New Data Suggest Machine Learning Algorithms Can Accurately Predict C. Diff Infection in Hospitalized Patients

New Data Suggest Machine Learning Algorithms Can Accurately Predict C. Diff Infection in Hospitalized Patients

Findings published in the American Journal of Infection Control could help reduce clinical and economic impact of common and serious HAIs

Arlington, Va., January 20, 2022 - New data published today suggest that several commonly used machine learning algorithms (MLAs) can effectively predict which hospitalized patients will become infected with Clostridiodes difficile (C. diff). The findings, which appear in the American Journal of Infection Control (AJIC), the journal of the Association for Professionals in Infection Control and Epidemiology (APIC), could support infection prevention and early diagnosis, as well as more timely implementation of infection control measures to minimize C. diff spread.

"Our study findings suggest that MLAs could play a significant role in reducing the clinical and economic impact of healthcare-associated infections such as C. diff by providing early predictions of at-risk patients prior to them developing serious complications," said Jana Hoffman, VP of Science, Dascena, Inc. "These data are consistent with a growing body of evidence that validates artificial intelligence and MLAs as integral components of healthcare management that can improve patient outcomes and assist time-constrained clinicians in providing the best patient care."

C. diff infection (CDI) is the leading cause of hospital-acquired diarrhea and is associated with significant morbidity, mortality, and healthcare costs. There is currently no gold standard tool to assess individual patients' risk of acquiring CDI. Hoffman and her colleagues have previously published data which demonstrate that MLAs can predict patients at risk of developing other high-impact HAIs.

For the study published today, the researchers used a database comprising electronic health record (EHR) patient data from more than 700 hospitals nationwide to train and then systematically evaluate three different, classical machine-learning and deep-learning methods. They initially assessed various models of each of these methods to determine whether they could effectively predict CDI among hospitalized patients using early inpatient data, and then used a distinct, external dataset to evaluate the generalizability of the best-performing MLA models.

Results suggest that MLAs can predict CDI with excellent discrimination using just the first six hours of inpatient data. Among the three methods studied, a machine-learning method called XGBoost provided the highest overall accuracy in predicting CDI, despite being the least complex model. XGBoost also demonstrated generalizability by maintaining its predictive performance in an external dataset. The other two methods researchers evaluated, neural networks known as Deep Long Short Term Memory (D-LSTM) and one-dimensional convolutional neural network (1D-CNN), also demonstrated high levels of predictive accuracy, though were less generalizable.

The best-performing XGBoost, D-LSTM and 1D-CNN models used similar features to predict CDI among patients, all of which have previously been identified as risk factors. In this study, age was the leading CDI risk factor, followed by clinical measurements such as sodium, body mass index, white blood cell count, and heart rate; active treatment with antibiotics or proton pump inhibitors; glycated hemoglobin; and race.

"This study supports earlier research suggesting that MLAs provide reliable infection-risk prediction that can empower clinical teams to implement appropriate infection control measures at earlier time points and thereby improve healthcare outcomes," said Linda Dickey, RN, MPH, CIC, FAPIC, and 2022 APIC president.

About APIC

Founded in 1972, the Association for Professionals in Infection Control and Epidemiology (APIC) is the leading association for infection preventionists and epidemiologists. With more than 15,000 members, APIC advances the science and practice of infection prevention and control. APIC carries out its mission through research, advocacy, and patient safety; education, credentialing, and certification; and fostering development of the infection prevention and control workforce of the future. Together with our members and partners, we are working toward a safer world through the prevention of infection. Join us and learn more at apic.org.

About AJIC

As the official peer-reviewed journal of APIC, The American Journal of Infection Control(AJIC) is the foremost resource on infection control, epidemiology, infectious diseases, quality management, occupational health, and disease prevention. Published by Elsevier, AJIC also publishes infection control guidelines from APIC and the CDC. AJIC is included in Index Medicus and CINAHL. Visit AJIC atajicjournal.org.

NOTES FOR EDITORS

"A comparative analysis of machine learning approaches to predict C. difficile infection in hospitalized patients," by Saarang Panchavati, Nicole S. Zelin, MD, Anurag Garikipati, MS, Emily Pellegrini, MEng, Zohora Iqbal, PhD, Gina Barnes, MPH, Jana Hoffman, PhD, Jacob Calvert, MSc, Qingqing Mao, PhD, and Ritankar Das, MSc, was published online in AJIC on January 20, 2022. The article may be found online at: https://doi.org/10.1016/j.ajic.2021.11.012

AUTHORS

Zohora Iqbal, PhD (Corresponding author:[email protected])

Dascena, Inc.

Houston, TX, USA

Saarang Panchavati

Dascena, Inc.

Houston, TX, USA

Nicole S. Zelin, MD

Dascena, Inc.

Houston, TX, USA

Anurag Garikipati, MS

Dascena, Inc.

Houston, TX, USA

Emily Pellegrini, MEng

Dascena, Inc.

Houston, TX, USA

Gina Barnes, MPH

Dascena, Inc.

Houston, TX, USA

Jana Hoffman, PhD

Dascena, Inc.

Houston, TX, USA

Jacob Calvert, MSc

Dascena, Inc.

Houston, TX, USA

Qingqing Mao, PhD

Dascena, Inc.

Houston, TX, USA

Ritankar Das, MSc

Dascena, Inc.

Houston, TX, USA

Media contacts: Aaron Cohen, (301) 633-6773, [email protected]; Liz Garman, 202-365-7421, [email protected]

Public link

Please use the above public link if you want to share this noodl on another website.