โก Quick Summary
This pilot study explored the use of machine learning models to predict urinary tract infections (UTIs) by analyzing factors such as urinary vitamin D levels, urine pH, age, and gender. The results demonstrated that a stacking model achieved an impressive 88% accuracy and a AUC-ROC of 0.93, highlighting the potential of these models in clinical settings.
๐ Key Details
- ๐ Dataset: 358 subjects analyzed
- ๐งฉ Features used: Urinary 25-hydroxyvitamin D levels, urine pH, age, gender
- โ๏ธ Technology: Twelve machine learning models assessed
- ๐ Performance: Stacking model: 88% accuracy, AUC-ROC 0.93
๐ Key Takeaways
- ๐ฌ Vitamin D deficiency is linked to increased UTI risk.
- ๐ค Machine learning models can effectively predict UTI occurrence.
- ๐ Stacking model outperformed other models with an accuracy of 88%.
- ๐ Significant difference in vitamin D levels between positive and negative urine cultures (p < 0.001).
- ๐ High specificity of 94% and sensitivity of 83% were achieved by the stacking model.
- ๐งช Further validation is needed to enhance clinical applicability.
- ๐ก Models do not identify causative pathogens or antibiotic susceptibility.
๐ Background
Urinary tract infections (UTIs) are common and can lead to significant morbidity. Recent research has indicated that vitamin D plays a crucial role in immune function, and its deficiency may contribute to the risk of infections, including UTIs. This study aims to leverage machine learning techniques to enhance the prediction and diagnosis of UTIs, potentially improving patient outcomes.
๐๏ธ Study
Conducted with a cohort of 358 subjects, this study analyzed demographic, biochemical, and microbiological data to develop machine learning models for predicting UTIs. The dataset was divided into a training set (70%) and a test set (30%), focusing on four key predictors: age, gender, urine pH, and urinary vitamin D levels.
๐ Results
The study found a significant difference in urinary 25-hydroxyvitamin D levels between individuals with positive (1.33 ยฑ 4.13 ng/mL) and negative (2.48 ยฑ 4.52 ng/mL) urine cultures (p < 0.001). The twelve machine learning models demonstrated varying degrees of performance, with accuracies ranging from 64% to 87%. Notably, the stacking model achieved an 88% accuracy, 83% sensitivity, and 94% specificity, indicating its robustness in predicting UTI risk.
๐ Impact and Implications
The findings from this study suggest that machine learning models can serve as a valuable adjunct in the diagnosis of UTIs, potentially complementing traditional culture methods. As healthcare continues to evolve with technology, these models could lead to more accurate and timely diagnoses, ultimately improving patient care and antibiotic stewardship.
๐ฎ Conclusion
This pilot study highlights the promising role of machine learning in predicting urinary tract infections through the analysis of various predictors, including vitamin D levels. With further validation and development, these models could significantly enhance clinical screening programs and contribute to better management of UTIs. The future of integrating AI in healthcare looks bright, and ongoing research is essential to fully realize its potential.
๐ฌ Your comments
What are your thoughts on the use of machine learning for predicting urinary tract infections? We would love to hear your insights! ๐ฌ Leave your comments below or connect with us on social media:
Multifactor machine learning models for predicting urinary tract infections: a pilot study.
Abstract
PURPOSE: Vitamin D, a fat-soluble prohormone essential for calcium-phosphate homeostasis and bone health, also regulates innate and adaptive immunity through receptors expressed on B cells, T cells, and antigen-presenting cells capable of synthesizing its active form. Deficiency in vitamin D is linked to dysregulated immune responses and an increased risk of autoimmune diseases and infections, particularly urinary tract infections (UTIs) in both children and adults. Here, we explore 12 machine learning models that utilize urinary 25-hydroxyvitamin D (25(OH)D) levels, urine pH, gender, and age to predict UTIs.
METHODS: A cohort of 358 subjects was analyzed. Demographic, biochemical, and microbiological data were collected for each participant. The dataset was randomly divided into a training set (70%) and an independent test set (30%). Four predictors, age, gender, urine pH, and vitamin D, were included in the analysis. Twelve machine learning models were assessed based on accuracy, specificity, sensitivity, positive predictive value (PPV), negative predictive value (NPV), area under the ROC curve (AUC-ROC), and F1 score.
RESULTS: A significant difference in urinary 25(OH)D levels was found between individuals with positive (1.33โยฑโ4.13โฏng/mL) and negative (2.48โยฑโ4.52โฏng/mL) urine cultures (pโ<โ0.001). Using urinary 25(OH)D, urine pH, age, and gender as predictors, 12 machine learning models showed accuracies of 64-87%, sensitivities of 59-79%, specificities of 51-95%, PPVs of 61-94%, NPVs of 63-82%, AUC-ROC values of 0.63-0.93, and F1 scores of 0.63-0.86. A stacking machine learning model achieved 88% accuracy, 83% sensitivity, 94% specificity, 93% PPV, 84% NPV, AUC-ROC of 0.93, and an F1 score of 0.88.
CONCLUSION: Significant differences in urinary 25(OH)D levels between positive and negative urine cultures confirm the association between low vitamin D levels and UTI occurrence. The developed machine learning models demonstrated high accuracy and represent a promising adjunct for clinicians in UTI diagnosis. With additional validation and assay development, such models may eventually complement conventional culture methods in clinical screening programs. Further external validation using independent datasets, along with prospective studies assessing their impact on antibiotic prescribing practices, is warranted. While these models estimate UTI risk, they do not identify the causative pathogen or determine antibiotic susceptibility.
Author: [‘Grizzi F’, ‘Hegazi MAAA’, ‘Monari MN’, ‘Petrillo P’, ‘Beltrame S’, ‘Pasqualini F’, ‘Fasulo V’, ‘Vota P’, ‘Zanoni M’, ‘Frego N’, ‘Mazzieri C’, ‘Marsili E’, ‘Taverna G’]
Journal: Int Urol Nephrol
Citation: Grizzi F, et al. Multifactor machine learning models for predicting urinary tract infections: a pilot study. Multifactor machine learning models for predicting urinary tract infections: a pilot study. 2025; (unknown volume):(unknown pages). doi: 10.1007/s11255-025-04953-w