Your browser doesn't support javascript.
Predicting COVID-19 mortality with electronic medical records.
Estiri, Hossein; Strasser, Zachary H; Klann, Jeffy G; Naseri, Pourandokht; Wagholikar, Kavishwar B; Murphy, Shawn N.
  • Estiri H; Laboratory of Computer Science, Massachusetts General Hospital, Boston, MA, 02144, USA. hestiri@mgh.harvard.edu.
  • Strasser ZH; Department of Medicine, Massachusetts General Hospital, Boston, MA, 02144, USA. hestiri@mgh.harvard.edu.
  • Klann JG; Harvard Medical School, Boston, MA, 02115, USA. hestiri@mgh.harvard.edu.
  • Naseri P; Laboratory of Computer Science, Massachusetts General Hospital, Boston, MA, 02144, USA.
  • Wagholikar KB; Department of Medicine, Massachusetts General Hospital, Boston, MA, 02144, USA.
  • Murphy SN; Harvard Medical School, Boston, MA, 02115, USA.
NPJ Digit Med ; 4(1): 15, 2021 Feb 04.
Article in English | MEDLINE | ID: covidwho-1065966
Semantic information from SemMedBD (by NLM)
1. COVID-19 COEXISTS_WITH risk factors
Subject
COVID-19
Predicate
COEXISTS_WITH
Object
risk factors
2. COVID-19 PROCESS_OF Patients
Subject
COVID-19
Predicate
PROCESS_OF
Object
Patients
3. risk factors PREDISPOSES COVID-19
Subject
risk factors
Predicate
PREDISPOSES
Object
COVID-19
4. COVID-19 COEXISTS_WITH risk factors
Subject
COVID-19
Predicate
COEXISTS_WITH
Object
risk factors
5. COVID-19 PROCESS_OF Patients
Subject
COVID-19
Predicate
PROCESS_OF
Object
Patients
6. risk factors PREDISPOSES COVID-19
Subject
risk factors
Predicate
PREDISPOSES
Object
COVID-19
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.

Full text: Available Collection: International databases Database: MEDLINE Document Type: Article Type of study: Prognostic study / Risk factors Language: English Journal: NPJ Digit Med Clinical aspect: Etiology / Prediction / Prognosis Year: 2021

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Document Type: Article Type of study: Prognostic study / Risk factors Language: English Journal: NPJ Digit Med Clinical aspect: Etiology / Prediction / Prognosis Year: 2021
...