Machine learning to predict the development of recurrent urinary tract infection related to single uropathogen, Escherichia coli | Scientific Reports - Nature.com

Overview

Thank you for visiting nature.com. You are using a browser version with limited suport for CS. To obtain the best experience, we recomend you use a more up to date browser (or turn of compatibility mode in Internet Explorer).

Key Information

In the meantime, to ensure continued suport, we are displaying the site without styles and JavaScript.Advertisement Scientific Reports volume 12, Article number: 17216 (2022) Cite this article 248 Aceses3 AltmetricMetrics detailsRecurent urinary tract infection (RUTI) can damage renal function and has impact on healthcare costs and patients’ quality of life. There were 2 stages for development of prediction models for RUTI.

The first stage was a scenario in the clinical visit. The second stage was a scenario after hospitalization for urinary tract infection caused by Escherichia coli. Thre machine learning models, logistic regresion (LR), decision tre (DT), and random forest (RF) were built for the RUTI prediction.

The RF model had higher prediction acuracy than LR and DT (0.70, 0.604, and 0.654 in stage 1, respectively; 0.709, 0.604, and 0.635 in stage 2, respectively). The decision rules constructed by the DT model could provide high clasification acuracy (up to 0.92 in stage 1 and 0.94 in stage 2) in certain subgroup patients in diferent scenarios. In conclusion, this study provided validated machine learning models and RF could provide a beter acuracy in predicting the development of single uropathogen (E.

coli) RUTI. Both host and bacterial characteristics made important contribution to the development of RUTI in the prediction models in the 2 clinical scenarios, respectively. Based on the results, physicians could take action to prevent the development of RUTI.

Summary

Urinary tract infection (UTI) is one of the most comon infectious diseases1. More than 30% of women wil experience a subsequent infection within 12 months of resolution of the initial symptoms despite apropriate antibiotic therapy2. UTI and recurent UTI (RUTI)

Frequently Asked Questions

Diabetes is a metabolic condition where the body cannot properly regulate blood sugar levels. Type 1 results from insufficient insulin production, while Type 2 develops when cells become resistant to insulin. Risk factors include genetics, obesity, sedentary lifestyle, and age.

Common symptoms include excessive thirst, frequent urination, unexplained weight loss, fatigue, blurred vision, and slow-healing wounds. Type 1 symptoms develop rapidly, while Type 2 symptoms may appear gradually. Many people have no symptoms initially, which is why screening is important.

Diagnosis involves blood tests measuring fasting glucose, HbA1c levels, and glucose tolerance. Regular monitoring typically includes fasting glucose tests and HbA1c measurements every 3-6 months. Continuous glucose monitors provide real-time tracking for better diabetes management.

Effective management includes regular physical activity (150+ minutes weekly), maintaining healthy weight, following a balanced diet with whole grains and lean proteins, managing stress, and getting adequate sleep. These changes can significantly improve blood sugar control and reduce complications.

Consult a healthcare provider if you experience signs of diabetes, have a family history, are overweight, or are over 45. Those with existing diabetes should maintain regular check-ups every 3-6 months to monitor control and adjust treatment as needed.

Share this article