Dataset Information

Predicting COVID-19 mortality with electronic medical records.

ABSTRACT: This study aims to predict death after COVID-19 using only the past medical information routinely collected in electronic health records (EHRs) and to understand the differences in risk factors across age groups. Combining computational methods and clinical expertise, we curated clusters that represent 46 clinical conditions as potential risk factors for death after a COVID-19 infection. We trained age-stratified generalized linear models (GLMs) with component-wise gradient boosting to predict the probability of death based on what we know from the patients before they contracted the virus. Despite only relying on previously documented demographics and comorbidities, our models demonstrated similar performance to other prognostic models that require an assortment of symptoms, laboratory values, and images at the time of diagnosis or during the course of the illness. In general, we found age as the most important predictor of mortality in COVID-19 patients. A history of pneumonia, which is rarely asked in typical epidemiology studies, was one of the most important risk factors for predicting COVID-19 mortality. A history of diabetes with complications and cancer (breast and prostate) were notable risk factors for patients between the ages of 45 and 65 years. In patients aged 65-85 years, diseases that affect the pulmonary system, including interstitial lung disease, chronic obstructive pulmonary disease, lung cancer, and a smoking history, were important for predicting mortality. The ability to compute precise individual-level risk scores exclusively based on the EHR is crucial for effectively allocating and distributing resources, such as prioritizing vaccination among the general population.

SUBMITTER: Estiri H

PROVIDER: S-EPMC7862405 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting COVID-19 mortality with electronic medical records.

Estiri Hossein H Strasser Zachary H ZH Klann Jeffy G JG Naseri Pourandokht P Wagholikar Kavishwar B KB Murphy Shawn N SN

NPJ digital medicine 20210204 1

This study aims to predict death after COVID-19 using only the past medical information routinely collected in electronic health records (EHRs) and to understand the differences in risk factors across age groups. Combining computational methods and clinical expertise, we curated clusters that represent 46 clinical conditions as potential risk factors for death after a COVID-19 infection. We trained age-stratified generalized linear models (GLMs) with component-wise gradient boosting to predict t ...[more]

PMID: 33542473

Similar Datasets

Project description:BackgroundElectronic medical records have opened opportunities to analyze clinical practice at large scale. Structured registries and coding procedures such as the International Classification of Primary Care further improved these procedures. However, a large part of the information about the state of patient and the doctors' observations is still entered in free text fields. The main function of those fields is to report the doctor's line of thought, to remind oneself and his or her colleagues on follow-up actions, and to be accountable for clinical decisions. These fields contain rich information that can be complementary to that in coded fields, and until now, they have been hardly used for analysis.ObjectiveThis study aims to develop a prediction model to convert the free text information on COVID-19-related symptoms from out of hours care electronic medical records into usable symptom-based data that can be analyzed at large scale.MethodsThe design was a feasibility study in which we examined the content of the raw data, steps and methods for modelling, as well as the precision and accuracy of the models. A data prediction model for 27 preidentified COVID-19-relevant symptoms was developed for a data set derived from the database of primary-care out-of-hours consultations in Flanders. A multiclass, multilabel categorization classifier was developed. We tested two approaches, which were (1) a classical machine learning-based text categorization approach, Binary Relevance, and (2) a deep neural network learning approach with BERTje, including a domain-adapted version. Ethical approval was acquired through the Institutional Review Board of the Institute of Tropical Medicine and the ethics committee of the University Hospital of Antwerpen (ref 20/50/693).ResultsThe sample set comprised 3957 fields. After cleaning, 2313 could be used for the experiments. Of the 2313 fields, 85% (n=1966) were used to train the model, and 15% (n=347) for testing. The normal BERTje model performed the best on the data. It reached a weighted F1 score of 0.70 and an exact match ratio or accuracy score of 0.38, indicating the instances for which the model has identified all correct codes. The other models achieved respectable results as well, ranging from 0.59 to 0.70 weighted F1. The Binary Relevance method performed the best on the data without a frequency threshold. As for the individual codes, the domain-adapted version of BERTje performs better on several of the less common objective codes, while BERTje reaches higher F1 scores for the least common labels especially, and for most other codes in general.ConclusionsThe artificial intelligence model BERTje can reliably predict COVID-19-related information from medical records using text mining from the free text fields generated in primary care settings. This feasibility study invites researchers to examine further possibilities to use primary care routine data.

Project description:BACKGROUND:Falls in hospitals are the most common risk factor that affects the safety of inpatients and can result in severe harm. Therefore, preventing falls is one of the most important areas of risk management for health care organizations. However, existing methods for predicting falls are laborious and costly. OBJECTIVE:The objective of this study is to verify whether hospital inpatient falls can be predicted through the analysis of a single input-unstructured nursing records obtained from Japanese electronic medical records (EMRs)-using a natural language processing (NLP) algorithm and machine learning. METHODS:The nursing records of 335 fallers and 408 nonfallers for a 12-month period were extracted from the EMRs of an acute care hospital and randomly divided into a learning data set and test data set. The former data set was subjected to NLP and machine learning to extract morphemes that contributed to separating fallers from nonfallers to construct a model for predicting falls. Then, the latter data set was used to determine the predictive value of the model using receiver operating characteristic (ROC) analysis. RESULTS:The prediction of falls using the test data set showed high accuracy, with an area under the ROC curve, sensitivity, specificity, and odds ratio of mean 0.834 (SD 0.005), mean 0.769 (SD 0.013), mean 0.785 (SD 0.020), and mean 12.27 (SD 1.11) for five independent experiments, respectively. The morphemes incorporated into the final model included many words closely related to known risk factors for falls, such as the use of psychotropic drugs, state of consciousness, and mobility, thereby demonstrating that an NLP algorithm combined with machine learning can effectively extract risk factors for falls from nursing records. CONCLUSIONS:We successfully established that falls among hospital inpatients can be predicted by analyzing nursing records using an NLP algorithm and machine learning. Therefore, it may be possible to develop a fall risk monitoring system that analyzes nursing records daily and alerts health care professionals when the fall risk of an inpatient is increased.

Project description:ImportanceThe influence of the COVID-19 pandemic on fertility rates has been suggested in the lay press and anticipated based on documented decreases in fertility and pregnancy rates during previous major societal and economic shifts. Anticipatory planning for birth rates is important for health care systems and government agencies to accurately estimate size of economy and model working and/or aging populations.ObjectiveTo use projection modeling based on electronic health care records in a large US university medical center to estimate changes in pregnancy and birth rates prior to and after the COVID-19 pandemic societal lockdowns.Design, setting, and participantsThis cohort study included all pregnancy episodes within a single US academic health care system retrospectively from 2017 and modeled prospectively to 2021. Data were analyzed September 2021.ExposuresPre- and post-COVID-19 pandemic societal shutdown measures.Main outcomes and measuresThe primary outcome was number of new pregnancy episodes initiated within the health care system and use of those episodes to project birth volumes. Interrupted time series analysis was used to assess the degree to which COVID-19 societal changes may have factored into pregnancy episode volume. Potential reasons for the changes in volumes were compared with historical pregnancy volumes, including delays in starting prenatal care, interruptions in reproductive endocrinology and infertility services, and preterm birth rates.ResultsThis cohort study documented a steadily increasing number of pregnancy episodes over the study period, from 4100 pregnancies in 2017 to 4620 in 2020 (28 284 total pregnancies; median maternal [interquartile range] age, 30 [27-34] years; 18 728 [66.2%] White women, 3794 [13.4%] Black women; 2177 [7.7%] Asian women). A 14% reduction in pregnancy episode initiation was observed after the societal shutdown of the COVID-19 pandemic (risk ratio, 0.86; 95% CI, 0.79-0.92; P < .001). This decrease appeared to be due to a decrease in conceptions that followed the March 15 mandated COVID-19 pandemic societal shutdown. Prospective modeling of pregnancies currently suggests that a birth volume surge can be anticipated in summer 2021.Conclusions and relevanceThis cohort study using electronic medical record surveillance found an initial decline in births associated with the COVID-19 pandemic societal changes and an anticipated increase in birth volume. Future studies can further explore how pregnancy episode volume changes can be monitored and birth rates projected in real-time during major societal events.

Project description:IntroductionObservational studies of COVID-19 vaccines' effectiveness can provide crucial information regarding the strength and durability of protection against SARS-CoV-2 infection and whether the protective response varies across different patient subpopulations and in the context of different SARS-CoV-2 variants.MethodsWe used a test-negative study design to assess vaccine effectiveness against SARS-CoV-2 infection and severe COVID-19 resulting in hospitalization, intensive care unit admission, or death using electronic health records data of 170,741 adults who had been tested for COVID-19 at the University of Michigan Medical Center between January 1 and December 31, 2021. We estimated vaccine effectiveness by comparing the odds of vaccination between cases and controls during each 2021 calendar quarter and stratified all outcomes by vaccine type, patient demographic and clinical characteristics, and booster status.ResultsUnvaccinated individuals had more than double the rate of infections (12.1% vs 4.7%) and >3 times the rate of severe COVID-19 outcomes (1.4% vs 0.4%) than vaccinated individuals. COVID-19 vaccines were 62.1% (95% CI=60.3, 63.8) effective against a new infection, with protection waning in the last 2 quarters of 2021. The vaccine effectiveness against severe disease overall was 73.7% (95% CI=69.6, 77.3) and remained high throughout 2021. Data from the last quarter of 2021 indicated that adding a booster dose augmented effectiveness against infection up to 87.3% (95% CI=85.0, 89.2) and against severe outcomes up to 94.0% (95% CI=89.5, 96.6). Pfizer-BioNTech and Moderna vaccines showed comparable performance when controlling for vaccination timing. Vaccine effectiveness was greater in more socioeconomically affluent areas and among healthcare workers; otherwise, we did not detect any significant modification of vaccine effectiveness by covariates, including gender, race, and SES.ConclusionsCOVID-19 vaccines were highly protective against infection and severe COVID-19 resulting in hospitalization, intensive care unit admission, or death. Administration of a booster dose significantly increased vaccine effectiveness against both outcomes. Ongoing surveillance is required to assess the durability of these findings.

Dataset Information

Predicting COVID-19 mortality with electronic medical records.

Publications

Predicting COVID-19 mortality with electronic medical records.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets