Saturday, November 23, 2024
Subscribe American Journal of Medicine Free Newsletter
clinical practicePredicting In-Hospital Mortality at Admission to the Medical Ward: A Big-Data Machine...

Predicting In-Hospital Mortality at Admission to the Medical Ward: A Big-Data Machine Learning Model

General medical wards admit high-risk patients. Artificial intelligence algorithms can use big data for developing models to assess patients’ risk stratification. The aim of this study was to develop a mortality prediction machine learning model using data available at the time of admission to the medical ward.

Methods

We included consecutive patients (ages 18-100) admitted to medical wards at a single medical center (January 1, 2013-December 31, 2018). We constructed a machine learning model using patient characteristics, comorbidities, laboratory tests, and patients’ emergency department (ED) management. The model was trained on data from the years 2013 to 2017 and validated on data from the year 2018. The area under the curve (AUC) for mortality prediction was used as an outcome metric. Youden index was used to find an optimal sensitivity-specificity cutoff point.

Results

Of the 118,262 patients admitted to the medical ward, 6311 died (5.3%). The single variables with the highest AUCs were medications administered in the ED (AUC = 0.74), ED diagnosis (AUC = 0.74), and albumin (AUC = 0.73). The machine learning model yielded an AUC of 0.924 (95% confidence interval [CI]: 0.917-0.930). For Youden index, a sensitivity of 0.88 (95% CI: 0.86-0.89) and specificity of 0.83 (95% CI: 0.83–0.83) were observed. This corresponds to a false-positive rate of 1:5.9 and negative predictive value of 0.99.

Conclusion

A machine learning model outperforms single variables predictions of in-hospital mortality at the time of admission to the medical ward. Such a decision support tool has the potential to augment clinical decision-making regarding level of care needed for admitted patients.

To read this article in its entirety please visit our website.

-Shelly Soffer, MD, Eyal Klang, MD, Yiftach Barash, MD, MSc, Ehud Grossman, MD, Eyal Zimlichman, MD

This article originally appeared in the February 2021 issue of The American Journal of Medicine.

Latest Posts

lupus

Sarcoidosis with Lupus Pernio in an Afro-Caribbean Man

A 54-year-old man of Afro-Caribbean ancestry presented with a 2-month history of nonproductive cough, 10-day history of constant subjective fevers, and a 1-day history...
Flue Vaccine

Flu Vaccination to Prevent Cardiovascular Mortality (video)

0
"Influenza can cause a significant burden on patients with coronary artery disease," write Barbetta et al in The American Journal of Medicine. For this...
varicella zoster

Varicella Zoster Virus-Induced Complete Heart Block

0
Complete heart block is usually caused by chronic myocardial ischemia and fibrosis but can also be induced by bacterial and viral infections. The varicella...
Racial justice in healthcare

Teaching Anti-Racism in the Clinical Environment

0
"Teaching Anti-Racism in the Clinical Environment: The Five-Minute Moment for Racial Justice in Healthcare" was originally published in the April 2023 issue of The...
Invisible hand of the market

The ‘Invisible Hand’ Doesn’t Work for Prescription Drugs

0
Pharmaceutical innovation has been responsible for many “miracles of modern medicine.” Reliance on the “invisible hand” of Adam Smith to allocate resources in the...
Joseph S. Alpert, MD

New Coronary Heart Disease Risk Factors

0
"New Coronary Heart Disease Risk Factors" by AJM Editor-in Chief Joseph S. Alpert, MD was originally published in the April 2023 issue of The...
Cardiovascular risk from noncardiac activities

Cardiac Risk Related to Noncardiac & Nonsurgical Activities

0
"Assessment of Cardiovascular Risk for Noncardiac and Nonsurgical Activities" was originally published in the April 2023 issue of The American Journal of Medicine. Cardiovascular risk...