibaja, Manuel, Pham, Tài, Wrigge, Hermann, Matamis, Dimitrios, Ranero, Jorge Luis, Hashemian, S. M, Amin, Pravin, Clarkson, Kevin, Bellani, Giacomo, Kurahashi, Kiyoyasu, Villagomez, Asisclo, Zeggwagh, Amine Ali, Heunks, Leo M, Laake, Jon Henrik, Palo, Jose Emmanuel, do Vale Fernandes, Antero, Sandesc, Dorel, Arabi, Yaasen, Bumbasierevic, Vesna, Nin, Nicolas, Lorente, Jose A, Larsson, Anders, Piquilloud, Lise, Abroug, Fekri, McAuley, Daniel F, McNamee, Lia, Hurtado, Javier, Bajwa, Ed, Démpaire, Gabriel, Francois, Guy M, Sula, Hektor, Nunci, Lordian, Cani, Alma, Zazu, Alan, Dellera, Christian, Insaurralde, Carolina S, Alejandro, Risso V, Daldin, Julio, Vinzio, Mauricio, Fernandez, Ruben O, Cardonnet, Luis P, Bettini, Lisandro R, Bisso, Mariano Carboni, Osman, Emilio M, Setten, Mariano G, Lovazzano, Pablo, Alvarez, Javier, Villar, Veronica, Milstein, Cesar, Pozo, Norberto C, Grubissich, Nicolas, Plotnikow, Gustavo A, Vasquez, Daniela N, Ilutovich, Santiago, Tiribelli, Norberto, Chena, Ariel, Pellegrini, Carlos A, Saenz, María G, Estenssoro, Elisa, Brizuela, Matias, Gianinetto, Hernan, Gomez, Pablo E, Cerrato, Valeria I, Bezzi, Marco G, Borello, Silvina A, Loiacono, Flavia A, Fernandez, Adriana M, Knowles, Serena, Reynolds, Claire, Inskip, Deborah M, Miller, Jennene J, Kong, Jing, Whitehead, Christina, Bihari, Shailesh, Seven, Aylin, Krstevski, Amanda, Rodgers, Helen J, Millar, Rebecca T, Mckenna, Toni E, Bailey, Irene M, Hanlon, Gabrielle C, Aneman, Anders, Lynch, Joan M, Azad, Raman, Neal, John, Woods, Paul W, Roberts, Brigit L, Kol, Mark R, Wong, Helen S, Riss, Katharina C, Staudinger, Thomas, Wittebole, Xavier, Berghe, Caroline, Bulpa, Pierre A, Dive, Alain M, Verstraete, Rik, Lebbinck, Herve, Depuydt, Pieter, Vermassen, Joris, Meersseman, Philippe, Ceunen, Helga, Rosa, Jonas I, Beraldo, Daniel O, Piras, Claudio, Ampinelli, Adenilton M R, Nassar Jr, Antonio P, Mataloun, Sergio, Moock, Marcelo, Thompson, Marlus M, Gonçalves, Claudio H, Antônio, Ana Carolina P, Ascoli, Aline, Biondi, Rodrigo S, Fontenele, Danielle C, Nobrega, Danielle, Sales, Vanessa M, Shindhe, Suresh, Ismail, Dk Maizatul Aiman B Pg Hj, Laffey, John, Beloncle, Francois, Davies, Kyle G, Cirone, Rob, Manoharan, Venika, Ismail, Mehvish, Goligher, Ewan C, Jassal, Mandeep, Nishikawa, Erin, Javeed, Areej, Curley, Gerard, Rittayamai, Nuttapol, Parotto, Matteo, Ferguson, Niall D, Mehta, Sangeeta, Knoll, Jenny, Pronovost, Antoine, Canestrini, Sergio, Bruhn, Alejandro R, Garcia, Patricio H, Aliaga, Felipe A, Farías, Pamela A, Yumha, Jacob S, Ortiz, Claudia A, Salas, Javier E, Saez, Alejandro A, Vega, Luis D, Labarca, Eduardo F, Martinez, Felipe T, Carreño, Nicolás G, Lora, Pilar, Liu, Haitao, Liu, Ling, Tang, Rui, Luo, Xiaoming, An, Youzhong, Zhao, Huiying, Gao, Yan, Zhai, Zhe, Ye, Zheng L, Wang, Wei, Li, Wenwen, Li, Qingdong, Zheng, Ruiqiang, Yu, Wenkui, Shen, Juanhong, Li, Xinyu, Yu, Tao, Lu, Weihua, Wu, Ya Q, Huang, Xiao B, He, Zhenyang, Lu, Yuanhua, Han, Hui, Zhang, Fan, Sun, Renhua, Wang, Hua X, Qin, Shu H, Zhu, Bao H, Zhao, Jun, Liu, Jian, Li, Bin, Liu, Jing L, Zhou, Fa C, Li, Qiong J, Zhang, Xing Y, Li-Xin, Zhou, Xin-Hua, Qiang, Jiang, Liangyan, Gao, Yuan N, Zhao, Xian Y, Li, Yuan Y, Li, Xiao L, Wang, Chunting, Yao, Qingchun, Yu, Rongguo, Chen, Kai, Shao, Huanzhang, Qin, Bingyu, Huang, Qing Q, Zhu, Wei H, Hang, Ai Y, Hua, Ma X, Li, Yimin, Xu, Yonghao, Di, Yu D, Ling, Long L, Qin, Tie H, Wang, Shou H, Qin, Junping, Han, Yi, Zhou, Suming, Vargas, Monica P, Silesky Jimenez, Juan I, González Rojas, Manuel A, Solis-Quesada, Jaime E, Ramirez-Alfaro, Christian M, Máca, Jan, Sklienka, Peter, Gjedsted, Jakob, Christiansen, Aage, Villamagua, Boris G, Llano, Miguel, Burtin, Philippe, Buzancais, Gautier, Beuret, Pascal, Pelletier, Nicolas, Mortaza, Satar, Mercat, Alain, Chelly, Jonathan, Jochmans, Sébastien, Terzi, Nicolas, Daubin, Cédric, Carteaux, Guillaume, de Prost, Nicolas, Chiche, Jean-Daniel, Daviaud, Fabrice, Pham, Tai, Fartoukh, Muriel, Barberet, Guillaume, Biehler, Jerome, Dellamonica, Jean, Doyen, Denis, Arnal, Jean-Michel, Briquet, Anais, Hraiech, Sami, Papazian, Laurent, Follin, Arnaud, Roux, Damien, Messika, Jonathan, Kalaitzis, Evangelos, Dangers, Laurence, Combes, Alain, Au, Siu-Ming, Béduneau, Gaetan, Carpentier, Dorothée, Zogheib, Elie H, Dupont, Herve, Ricome, Sylvie, Santoli, Francesco L, Besset, Sebastien L, Michel, Philippe, Gelée, Bruno, Danin, Pierre-Eric, Goubaux, Bernard, Crova, Philippe J, Phan, Nga T, Berkelmans, Frantz, Badie, Julio C, Tapponnier, Romain, Gally, Josette, Khebbeb, Samy, Herbrecht, Jean-Etienne, Schneider, Francis, Declercq, Pierre-Louis M, Rigaud, Jean-Philippe, Duranteau, Jacques, Harrois, Anatole, Chabanne, Russell, Marin, Julien, Bigot, Charlene, Thibault, Sandrine, Ghazi, Mohammed, Boukhazna, Messabi, Ould Zein, Salem, Richecoeur, Jack R, Combaux, Daniele M, Grelon, Fabien, Le Moal, Charlene, Sauvadet, Elise P, Robine, Adrien, Lemiale, Virginie, Reuter, Danielle, Dres, Martin, Demoule, Alexandre, Goldgran-Toledano, Dany, Baboi, Loredana, Guérin, Claude, Lohner, Ralph, Kraßler, Jens, Schäfer, Susanne, Zacharowski, Kai D, Meybohm, Patrick, Reske, Andreas W, Simon, Philipp, Hopf, Hans-Bernd F, Schuetz, Michael, Baltus, Thomas, Papanikolaou, Metaxia N, Papavasilopoulou, Theonymfi G, Zacharas, Giannis A, Ourailogloy, Vasilis, Mouloudi, Eleni K, Massa, Eleni V, Nagy, Eva O, Stamou, Electra E, Kiourtzieva, Ellada V, Oikonomou, Marina A, Avila, Luis E, Cortez, Cesar A, Citalán, Johanna E, Jog, Sameer A, Sable, Safal D, Shah, Bhagyesh, Gurjar, Mohan, Baronia, Arvind K, Memon, Mohammedfaruk, Muthuchellappan, Radhakrishnan, Ramesh, Venkatapura J, Shenoy, Anitha, Unnikrishnan, Ramesh, Dixit, Subhal B, Rhayakar, Rachana V, Ramakrishnan, Nagarajan, Bhardwaj, Vallish K, Mahto, Heera L, Sagar, Sudha V, Palaniswamy, Vijayanand, Ganesan, Deeban, Mohammadreza Hashemian, Seyed, Jamaati, Hamidreza, Heidari, Farshad, Meaney, Edel A, Nichol, Alistair, Knapman, Karl M, O'Croinin, Donall, Dunne, Eimhin S, Breen, Dorothy M, Clarkson, Kevin P, Jaafar, Rola F, Dwyer, Rory, Amir, Fahd, Ajetunmobi, Olaitan O, O'Muircheartaigh, Aogan C, Black, Colin S, Treanor, Nuala, Collins, Daniel V, Altaf, Wahid, Zani, Gianluca, Fusari, Maurizio, Spadaro, Savino, Volta, Carlo A, Graziani, Romano, Brunettini, Barbara, Palmese, Salvatore, Formenti, Paolo, Umbrello, Michele, Lombardo, Andrea, Pecci, Elisabetta, Botteri, Marco, Savioli, Monica, Protti, Alessandro, Mattei, Alessia, Schiavoni, Lorenzo, Tinnirello, Andrea, Todeschini, Manuel, Giarratano, Antonino, Cortegiani, Andrea, Sher, Sara, Rossi, Anna, Antonelli, Massimo M, Montini, Luca M, Casalena, Paolo, Scafetti, Sergio, Panarello, Giovanna, Occhipinti, Giovanna, Patroniti, Nicolò, Pozzi, Matteo, Biscione, Roberto R, Poli, Michela M, Raimondi, Ferdinando, Albiero, Daniela, Crapelli, Giulia, Beck, Eduardo, Pota, Vincenzo, Schiavone, Vincenzo, Molin, Alexandre, Tarantino, Fabio, Monti, Giacomo, Frati, Elena, Mirabella, Lucia, Cinnella, Gilda, Fossali, Tommaso, Colombo, Riccardo, Terragni, Pierpaolo, Pattarino, Ilaria, Mojoli, Francesco, Braschi, Antonio, Borotto, Erika E, Cracchiolo, Andrea N, Palma, Daniela M, Raponi, Francesco, Foti, Giuseppe, Vascotto, Ettore R, Coppadoro, Andrea, Brazzi, Luca, Floris, Leda, Iotti, Giorgio A, Venti, Aaron, Yamaguchi, Osamu, Takagi, Shunsuke, Maeyama, Hiroki N, Watanabe, Eizo, Yamaji, Yoshihiro, Shimizu, Kazuyoshi, Shiozaki, Kyoko, Futami, Satoru, Ryosuke, Sekine, Saito, Koji, Kameyama, Yoshinobu, Ueno, Keiko, Izawa, Masayo, Okuda, Nao, Suzuki, Hiroyuki, Harasawa, Tomofumi, Nasu, Michitaka, Takada, Tadaaki, Ito, Fumihito, Nunomiya, Shin, Koyama, Kansuke, Abe, Toshikazu, Andoh, Kohkichi, Kusumoto, Kohei, Hirata, Akira, Takaba, Akihiro, Kimura, Hiroyasu, Matsumoto, Shuhei, Higashijima, Ushio, Honda, Hiroyuki, Aoki, Nobumasa, Imai, Hiroshi, Ogino, Yasuaki, Mizuguchi, Ichiko, Ichikado, Kazuya, Nitta, Kenichi, Mochizuki, Katsunori, Hashida, Tomoaki, Tanaka, Hiroyuki, Nakamura, Tomoyuki, Niimi, Daisuke, Ueda, Takeshi, Kashiwa, Yozo, Uchiyama, Akinori, Sabelnikovs, Olegs, Oss, Peteris, Haddad, Youssef, Liew, Kong Y, Ñamendys-Silva, Silvio A, Jarquin-Badiola, Yves D, Sanchez-Hurtado, Luis A, Gomez-Flores, Saira S, Marin, Maria C, Villagomez, Asisclo J, Lemus, Jordana S, Fierro, Jonathan M, Cervantes, Mavy Ramirez, Mejia, Francisco Javier Flores, Gonzalez, Daniel R, Dector, Dulce M, Estrella, Claudia R, Sanchez-Medina, Jorge R, Ramirez-Gutierrez, Alvaro, George, Fernando G, Aguirre, Janet S, Buensuseso, Juan A, Poblano, Manuel, Dendane, Tarek, Balkhi, Hicham, Elkhayari, Mina, Samkaoui, Nacer, Ezzouine, Hanane, Benslama, Abdellatif, Amor, Mourad, Maazouzi, Wajdi, Cimic, Nedim, Beck, Oliver, Bruns, Monique M, Schouten, Jeroen A, Rinia, Myra, Raaijmakers, Monique, Van Wezel, Hellen M, Heines, Serge J, Buise, Marc P, Simonis, Fabienne D, Schultz, Marcus J, Goodson, Jennifer C, rowne, Troy S B, Navarra, Leanlove, Hunt, Anna, Hutchison, Robyn A, Bailey, Mathew B, Newby, Lynette, Mcarthur, Colin, Kalkoff, Michael, Mcleod, Alex, Casement, Jonathan, Hacking, Danielle J, Andersen, Finn H, Dolva, Merete S, Laake, Jon H, Barratt-Due, Andreas, Noremark, Kim Andre L, Søreide, Eldar, Sjøbø, Brit Å, Guttormsen, Anne B, Yoshido, Hector H Leon, Aguilar, Ronald Zumaran, Oscanoa, Fredy A Montes, Alisasis, Alain U, Robles, Joanne B, Pasanting-Lim, Rossini Abbie B, Tan, Beatriz C, Andruszkiewicz, Pawel, Jakubowska, Karina, Cox, Cristina M, Alvarez, António M, Oliveira, Bruno S, Montanha, Gustavo M, Barros, Nelson C, Pereira, Carlos S, Messias, António M, Monteiro, Jorge M, Araujo, Ana M, Catorze, Nuno T, Marum, Susan M, Bouw, Maria J, Gomes, Rui M, Brito, Vania A, Castro, Silvia, Estilita, Joana M, Barros, Filipa M, Serra, Isabel M, Martinho, Aurelia M, Tomescu, Dana R, Marcu, Alexandra, Bedreag, Ovidiu H, Papurica, Marius, Corneci, Dan E, Negoita, Silvius Ioan, Grigoriev, Evgeny, Gritsan, Alexey I, Gazenkampf, Andrey A, Almekhlafi, Ghaleb, Albarrak, Mohamad M, Mustafa, Ghanem M, Maghrabi, Khalid A, Salahuddin, Nawal, Aisa, Tharwat M, Al Jabbary, Ahmed S, Tabhan, Edgardo, Arabi, Yaseen M, Trinidad, Olivia A, Al Dorzi, Hasan M, Tabhan, Edgardo E, Bolon, Stefan, Smith, Oliver, Mancebo, Jordi, Aguirre-Bermeo, Hernan, Lopez-Delgado, Juan C, Esteve, Francisco, Rialp, Gemma, Forteza, Catalina, De Haro, Candelaria, Artigas, Antonio, Albaiceta, Guillermo M, De Cima-Iglesias, Sara, Seoane-Quiroga, Leticia, Ceniceros-Barros, Alexandra, Ruiz-Aguilar, Antonio L, Claraco-Vega, Luis M, Soler, Juan Alfonso, Lorente, Maria del Carmen, Hermosa, Cecilia, Gordo, Federico, Prieto-González, Miryam, López-Messa, Juan B, Perez, Manuel P, Pere, Cesar P, Allue, Raquel Montoiro, Roche-Campo, Ferran, Ibañez-Santacruz, Marcos, Temprano, Susana, Pintado, Maria C, De Pablo, Raul, Gómez, Pilar Ricart Aroa, Ruiz, Silvia Rodriguez, Moles, Silvia Iglesias, Jurado, Mª Teresa, Arizmendi, Alfons, Piacentini, Enrique A, Franco, Nieves, Honrubia, Teresa, Perez Cheng, Meisy, Perez Losada, Elena, Blanco, Javier, Yuste, Luis J, Carbayo-Gorriz, Cecilia, Cazorla-Barranquero, Francisca G, Alonso, Javier G, Alda, Rosa S, Algaba, Ángela, Navarro, Gonzalo, Cereijo, Enrique, Diaz-Rodriguez, Esther, Marcos, Diego Pastor, Montero, Laura Alvarez, Para, Luis Herrera, Sanchez, Roberto Jimenez, Blasco Navalpotro, Miguel Angel, Abad, Ricardo Diaz, Montiel González, Raquel, Toribio, Dácil Parrilla, Castro, Alejandro G, Artiga, Maria Jose D, Penuelas, Oscar, Roser, Tomas P, Olga, Moreno F, Curto, Elena Gallego, Sánchez, Rocío Manzano, Imma, Vallverdu P, Elisabet, Garcia M, Claverias, Laura, Magret, Monica, Pellicer, Ana M, Rodriguez, Lucia L, Sánchez-Ballesteros, Jesús, González-Salamanca, Ángela, Jimenez, Antonio G, Huerta, Francisco P, Diaz, Juan Carlos J Sotillo, Lopez, Esther Bermejo, Moya, David D Llinares, Alfonso, Alec A Tallet, Eugenio Luis, Palazon Sanchez, Cesar, Palazon Sanchez, Rafael, Sánchez I, Virgilio, Corcoles G, Recio, Noelia N, Adamsson, Richard O, Rylander, Christian C, Holzgraefe, Bernhard, Broman, Lars M, Wessbergh, Joanna, Persson, Linnea, Schiöler, Fredrik, Kedelv, Hans, Tibblin, Anna Oscarsson, Appelberg, Henrik, Hedlund, Lars, Helleberg, Johan, Eriksson, Karin E, Glietsch, Rita, Larsson, Niklas, Nygren, Ingela, Nunes, Silvia L, Morin, Anna-Karin, Kander, Thomas, Adolfsson, Anne, Zender, Hervé O., Leemann-Refondini, Corinne, Elatrous, Souheil, Bouchoucha, Slaheddine, Chouchene, Imed, Ouanes, Islem, Ben Souissi, Asma, Kamoun, Salma, Demirkiran, Oktay, Aker, Mustafa, Erbabacan, Emre, Ceylan, Ilkay, Girgin, Nermin Kelebek, Ozcelik, Menekse, Ünal, Necmettin, Meco, Basak Ceyda, Akyol, Onat O, Derman, Suleyman S, Kennedy, Barry, Parhar, Ken, Srinivasa, Latha, McAuley, Danny, Steinberg, Jack, Hopkins, Phil, Mellis, Clare, Stansil, Frank, Kakar, Vivek, Hadfield, Dan, Brown, Christine, Vercueil, Andre, Bhowmick, Kaushik, Humphreys, Sally K, Ferguson, Andrew, Mckee, Raymond, Raj, Ashok S, Fawkes, Danielle A, Watt, Philip, Twohey, Linda, Thomas, Rajeev R Jha Matthew, Morton, Alex, Kadaba, Varsha, Smith, Mark J, Hormis, Anil P, Kannan, Santhana G, Namih, Miriam, Reschreiter, Henrik, Camsooksai, Julie, Kumar, Alek, Rugonfalvi, Szabolcs, Nutt, Christopher, Oneill, Orla, Seasman, Colette, Dempsey, Ged, Scott, Christopher J, Ellis, Helen E, Mckechnie, Stuart, Hutton, Paula J, Di Tomasso, Nora N, Vitale, Michela N, Griffin, Ruth O, Dean, Michael N, Cranshaw, Julius H, Willett, Emma L, Ioannou, Nicholas, Gillis, Sarah, Csabi, Peter, Macfadyen, Rosaleen, Dawson, Heidi, Preez, Pieter D, Williams, Alexandra J, Boyd, Owen, De Gordoa, Laura Ortiz-Ruiz, Bramall, Jon, Symmonds, Sophie, Chau, Simon K, Wenham, Tim, Szakmany, Tamas, Toth-Tarsoly, Piroska, Mccalman, Katie H, Alexander, Peter, Stephenson, Lorraine, Collyer, Thomas, Chapman, Rhiannon, Cooper, Raphael, Allan, Russell M, Sim, Malcolm, Wrathall, David W, Irvine, Donald A, Zantua, Kim S, Adams, John C, Burtenshaw, Andrew J, Sellors, Gareth P, Welters, Ingeborg D, Williams, Karen E, Hessell, Robert J, Oldroyd, Matthew G, Battle, Ceri E, Pillai, Suresh, Kajtor, Istvan, Sivashanmugave, Mageswaran, Okane, Sinead C, Donnelly, Adrian, Frigyik, Aniko D, Careless, Jon P, May, Martin M, Stewart, Richard, Trinder, T John, Hagan, Samantha J, Wise, Matt P, Cole, Jade M, MacFie, Caroline C, Dowling, Anna T, Nuñez, Edgardo, Pittini, Gustavo, Rodriguez, Ruben, Imperio, María C, Santos, Cristina, França, Ana G., Ebeid, Alejandro, Deicas, Alberto, Serra, Carolina, Uppalapati, Aditya, Kamel, Ghassan, Banner-Goodspeed, Valerie M, Beitler, Jeremy R, Mukkera, Satyanarayana Reddy, Kulkarni, Shreedhar, Lee, Jarone, Mesar, Tomaz, Shinn Iii, John O, Gomaa, Dina, Tainter, Christopher, Cowley, R Adams, Yeatts, Dale J, Warren, Jessica, Lanspa, Michael J, Miller, Russel R, Grissom, Colin K, Brown, Samuel M, Bauer, Philippe R, Gosselin, Ryan J, Kitch, Barrett T, Cohen, Jason E, Beegle, Scott H, Gueret, Renaud M, Tulaimat, Aiman, Choudry, Shazia, Stigler, William, Batra, Hitesh, Huff, Nidhi G, Lamb, Keith D, Oetting, Trevor W, Mohr, Nicholas M, Judy, Claine, Saito, Shigeki, Kheir, Fayez M, Schlichting, Adam B, Delsing, Angela, Elmasri, Mary, Crouch, Daniel R, Ismail, Dina, Blakeman, Thomas C, Dreyer, Kyle R, Baron, Rebecca M, Grijalba, Carolina Quintana, Hou, Peter C, Seethala, Raghu, Aisiku, Imo, Henderson, Galen, Frendl, Gyorgy, Hou, Sen-Kuang, Owens, Robert L, Schomer, Ashley, Bumbasirevic, Vesna, Jovanovic, Bojan, Surbatovic, Maja, Veljovic, Milic, Maddali, Manoj V, Churpek, Matthew, Rezoagli, Emanuele, Zhuo, Hanjing, Zhao, Wendi, He, June, Delucchi, Kevin L, Wang, Chunxue, Wickersham, Nancy, McNeil, J Brennan, Jauregui, Alejandra, Ke, Serena, Vessel, Kathryn, Gomez, Antonio, Hendrickson, Carolyn M, Kangelaris, Kirsten N, Sarma, Aartik, Leligdowicz, Aleksandra, Liu, Kathleen D, Matthay, Michael A, Ware, Lorraine B, Laffey, John G, Calfee, Carolyn S, and Sinha, Pratik

Published
2022
Full Text
View/download PDF

40. Automated stratification of trauma injury severity across multiple body regions using multi-modal, multi-class machine learning models.

Author

Gao, Jifan, Chen, Guanhua, O'Rourke, Ann P, Caskey, John, Carey, Kyle A, Oguss, Madeline, Stey, Anne, Dligach, Dmitriy, Miller, Timothy, Mayampurath, Anoop, Churpek, Matthew M, and Afshar, Majid

Abstract

Objective The timely stratification of trauma injury severity can enhance the quality of trauma care but it requires intense manual annotation from certified trauma coders. The objective of this study is to develop machine learning models for the stratification of trauma injury severity across various body regions using clinical text and structured electronic health records (EHRs) data. Materials and Methods Our study utilized clinical documents and structured EHR variables linked with the trauma registry data to create 2 machine learning models with different approaches to representing text. The first one fuses concept unique identifiers (CUIs) extracted from free text with structured EHR variables, while the second one integrates free text with structured EHR variables. Temporal validation was undertaken to ensure the models' temporal generalizability. Additionally, analyses to assess the variable importance were conducted. Results Both models demonstrated impressive performance in categorizing leg injuries, achieving high accuracy with macro-F1 scores of over 0.8. Additionally, they showed considerable accuracy, with macro-F1 scores exceeding or near 0.7, in assessing injuries in the areas of the chest and head. We showed in our variable importance analysis that the most important features in the model have strong face validity in determining clinically relevant trauma injuries. Discussion The CUI-based model achieves comparable performance, if not higher, compared to the free-text-based model, with reduced complexity. Furthermore, integrating structured EHR data improves performance, particularly when the text modalities are insufficiently indicative. Conclusions Our multi-modal, multiclass models can provide accurate stratification of trauma injury severity and clinically relevant interpretations. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

42. The Laboratory-Based Intermountain Validated Exacerbation (LIVE) Score Identifies Chronic Obstructive Pulmonary Disease Patients at High Mortality Risk

Author

Blagev, Denitza P, Collingridge, Dave S, Rea, Susan, Horne, Benjamin D, Press, Valerie G, Churpek, Matthew M, Carey, Kyle A, Mularski, Richard A, Zeng, Siyang, and Arjomandi, Mehrdad

Subjects
Health Services and Systems, Health Sciences, Clinical Research, Lung, Prevention, Chronic Obstructive Pulmonary Disease, Respiratory, Good Health and Well Being, COPD, cluster analysis, comorbidity, risk stratification, informatics, LIVE Score, Biomedical and clinical sciences, Health sciences
Abstract

Background: Identifying COPD patients at high risk for mortality or healthcare utilization remains a challenge. A robust system for identifying high-risk COPD patients using Electronic Health Record (EHR) data would empower targeting interventions aimed at ensuring guideline compliance and multimorbidity management. The purpose of this study was to empirically derive, validate, and characterize subgroups of COPD patients based on routinely collected clinical data widely available within the EHR. Methods: Cluster analysis was used in 5,006 patients with COPD at Intermountain to identify clusters based on a large collection of clinical variables. Recursive Partitioning (RP) was then used to determine a preferred tree that assigned patients to clusters based on a parsimonious variable subset. The mortality, COPD exacerbations, and comorbidity profile of the identified groups were examined. The findings were validated in an independent Intermountain cohort and in external cohorts from the United States Veterans Affairs (VA) and University of Chicago Medicine systems. Measurements and Main Results: The RP algorithm identified five LIVE Scores based on laboratory values: albumin, creatinine, chloride, potassium, and hemoglobin. The groups were characterized by increasing risk of mortality. The lowest risk, LIVE Score 5 had 8% 4-year mortality vs. 56% in the highest risk LIVE Score 1 (p < 0.001). These findings were validated in the VA cohort (n = 83,134), an expanded Intermountain cohort (n = 48,871) and in the University of Chicago system (n = 3,236). Higher mortality groups also had higher COPD exacerbation rates and comorbidity rates. Conclusions: In large clinical datasets across different organizations, the LIVE Score utilizes existing laboratory data for COPD patients, and may be used to stratify risk for mortality and COPD exacerbations.

Published
2018

43. Stability of Frequency of Severe Chronic Obstructive Pulmonary Disease Exacerbations and Health Care Utilization in Clinical Populations.

Author

Blagev, Denitza P, Collingridge, Dave S, Rea, Susan, Press, Valerie G, Churpek, Matthew M, Carey, Kyle, Mularski, Richard A, Zeng, Siyang, and Arjomandi, Mehrdad

Subjects
Biomedical and Clinical Sciences, Clinical Sciences, Health Sciences, Clinical Research, Infectious Diseases, Lung, Clinical Trials and Supportive Activities, Health Services, Chronic Obstructive Pulmonary Disease, Respiratory, Good Health and Well Being, chronic obstructive pulmonary disease, COPD, COPD exacerbation, stability, health care utilization
Abstract

Rationale: Although chronic obstructive pulmonary disease (COPD) exacerbation frequency is stable in research cohorts, whether severe COPD exacerbation frequency can be used to identify patients at high risk for future severe COPD exacerbations and/or mortality is unknown. Methods: Severe COPD exacerbation frequency stability was determined in 3 distinct clinical cohorts. A total of 17,450 patients with COPD in Intermountain Healthcare were categorized based on the number of severe COPD exacerbations per year. We determined whether exacerbation frequency was stable and whether it predicted mortality. These findings were validated in 83,134 patients from the U.S. Veterans Affairs (VA) nationwide health care system and 3326 patients from the University of Chicago Medicine health system. Results: In the Intermountain Healthcare cohort, the majority (84%, 14,706 patients) had no exacerbations in 2009 and were likely to remain non-exacerbators with a significantly lower 6-year mortality compared with frequent exacerbators (2 or more exacerbations per year) (25% versus 57%, p

Published
2018

44. Development and Validation of a Risk Score Predicting Death Without Transplant in Adult Heart Transplant Candidates

Author

Zhang, Kevin C., primary, Narang, Nikhil, additional, Jasseron, Carine, additional, Dorent, Richard, additional, Lazenby, Kevin A., additional, Belkin, Mark N., additional, Grinstein, Jonathan, additional, Mayampurath, Anoop, additional, Churpek, Matthew M., additional, Khush, Kiran K., additional, and Parker, William F., additional

Published
2024
Full Text
View/download PDF

45. Causes, Diagnostic Testing, and Treatments Related to Clinical Deterioration Events among High-Risk Ward Patients

Author

Churpek, Matthew M., primary, Ingebritsen, Ryan, additional, Carey, Kyle A., additional, Rao, Saieesh A, additional, Murnin, Emily, additional, Qyli, Tonela, additional, Oguss, Madeline K., additional, Picart, Jamila, additional, Penumalee, Leena, additional, Follman, Benjamin D., additional, Nezirova, Lily K, additional, Tully, Sean T., additional, Benjamin, Charis, additional, Nye, Christopher, additional, Gilbert, Emily R., additional, Shah, Nirav S., additional, Winslow, Christopher J., additional, Afshar, Majid, additional, and Edelson, Dana P., additional

Published
2024
Full Text
View/download PDF

48. Automated stratification of trauma injury severity across multiple body regions using multi-modal, multi-class machine learning models

Author

Gao, Jifan, primary, Chen, Guanhua, additional, O'Rourke, Ann P, additional, Caskey, John, additional, Carey, Kyle, additional, Oguss, Madeline, additional, Stey, Anne, additional, Dligach, Dmitriy, additional, Miller, Timothy, additional, Mayampurath, Anoop, additional, Churpek, Matthew M, additional, and Afshar, Majid, additional

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results