1
|
Bhavani SV, Robichaux C, Verhoef PA, Churpek MM, Coopersmith CM. Using Trajectories of Bedside Vital Signs to Identify COVID-19 Subphenotypes. Chest 2024; 165:529-539. [PMID: 37748574 PMCID: PMC10925543 DOI: 10.1016/j.chest.2023.09.020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2023] [Revised: 08/23/2023] [Accepted: 09/18/2023] [Indexed: 09/27/2023] Open
Abstract
BACKGROUND Trajectories of bedside vital signs have been used to identify sepsis subphenotypes with distinct outcomes and treatment responses. The objective of this study was to validate the vitals trajectory model in a multicenter cohort of patients hospitalized with COVID-19 and to evaluate the clinical characteristics and outcomes of the resulting subphenotypes. RESEARCH QUESTION Can the trajectory of routine bedside vital signs identify COVID-19 subphenotypes with distinct clinical characteristics and outcomes? STUDY DESIGN AND METHODS The study included adult patients admitted with COVID-19 to four academic hospitals in the Emory Healthcare system between March 1, 2020, and May 31, 2022. Using a validated group-based trajectory model, we classified patients into previously defined vital sign trajectories using oral temperature, heart rate, respiratory rate, and systolic and diastolic BP measured in the first 8 h of hospitalization. Clinical characteristics, biomarkers, and outcomes were compared between subphenotypes. Heterogeneity of treatment effect to tocilizumab was evaluated. RESULTS The 7,065 patients with hospitalized COVID-19 were classified into four subphenotypes: group A (n = 1,429, 20%)-high temperature, heart rate, respiratory rate, and hypotensive; group B (1,454, 21%)-high temperature, heart rate, respiratory rate, and hypertensive; group C (2,996, 42%)-low temperature, heart rate, respiratory rate, and normotensive; and group D (1,186, 17%)-low temperature, heart rate, respiratory rate, and hypotensive. Groups A and D had higher ORs of mechanical ventilation, vasopressors, and 30-day inpatient mortality (P < .001). On comparing patients receiving tocilizumab (n = 55) with those who met criteria for tocilizumab but were admitted before its use (n = 461), there was significant heterogeneity of treatment effect across subphenotypes in the association of tocilizumab with 30-day mortality (P = .001). INTERPRETATION By using bedside vital signs available in even low-resource settings, we found novel subphenotypes associated with distinct manifestations of COVID-19, which could lead to preemptive and targeted treatments.
Collapse
Affiliation(s)
| | - Chad Robichaux
- Department of Biomedical Informatics, Emory University, Atlanta, GA
| | - Philip A Verhoef
- Department of Medicine, University of Hawaii John A. Burns School of Medicine, Honolulu, HI; Hawaii Permanente Medical Group, Honolulu, HI
| | | | - Craig M Coopersmith
- Emory Critical Care Center, Atlanta, GA; Department of Surgery, Emory University, Atlanta, GA
| |
Collapse
|
2
|
Appelman B, Michels EHA, de Brabander J, Peters-Sengers H, van Amstel RBE, Noordzij SM, Klarenbeek AM, van Linge CCA, Chouchane O, Schuurman AR, Reijnders TDY, Douma RA, Bos LDJ, Wiersinga WJ, van der Poll T. Thrombocytopenia is associated with a dysregulated host response in severe COVID-19. Thromb Res 2023; 229:187-197. [PMID: 37541167 DOI: 10.1016/j.thromres.2023.07.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2023] [Revised: 06/23/2023] [Accepted: 07/17/2023] [Indexed: 08/06/2023]
Abstract
BACKGROUND Thrombocytopenia is associated with increased mortality in COVID-19 patients. OBJECTIVE To determine the association between thrombocytopenia and alterations in host response pathways implicated in disease pathogenesis in patients with severe COVID-19. PATIENTS/METHODS We studied COVID-19 patients admitted to a general hospital ward included in a national (CovidPredict) cohort derived from 13 hospitals in the Netherlands. In a subgroup, 43 host response biomarkers providing insight in aberrations in distinct pathophysiological domains (coagulation and endothelial cell function; inflammation and damage; cytokines and chemokines) were determined in plasma obtained at a single time point within 48 h after admission. Patients were stratified in those with normal platelet counts (150-400 × 109/L) and those with thrombocytopenia (<150 × 109/L). RESULTS 6.864 patients were enrolled in the national cohort, of whom 1.348 had thrombocytopenia and 5.516 had normal platelets counts; the biomarker cohort consisted of 429 patients, of whom 85 with thrombocytopenia and 344 with normal platelet counts. Plasma D-dimer levels were not different in thrombocytopenia, although patients with moderate-severe thrombocytopenia (<100 × 109/L) showed higher D-dimer levels, indicating enhanced coagulation activation. Patients with thrombocytopenia had lower plasma levels of many proinflammatory cytokines and chemokines, and antiviral mediators, suggesting involvement of platelets in inflammation and antiviral immunity. Thrombocytopenia was associated with alterations in endothelial cell biomarkers indicative of enhanced activation and a relatively preserved glycocalyx integrity. CONCLUSION Thrombocytopenia in hospitalized patients with severe COVID-19 is associated with broad host response changes across several pathophysiological domains. These results suggest a role of platelets in the immune response during severe COVID-19.
Collapse
Affiliation(s)
- Brent Appelman
- Amsterdam UMC location University of Amsterdam, Center for Experimental and Molecular Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands.
| | - Erik H A Michels
- Amsterdam UMC location University of Amsterdam, Center for Experimental and Molecular Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands
| | - Justin de Brabander
- Amsterdam UMC location University of Amsterdam, Center for Experimental and Molecular Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands
| | - Hessel Peters-Sengers
- Amsterdam UMC location University of Amsterdam, Center for Experimental and Molecular Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands; Amsterdam UMC location Vrije Universiteit Amsterdam, Department of Epidemiology and Data Science, Boelelaan 1117, Amsterdam, the Netherlands
| | - Rombout B E van Amstel
- Amsterdam UMC location University of Amsterdam, Department of Intensive Care Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands
| | - Sophie M Noordzij
- Amsterdam UMC location University of Amsterdam, Center for Experimental and Molecular Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands
| | - Augustijn M Klarenbeek
- Amsterdam UMC location University of Amsterdam, Center for Experimental and Molecular Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands
| | - Christine C A van Linge
- Amsterdam UMC location University of Amsterdam, Center for Experimental and Molecular Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands
| | - Osoul Chouchane
- Amsterdam UMC location University of Amsterdam, Center for Experimental and Molecular Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands
| | - Alex R Schuurman
- Amsterdam UMC location University of Amsterdam, Center for Experimental and Molecular Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands
| | - Tom D Y Reijnders
- Amsterdam UMC location University of Amsterdam, Center for Experimental and Molecular Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands
| | - Renée A Douma
- Flevo Hospital, Department of Internal Medicine, Almere, the Netherlands
| | - Lieuwe D J Bos
- Amsterdam UMC location University of Amsterdam, Department of Intensive Care Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands
| | - W Joost Wiersinga
- Amsterdam UMC location University of Amsterdam, Center for Experimental and Molecular Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands; Amsterdam UMC location University of Amsterdam, Division of Infectious Diseases, Department of Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands
| | - Tom van der Poll
- Amsterdam UMC location University of Amsterdam, Center for Experimental and Molecular Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands; Amsterdam UMC location University of Amsterdam, Division of Infectious Diseases, Department of Medicine, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands
| |
Collapse
|
3
|
Siepel S, Dam TA, Fleuren LM, Girbes AR, Hoogendoorn M, Thoral PJ, Elbers PW, Bennis FC. Evolution of Clinical Phenotypes of COVID-19 Patients During Intensive Care Treatment: An Unsupervised Machine Learning Analysis. J Intensive Care Med 2023:8850666231153393. [PMID: 36744415 PMCID: PMC9902809 DOI: 10.1177/08850666231153393] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
BACKGROUND Identification of clinical phenotypes in critically ill COVID-19 patients could improve understanding of the disease heterogeneity and enable prognostic and predictive enrichment. However, previous attempts did not take into account temporal dynamics with high granularity. By including the dimension of time, we aim to gain further insights into the heterogeneity of COVID-19. METHODS We used granular data from 3202 adult COVID patients in the Dutch Data Warehouse that were admitted to one of 25 Dutch ICUs between February 2020 and March 2021. Parameters including demographics, clinical observations, medications, laboratory values, vital signs, and data from life support devices were selected. Twenty-one datasets were created that each covered 24 h of ICU data for each day of ICU treatment. Clinical phenotypes in each dataset were identified by performing cluster analyses. Both evolution of the clinical phenotypes over time and patient allocation to these clusters over time were tracked. RESULTS The final patient cohort consisted of 2438 COVID-19 patients with a ICU mortality outcome. Forty-one parameters were chosen for cluster analysis. On admission, both a mild and a severe clinical phenotype were found. After day 4, the severe phenotype split into an intermediate and a severe phenotype for 11 consecutive days. Heterogeneity between phenotypes appears to be driven by inflammation and dead space ventilation. During the 21-day period, only 8.2% and 4.6% of patients in the initial mild and severe clusters remained assigned to the same phenotype respectively. The clinical phenotype half-life was between 5 and 6 days for the mild and severe phenotypes, and about 3 days for the medium severe phenotype. CONCLUSIONS Patients typically do not remain in the same cluster throughout intensive care treatment. This may have important implications for prognostic or predictive enrichment. Prominent dissimilarities between clinical phenotypes are predominantly driven by inflammation and dead space ventilation.
Collapse
Affiliation(s)
- Sander Siepel
- Quantitative Data Analytics Group, Department of Computer Science, Faculty of Science, Vrije Universiteit, Amsterdam, the Netherlands
- Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, the Netherlands
| | - Tariq A. Dam
- Quantitative Data Analytics Group, Department of Computer Science, Faculty of Science, Vrije Universiteit, Amsterdam, the Netherlands
- Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, the Netherlands
| | - Lucas M. Fleuren
- Quantitative Data Analytics Group, Department of Computer Science, Faculty of Science, Vrije Universiteit, Amsterdam, the Netherlands
- Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, the Netherlands
| | - Armand R.J. Girbes
- Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, the Netherlands
| | - Mark Hoogendoorn
- Quantitative Data Analytics Group, Department of Computer Science, Faculty of Science, Vrije Universiteit, Amsterdam, the Netherlands
| | - Patrick J. Thoral
- Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, the Netherlands
| | - Paul W.G. Elbers
- Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, the Netherlands
| | - Frank C. Bennis
- Quantitative Data Analytics Group, Department of Computer Science, Faculty of Science, Vrije Universiteit, Amsterdam, the Netherlands
- Nivel, Netherlands Institute for Health Services Research, Utrecht, the Netherlands
- Frank Bennis, Quantitative Data Analytics Group, Department of Computer Science, VU Amsterdam, De Boelelaan 1111, 1081 HV, Amsterdam, the Netherlands.
| | | |
Collapse
|
4
|
Sprockel Díaz JJ, Torres Tobar LA, Rodríguez Acosta MJ. Aplicación de la calculadora de probabilidad fenotípica FEN-COVID en pacientes hospitalizados por COVID-19 en una población latinoamericana. REPERTORIO DE MEDICINA Y CIRUGÍA 2022. [DOI: 10.31260/repertmedcir.01217372.1363] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022] Open
Abstract
Introducción: la variabilidad del comportamiento clínico del COVID-19 puede ser uno de los determinantes que limitan la toma de decisiones terapéuticas. Se busca clasificar a pacientes latinoamericanos hospitalizados mediante la herramienta FEN-COVID para la identificación de fenotipos clínicos y determinar su asociación con mortalidad e ingreso a la unidad de cuidado intensivo (UCI). Métodos: estudio observacional de cohorte retrospectivo, que incluyó adultos hospitalizados en dos centros de tercer nivel de atención con COVID-19 confirmado entre septiembre 2020 y marzo 2021. A cada paciente seleccionado se asignó un fenotipo aplicando la calculadora FEN-COVID. Se llevó a cabo un análisis multivariado para documentar las asociaciones entre el fenotipo, las complicaciones hospitalarias y los desenlaces clínicos. Resultados: se identificaron 126 pacientes hospitalizados por COVID-19, edad promedio de 58 años, 45 mujeres (35.7%), 23% diabéticos, 45% hipertensos y 20% obesos. 108 (85.7%) fueron del fenotipo B y 18 (14.2%) fenotipo C. Aunque en este último los desenlaces fueron peores (requerimiento de UCI 77.8% vs 45.4% y mortalidad 66% vs 22%, OR 1.408, IC95% 3.191-5.243, p <0.007), esta asociación no se mantuvo en el análisis multivariado con OR 1.110 (IC95% 0.780 - 1.581, p de 0.555) Conclusión: los fenotipos identificados a partir de FEN-COVID parecen discriminar un subgrupo de pacientes que ostenta el peor comportamiento clínico, aunque no tuvo representación del fenotipo más leve. El análisis bivariado documentó asociación con la muerte o ingreso a UCI que no se mantuvo en el modelo multivariado.
Collapse
|
5
|
Modern Learning from Big Data in Critical Care: Primum Non Nocere. Neurocrit Care 2022; 37:174-184. [PMID: 35513752 PMCID: PMC9071245 DOI: 10.1007/s12028-022-01510-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2021] [Accepted: 04/06/2022] [Indexed: 12/13/2022]
Abstract
Large and complex data sets are increasingly available for research in critical care. To analyze these data, researchers use techniques commonly referred to as statistical learning or machine learning (ML). The latter is known for large successes in the field of diagnostics, for example, by identification of radiological anomalies. In other research areas, such as clustering and prediction studies, there is more discussion regarding the benefit and efficiency of ML techniques compared with statistical learning. In this viewpoint, we aim to explain commonly used statistical learning and ML techniques and provide guidance for responsible use in the case of clustering and prediction questions in critical care. Clustering studies have been increasingly popular in critical care research, aiming to inform how patients can be characterized, classified, or treated differently. An important challenge for clustering studies is to ensure and assess generalizability. This limits the application of findings in these studies toward individual patients. In the case of predictive questions, there is much discussion as to what algorithm should be used to most accurately predict outcome. Aspects that determine usefulness of ML, compared with statistical techniques, include the volume of the data, the dimensionality of the preferred model, and the extent of missing data. There are areas in which modern ML methods may be preferred. However, efforts should be made to implement statistical frameworks (e.g., for dealing with missing data or measurement error, both omnipresent in clinical data) in ML methods. To conclude, there are important opportunities but also pitfalls to consider when performing clustering or predictive studies with ML techniques. We advocate careful valuation of new data-driven findings. More interaction is needed between the engineer mindset of experts in ML methods, the insight in bias of epidemiologists, and the probabilistic thinking of statisticians to extract as much information and knowledge from data as possible, while avoiding harm.
Collapse
|
6
|
Xu Z, Su C, Xiao Y, Wang F. Artificial intelligence for COVID-19: battling the pandemic with computational intelligence. INTELLIGENT MEDICINE 2022; 2:13-29. [PMID: 34697578 PMCID: PMC8529224 DOI: 10.1016/j.imed.2021.09.001] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/20/2021] [Revised: 09/15/2021] [Accepted: 09/29/2021] [Indexed: 12/15/2022]
Abstract
The new coronavirus disease 2019 (COVID-19) has become a global pandemic leading to over 180 million confirmed cases and nearly 4 million deaths until June 2021, according to the World Health Organization. Since the initial report in December 2019 , COVID-19 has demonstrated a high transmission rate (with an R0 > 2), a diverse set of clinical characteristics (e.g., high rate of hospital and intensive care unit admission rates, multi-organ dysfunction for critically ill patients due to hyperinflammation, thrombosis, etc.), and a tremendous burden on health care systems around the world. To understand the serious and complex diseases and develop effective control, treatment, and prevention strategies, researchers from different disciplines have been making significant efforts from different aspects including epidemiology and public health, biology and genomic medicine, as well as clinical care and patient management. In recent years, artificial intelligence (AI) has been introduced into the healthcare field to aid clinical decision-making for disease diagnosis and treatment such as detecting cancer based on medical images, and has achieved superior performance in multiple data-rich application scenarios. In the COVID-19 pandemic, AI techniques have also been used as a powerful tool to overcome the complex diseases. In this context, the goal of this study is to review existing studies on applications of AI techniques in combating the COVID-19 pandemic. Specifically, these efforts can be grouped into the fields of epidemiology, therapeutics, clinical research, social and behavioral studies and are summarized. Potential challenges, directions, and open questions are discussed accordingly, which may provide new insights into addressing the COVID-19 pandemic and would be helpful for researchers to explore more related topics in the post-pandemic era.
Collapse
Affiliation(s)
- Zhenxing Xu
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York 10065, United States
| | - Chang Su
- Department of Health Service Administration and Policy, Temple University, Philadelphia 19122, United States
| | - Yunyu Xiao
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York 10065, United States
| | - Fei Wang
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York 10065, United States,Corresponding author: Fei Wang, Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York 10065, United States of America
| |
Collapse
|