Related Experiment Video
Updated: Jan 20, 2026
Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
Closing the Gap in Surveillance and Audit of Invasive Mold Diseases for Antifungal Stewardship Using Machine Learning
Diva Baggio1,2, Trisha Peel1, Anton Y Peleg1,3
1Department of Infectious Diseases, The Alfred Hospital and Central Clinical School, Monash University, Melbourne 3004, VIC, Australia.
Abstract:
Clinical audit of invasive mold disease (IMD) in hematology patients is inefficient due to the difficulties of case finding. This results in antifungal stewardship (AFS) programs preferentially reporting drug cost and consumption rather than measures that actually reflect quality of care. We used machine learning-based natural language processing (NLP) to non-selectively screen chest tomography (CT) reports for pulmonary IMD, verified by clinical review against international definitions and benchmarked against key AFS measures. NLP screened 3014 reports from 1 September 2008 to 31 December 2017, generating 784 positives that after review, identified 205 IMD episodes (44% probable-proven) in 185 patients from 50,303 admissions. Breakthrough-probable/proven-IMD on antifungal prophylaxis accounted for 60% of episodes with serum monitoring of voriconazole or posaconazole in the 2 weeks prior performed in only 53% and 69% of episodes, respectively. Fiberoptic bronchoscopy within 2 days of CT scan occurred in only 54% of episodes. The average turnaround of send-away bronchoalveolar galactomannan of 12 days (range 7-22) was associated with high empiric liposomal amphotericin consumption. A random audit of 10% negative reports revealed two clinically significant misses (0.9%, 2/223). This is the first successful use of applied machine learning for institutional IMD surveillance across an entire hematology population describing process and outcome measures relevant to AFS. Compared to current methods of clinical audit, semi-automated surveillance using NLP is more efficient and inclusive by avoiding restrictions based on any underlying hematologic condition, and has the added advantage of being potentially scalable.
Insights
Machine learning-based natural language processing (NLP) improves invasive mold disease (IMD) surveillance in hematology patients. This approach enhances antifungal stewardship (AFS) by providing better quality of care measures than traditional drug cost tracking.
Area of Science:
- Medical Informatics
- Hematology
- Infectious Diseases
Background:
- Clinical audits for invasive mold disease (IMD) in hematology patients are inefficient due to case-finding challenges.
- Antifungal stewardship (AFS) programs often focus on drug costs rather than quality of care metrics.
- Pulmonary IMD surveillance is critical for patient outcomes in immunocompromised populations.
Purpose of the Study:
- To implement and evaluate a machine learning-based natural language processing (NLP) system for non-selective screening of chest tomography (CT) reports for pulmonary IMD.
- To benchmark the efficiency and inclusivity of NLP-driven surveillance against traditional clinical audit methods for AFS.
- To identify process and outcome measures relevant to AFS for hematology patients with IMD.
Main Methods:
- Utilized machine learning-based NLP to screen 3014 chest CT reports for pulmonary IMD.
- Performed clinical review of NLP-identified cases against international definitions.
- Benchmarked findings against key antifungal stewardship (AFS) measures and assessed audit misses.
Main Results:
- Identified 205 IMD episodes in 185 patients from 50,303 admissions, with 44% classified as probable-proven.
- Breakthrough IMD during antifungal prophylaxis occurred in 60% of episodes, with suboptimal medication monitoring.
- Fiberoptic bronchoscopy and diagnostic turnaround times were associated with high empiric antifungal use; NLP identified a 0.9% miss rate in a random audit.
Conclusions:
- Machine learning-based NLP offers an efficient and inclusive method for institutional IMD surveillance in hematology populations.
- This semi-automated approach provides superior process and outcome measures for antifungal stewardship compared to traditional audits.
- NLP surveillance is scalable and overcomes limitations of case-finding in clinical audits, improving quality of care assessment.
More Related Videos
06:22Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
Published on: September 19, 2025
11:38Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
Published on: October 4, 2024
Related Concept Videos
01:26Principles of Disease Surveillance
06:19Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:22Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
11:38A Live-cell Image-Based Machine Learning Strategy to Monitor Pluripotent Stem Cell Differentiation
04:04Asthma Detection Research Based on Voice Signal Processing and Machine Learning
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model