Big data model improves prediction of key hospital outcome

February 18, 2016 by Ziba Kashef, Yale University
Big data model improves prediction of key hospital outcome
Credit: Shutterstock/Yale University

More than half of hospital deaths in the United States are related to severe infections, or sepsis. Yale researchers developed a prediction model, drawing on "big data" about local patients and using machine-learning methods, that proved better at identifying at-risk patients than existing clinical practices.

Currently, emergency physicians can use simple calculators or point- scoring systems known as clinical decision rules to determine which hospitalized might die from sepsis. However, these methods often fail to identify patients most at risk because they are based on limited information, derived from models that are unable to capture the complexity of data, and developed using different patient populations.

The new model developed by researchers at Yale School of Medicine and the University of Washington uses a large amount of data collected in of local patients. Known as random forest modeling, the method draws on and learns from patient data to make predictions. Their big-data method outperformed existing models and has the potential to correctly classify an additional 200-300 patients per 5,000 with .

"By using the machine-learning technique and incorporating a large amount of variables—over 500—we created a model that has the potential to better predict sepsis mortality in patients admitted to the hospital," said Dr. R. Andrew Taylor, assistant professor of and first author on the study. Having proved the concept, Taylor and his colleagues hope to test the model in real-time with patients in New Haven while also promoting the big-data approach. "Our goal is to make patients' data work for them and create learning health systems where predictive models are developed and ultimately applied to improve patient care," he said.

The study published on this month in Academic Emergency Medicine.

Explore further: Electronic healthcare records data reveal factors linked to emergency department revisits

More information: R. Andrew Taylor et al. Prediction of In-hospital Mortality in Emergency Department Patients with Sepsis: A Local Big Data Driven, Machine Learning Approach, Academic Emergency Medicine (2015). DOI: 10.1111/acem.12876

Related Stories

Electronic healthcare records data reveal factors linked to emergency department revisits

February 12, 2016
A new study has identified distinctions in patient diagnoses and different patterns of Emergency Department usage between individuals who are more or less likely to return to the ED for care within a 72-hour period. These ...

Advances made against the deadly infection complication, sepsis

October 21, 2015
Sepsis is an inflammatory response to infection that's known to develop in hospital settings and can turn deadly when it's not discovered early on. In a new study, a hospital surveillance program focusing on reducing the ...

New depression model outperforms psychiatrists

January 21, 2016
A simple questionnaire filled out by depressed patients can help identify whether a particular medication is likely to help them, according to a new study by Yale University researchers published Jan. 20 in the journal Lancet ...

Sepsis and shock response team in the ED reduces mortality

October 19, 2015
Researchers from Mayo Clinic in Jacksonville, Florida, formed a multidisciplinary sepsis and shock response team (SSRT) to help alert emergency department providers when these disorders are suspected. An automated electronic ...

Sepsis tied to higher post-discharge mortality risk

February 9, 2016
(HealthDay)—Sepsis survivors have a substantially increased risk of all-cause mortality and major adverse cardiovascular events after discharge, according to a study published online Jan. 25 in the American Journal of Respiratory ...

High volume of severe sepsis patients may result in better outcomes

January 17, 2014
A recent study led by Boston University School of Medicine (BUSM) shows that "practice may make perfect" when it comes to caring for patients with severe sepsis. The study showed that patients admitted to academic medical ...

Recommended for you

Self-lubricating latex could boost condom use: study

October 17, 2018
A perpetually unctuous, self-lubricating latex developed by a team of scientists in Boston could boost the use of condoms, they reported Wednesday in the journal Royal Society Open Science.

How healthy will we be in 2040?

October 17, 2018
A new scientific study of forecasts and alternative scenarios for life expectancy and major causes of death in 2040 shows all countries are likely to experience at least a slight increase in lifespans. In contrast, one scenario ...

Father's nicotine use can cause cognitive problems in children and grandchildren

October 16, 2018
A father's exposure to nicotine may cause cognitive deficits in his children and even grandchildren, according to a study in mice publishing on October 16 in the open-access journal PLOS Biology by Pradeep Bhide of Florida ...

Study finds evidence of intergenerational transmission of trauma among ex-POWs from the Civil War

October 16, 2018
A trio of researchers affiliated with the National Bureau of Economic Research has found evidence that suggests men who were traumatized while POWs during the U.S. Civil War transmitted that trauma to their offspring—many ...

Many supplements contain unapproved, dangerous ingredients: study

October 13, 2018
(HealthDay)—U.S. health officials have issued more than 700 warnings during the last decade about the sale of dietary supplements that contain unapproved and potentially dangerous drug ingredients, new research reveals.

Age at which women experience their first period is linked to their sons' age at puberty

October 12, 2018
The age at which young women experience their first menstrual bleeding is linked to the age at which their sons start puberty, according to the largest study to investigate this association in both sons and daughters.

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.