November 18, 2026
Health news, explained with evidence
LIVE
Understanding and Addressing Love Handles Through Lifestyle Changes Ciele Releases New Woolmark-Certified Merino Winter Running Apparel Preventive Services Task Force Resumes Meetings Under New Leadership Blood-Based Genetic Signature May Predict CAR T-Cell Therapy Success in Lymphoma Ultraprocessed Diets May Impact Brain Reward Systems in Younger Adults Addressing Body Image and the Reality of Gluteal Anatomy Migraine and Smoking Linked to Increased Early Stroke Risk in Women CBD Oil Found Ineffective for Managing Behavioral Issues in Youths with Intellectual Disabilities Expert Advice on Hydration Gear Sparks Debate Among Recreational Runners A Structured Approach to Beginning a Strength and Cardio Routine Understanding and Addressing Love Handles Through Lifestyle Changes Ciele Releases New Woolmark-Certified Merino Winter Running Apparel Preventive Services Task Force Resumes Meetings Under New Leadership Blood-Based Genetic Signature May Predict CAR T-Cell Therapy Success in Lymphoma Ultraprocessed Diets May Impact Brain Reward Systems in Younger Adults Addressing Body Image and the Reality of Gluteal Anatomy Migraine and Smoking Linked to Increased Early Stroke Risk in Women CBD Oil Found Ineffective for Managing Behavioral Issues in Youths with Intellectual Disabilities Expert Advice on Hydration Gear Sparks Debate Among Recreational Runners A Structured Approach to Beginning a Strength and Cardio Routine

Machine Learning Model Predicts Daily Infection Risk in Leukemia Chemotherapy Patients

🔬 Research 2 min read 👁 4

Researchers in Finland have developed and validated a machine learning model that uses routine clinical data to predict the daily risk of febrile neutropenia in acute myeloid leukemia patients undergoing intensive chemotherapy.

🔬Research

Key points

  • New machine learning model predicts daily febrile neutropenia risk in acute myeloid leukemia patients.
  • The algorithm relies on seven routine clinical variables, including temperature and lab counts.
  • Researchers tested the model using data from two Finnish university hospital districts.

Infections represent a major hurdle during intensive chemotherapy for acute myeloid leukemia, frequently driving up illness and mortality rates. To address the lack of early detection tools, investigators at Helsinki University Hospital and Turku University Hospital built and tested a machine learning algorithm to forecast the daily risk of febrile neutropenia over a 48-hour window.

The retrospective observational study utilized registry data from two university hospital districts in Finland, analyzing a cohort of adult patients with newly diagnosed acute myeloid leukemia. Utilizing the Extreme Gradient Boosting algorithm, the model evaluated 1.2 million clinical data points based on seven key variables: white blood cell count, body temperature, duration since the start of the treatment cycle, C-reactive protein trends, absolute neutrophil count, treatment phase, and prior antibiotic exposure. The development cohort achieved an area under the receiver operating characteristic curve of 0.91, while external validation yielded an area under the curve of 0.79.

What to know: While the findings suggest that routinely gathered metrics can help forecast acute infection risks, the tool remains in the research phase and requires prospective validation before it can be integrated into regular clinical workflows. Readers should consult qualified healthcare professionals regarding any personal medical decisions or cancer treatment plans.

Source Nature Health Sciences — nature.com/articles/s43856-026-02001-x ↗

Contact the newsroom

Got a tip, a proposal or a partnership question? Write to us and we will reply shortly.