Fuzzy logic in respiratory medicine: a systematic review of predictive and diagnostic applications

There is increasing interest in the use of artificial intelligence (AI) to assist with respiratory diagnosis and risk prediction. Fuzzy logic is a form of AI that has the advantage of being transparent and interpretable, compared to alternatives such as deep neural networks. We systematically reviewed applications of fuzzy logic for outcome prediction in respiratory medicine.

We searched PubMed and IEEE Xplore from inception to November 2024 for studies which applied fuzzy logic to respiratory outcome prediction and diagnosis. Three reviewers independently screened titles and abstracts, then all five reviewers assessed full texts for eligibility. Risk of bias was assessed using PROBAST by three reviewers. We performed a narrative synthesis following the SWiM guidelines due to heterogeneity.

From 982 records, 29 studies (1998-2024) met the inclusion criteria. Studies addressed asthma (n = 5), obstructive sleep apnoea (n = 8), lung cancer (n = 4) and a variety of other conditions. Mamdani-type systems were the most frequently used (69%). Performance varied dramatically, with sensitivity/specificity ranging from 69 to 100% and 19-100%, respectively. The studies which displayed the highest accuracy (>95%) incorporated well-defined clinical variables, particularly for asthma and tuberculosis. However, 69% of studies displayed high risk of bias, frequently due to inadequate validation.

Fuzzy logic systems show potential as a transparent alternative to neural network-based machine learning for outcome prediction and diagnosis in respiratory medicine. However, clinical implementation is limited by frequent methodological limitations. Future research requires prospective validation studies and standardised reporting before fuzzy logic can enhance respiratory medicine.