Enhanced early prediction of clinically relevant neonatal hyperbilirubinemia with machine learning.

Pediatr Res

Adaptive Systems and Medical Data Science, Department of Mathematics and Computer Science, University of Basel, Basel, Switzerland.

Published: July 2019

Background: Machine learning models may enhance the early detection of clinically relevant hyperbilirubinemia based on patient information available in every hospital.

Methods: We conducted a longitudinal study on preterm and term born neonates with serial measurements of total serum bilirubin in the first two weeks of life. An ensemble, that combines a logistic regression with a random forest classifier, was trained to discriminate between the two classes phototherapy treatment vs. no treatment.

Results: Of 362 neonates included in this study, 98 had a phototherapy treatment, which our model was able to predict up to 48 h in advance with an area under the ROC-curve of 95.20%. From a set of 44 variables, including potential laboratory and clinical confounders, a subset of just four (bilirubin, weight, gestational age, hours since birth) suffices for a strong predictive performance. The resulting early phototherapy prediction tool (EPPT) is provided as an open web application.

Conclusion: Early detection of clinically relevant hyperbilirubinemia can be enhanced by the application of machine learning. Existing guidelines can be further improved to optimize timing of bilirubin measurements to avoid toxic hyperbilirubinemia in high-risk patients while minimizing unneeded measurements in neonates who are at low risk.

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41390-019-0384-xDOI Listing

Publication Analysis

Top Keywords

clinically relevant
12
machine learning
12
early detection
8
detection clinically
8
relevant hyperbilirubinemia
8
phototherapy treatment
8
enhanced early
4
early prediction
4
prediction clinically
4
relevant neonatal
4

Similar Publications

Advances in Diagnosis, Treatment and Prognostic in Aortoiliac Occlusive Disease - A Narrative Review.

Port J Card Thorac Vasc Surg

January 2025

Department of Biomedicine - Unit of Anatomy, Faculty of Medicine, University of Porto; RISE@Health, Porto, Portugal.

Background: Aortoiliac disease (AID) is a variant of peripheral artery disease involving the infrarenal aorta and iliac arteries. Similar to other arterial diseases, aortoiliac disease obstructs blood flow through narrowed lumens or by embolization of plaques. AID, when symptomatic, may present with a triad of claudication, impotence, and absence of femoral pulses, a triad also referred as Leriche Syndrome (LS).

View Article and Find Full Text PDF

Background: Malnutrition is common with esophagogastric cancers and is associated with negative outcomes. We aimed to evaluate if immunonutrition during neoadjuvant treatment improves patient's health-related quality of life (HRQOL) and reduces postoperative morbidity and toxicities during neoadjuvant treatment.

Methods: A multicenter double-blind randomized controlled trial (RCT) was undertaken.

View Article and Find Full Text PDF

The association between Chlamydia pneumoniae infection and prognosis in lung cancer patients: a prospective study.

BMC Infect Dis

January 2025

Department of Epidemiology and Health Statistics, School of Public Health, Fujian Medical University, Fuzhou, China.

Background: The prognostic value of Chlamydia pneumoniae (Cpn) infection in postoperative lung cancer patients remains unclear. This study aimed to evaluate the association between Cpn infection and survival in lung cancer patients.

Methods: This study included 309 newly diagnosed primary lung cancer patients from three hospitals in Fuzhou, China.

View Article and Find Full Text PDF

Background: Artificial Intelligence (AI) is increasingly applied in healthcare to boost productivity, reduce administrative workloads, and improve patient outcomes. In nursing, AI offers both opportunities and challenges. This study explores nurses' perspectives on implementing AI in nursing practice within the context of Jordan, focusing on the perceived benefits and concerns related to its integration.

View Article and Find Full Text PDF

Objective: Understanding healthcare-seeking propensity is crucial for optimizing healthcare utilization, especially for patients with chronic conditions like hypertension or diabetes, given their substantial burden on healthcare systems globally. This study aims to evaluate hypertensive or diabetic patients' healthcare-seeking propensity based on the severity of symptoms, categorizing symptoms as either major or minor. It also explores factors influencing healthcare-seeking propensity and examines whether healthcare-seeking propensity affects healthcare utilization and preventable hospitalizations.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!