Managing COVID-19 With a Clinical Decision Support Tool in a Community Health Network: Algorithm Development and Validation

McRae, Michael; Dapkins, Isaac; Sharif, Iman; Anderman, Judd; Fenyö, David; Sinokrot, Odai; Kang, Stella K.; Christodoulides, Nicolaos; Vurmaz, Deniz; Simmons, Glennon W.; Alcorn, Timothy M.; Daoura, Marco J; Gisburne, Stu; Zar, David; McDevitt, John T.

doi:10.2196/22033

Cited by 40 publications

(69 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…During the development of a dynamic measurement tool, such as the signs and symptoms and pre-existing of associated chronic diseases, the complete clinical condition should be regarded, but the early historical records for fever clinics do not include these data element. A research to build, validate, and expand a clinical decision support system and mobile app was suggested by the authors in (9) to help in COVID-19 symptom evaluation, management and treatment. Training data was obtained from 701 COVID-19 patients through services within the network of Family Medical Clinics at New York University Langone Health Centers.…”

mentioning

confidence: 99%

Coronavirus Disease Diagnosis, Care and Prevention (COVID-19) Based on Decision Support System

Salah

Ahmed

2021

Baghdad Sci.J

View full text Add to dashboard Cite

Automated clinical decision support system (CDSS) acts as new paradigm in medical services today. CDSSs are utilized to increment specialists (doctors) in their perplexing decision-making. Along these lines, a reasonable decision support system is built up dependent on doctors' knowledge and data mining derivation framework so as to help with the interest the board in the medical care gracefully to control the Corona Virus Disease (COVID-19) virus pandemic and, generally, to determine the class of infection and to provide a suitable protocol treatment depending on the symptoms of patient. Firstly, it needs to determine the three early symptoms of COVID-19 pandemic criteria (fever, tiredness, dry cough and breathing difficulty) used to diagnose the person being infected by COVID-19 virus or not. Secondly, this approach divides the infected peoples into four classes, based on their immune system risk level (very high degree, high degree, mild degree, and normal), and using two indices of age and current health status like diabetes, heart disorders, or hypertension. Where, these people are graded and expected to comply with their class regulations. There are six important COVID-19 virus infections of different classes that should receive immediate health care to save their lives. When the test is positive, the patient age is considered to choose one of the six classifications depending on the patient symptoms to provide him the suitable care as one of the four types of suggested treatment protocol of COVID-19 virus infection in COVID-19 DSS application. Finally, a report of all information about any classification case of COVID-19 infection is printed where this report includes the status of patient (infection level) and the prevention protocol. Later, the program sends the report to the control centre (medical expert) containing the information. In this paper, it was suggested the use of C4.5 Algorithm for decision tree.

show abstract

mentioning

confidence: 99%

Coronavirus Disease Diagnosis, Care and Prevention (COVID-19) Based on Decision Support System

Salah

Ahmed

2021

Baghdad Sci.J

View full text Add to dashboard Cite

show abstract

“…Previous work building machine learning models used patient data from Tongji Hospital 2,3 (Wuhan, China), Zhongnan Hospital 4 (Wuhan China), Mount Sinai Hospital 5 (NYC, US), and NYU Family Health Center 6 (NYC, US). Surprisingly, clinical features selected varied widely across studies.…”

Section: Background and Significancementioning

confidence: 99%

“…As of November 12 th , the US alone logged its highest tally to date with a 317% growth over the preceding 30 days 1 . The coronavirus disease (COVID-19) is far from seeing the end of its days and there remains a compelling need to prioritize care and resources for patients at elevated risk of morbidity and mortality.Previous work building machine learning models used patient data from Tongji Hospital 2,3 (Wuhan, China), Zhongnan Hospital 4 (Wuhan China), Mount Sinai Hospital 5 (NYC, US), and NYU Family Health Center 6 (NYC, US). Surprisingly, clinical features selected varied widely across studies.…”

mentioning

confidence: 99%

“…Surprisingly, clinical features selected varied widely across studies. For example, while McRae et al’s 2-tiered model 6 trained on 701 NYC patients to predict mortality was based on actual age, C-reactive protein (CRP), procalcitonin, and D-dimer, Yan et al’s model 2 trained on 485 patients from Wuhan selected lactate dehydrogenase (LDH), lymphocyte count, and CRP as the most predictive for mortality. Variations in selected features differed greatly even when trained to predict similar outcomes on data from patients of the same city.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Predictive modeling of morbidity and mortality in COVID-19 hospitalized patients and its clinical implications

Wang

Liu

Chen

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

ObjectiveRetrospective study of COVID-19 positive patients treated at NYU Langone Health (NYULH) to identify clinical markers predictive of disease severity to assist in clinical decision triage and provide additional biological insights into disease progression.Materials and MethodsClinical activity of 3740 de-identified patients at NYULH between January and August 2020. Models were trained on clinical data during different parts of their hospital stay to predict three clinical outcomes: deceased, ventilated, or admitted to ICU.ResultsXGBoost model trained on clinical data from the final 24 hours excelled at predicting mortality (AUC=0.92, specificity=86% and sensitivity=85%). Respiration rate was the most important feature, followed by SpO2 and age 75+. Performance of this model to predict the deceased outcome extended 5 days prior with AUC=0.81, specificity=70%, sensitivity=75%. When only using clinical data from the first 24 hours, AUCs of 0.79, 0.80, and 0.77 were obtained for deceased, ventilated, or ICU admitted, respectively. Although respiration rate and SpO2 levels offered the highest feature importance, other canonical markers including diabetic history, age and temperature offered minimal gain. When lab values were incorporated, prediction of mortality benefited the most from blood urea nitrogen (BUN) and lactate dehydrogenase (LDH). Features predictive of morbidity included LDH, calcium, glucose, and C-reactive protein (CRP).ConclusionTogether this work summarizes efforts to systematically examine the importance of a wide range of features across different endpoint outcomes and at different hospitalization time points.BACKGROUND AND SIGNIFICANCEThe first cluster of SARS-CoV-2 was reported in Wuhan, Hubei Province on December 31, 2019. Inciting symptoms remarkably similar to pneumonia, the disease quickly traveled around the world, earning its pandemic status by the World Health Organization on March 11, 2020. Although the first wave has since passed for hardest-hit regions such as New York City (NYC) and most of Asia, a resurgence of cases has already been reported in Europe and record new cases tallied in the Midwest and rural United States (US). As of November 12th, the US alone logged its highest tally to date with a 317% growth over the preceding 30 days1. The coronavirus disease (COVID-19) is far from seeing the end of its days and there remains a compelling need to prioritize care and resources for patients at elevated risk of morbidity and mortality.Previous work building machine learning models used patient data from Tongji Hospital2,3 (Wuhan, China), Zhongnan Hospital4 (Wuhan China), Mount Sinai Hospital5 (NYC, US), and NYU Family Health Center6 (NYC, US). Surprisingly, clinical features selected varied widely across studies. For example, while McRae et al.’s 2-tiered model6 trained on 701 NYC patients to predict mortality was based on actual age, C-reactive protein (CRP), procalcitonin, and D-dimer, Yan et al.’s model2 trained on 485 patients from Wuhan selected lactate dehydrogenase (LDH), lymphocyte count, and CRP as the most predictive for mortality. Variations in selected features differed greatly even when trained to predict similar outcomes on data from patients of the same city. Yao et al.’s model3 was trained on 137 patients from Wuhan and relied on 28 biomarkers in their final model to predict morbidity. Given the differences among prior models, some of which were driven by domain-specific knowledge, we decided to systematically examine the importance of a wide range of features across different endpoint outcomes and at different hospitalization time points.This study analyzes retrospective PCR-confirmed COVID-19 inpatient data collected at NYU Langone Hospital spanning 1/1/2020 to 8/7/2020 to predict three sets of clinical outcomes: alive vs deceased, ventilated vs not ventilated, or ICU admitted vs not ICU admitted. The clinical information of 3740 patient encounters included demographic data (age, sex, insurance, past diagnosis of diabetes, presence of cardiovascular comorbidities), vital signs (SpO2, pulse, respiration rate, temperature, blood pressure), and the 50 most frequently ordered lab tests in our dataset. Models were developed using two methods: logistic regression with feature selection using Least Absolute Shrinkage and Selection Operator7 (LASSO) and gradient tree boosting with XGBoost8. An explainable algorithm, such as logistic regression, provides easy to interpret insights into the features of importance. Conversely, the larger model capacity of XGBoost better handles data complexities to explore the extent that predictive performance can be optimized. Together, these methods ensure a holistic survey that explores the clinical underpinnings of disease etiology and the prospects of building models that are sufficiently competent to be effective decision support tools.

show abstract

“…As a response to this international public health crisis, scientists and clinicians have made enormous efforts in the last few months to generate new knowledge and to develop technological tools that may help in combatting this infectious disease and mitigate its effects. Some of these efforts include the development of drugs and vaccines [1][2][3][4], the construction of epidemiological models to forecast the dynamics of disease spreading in the population [5][6][7][8], the development of mobile-device applications for tracking infected patients and new cases [9][10][11], and the development of strategies and the application of new technologies to manage the resources and capacities in hospitals [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Identification of high-risk COVID-19 patients using machine learning

Quiroz-Juárez

Gómez

Hoyo-Ulloa

et al. 2021

Preprint

View full text Add to dashboard Cite

The current COVID-19 public health crisis, caused by SARSCoV- 2 (severe acute respiratory syndrome coronavirus 2), has produced a devastating toll both in terms of human life loss and economic disruption. In this paper we present a machine-learning algorithm capable of identifying whether a given patient (actually infected or suspected to be infected) is more likely to survive than to die, or vice-versa. We train this algorithm with historical data, including medical history, demographic data, as well as COVID-19-related information. This is extracted from a database of confirmed and suspected COVID-19 infections in Mexico, constituting the official COVID-19 data compiled and made publicly available by the Mexican Federal Government. We demonstrate that the proposed method can detect high-risk patients with high accuracy, in each of four identified treatment stages, thus improving hospital capacity planning and timely treatment. Furthermore, we show that our method can be extended to provide optimal estimators for hypothesis-testing techniques commonly-used in biological and medical statistics. We believe that our work could be of use in the context of the current pandemic in assisting medical professionals with real-time assessments so as to determine health care priorities.

show abstract

Managing COVID-19 With a Clinical Decision Support Tool in a Community Health Network: Algorithm Development and Validation

Cited by 40 publications

References 29 publications

Coronavirus Disease Diagnosis, Care and Prevention (COVID-19) Based on Decision Support System

Coronavirus Disease Diagnosis, Care and Prevention (COVID-19) Based on Decision Support System

Predictive modeling of morbidity and mortality in COVID-19 hospitalized patients and its clinical implications

Identification of high-risk COVID-19 patients using machine learning

Contact Info

Product

Resources

About