Machine learning models for screening clinically significant nephrolithiasis in overweight and obese populations.

PURPOSES: Our aim is to build and evaluate models to screen for clinically significant nephrolithiasis in overweight and obesity populations using machine learning (ML) methodologies and simple health checkup clinical and urine parameters easily obtained in clinics. METHODS: We developed ML models to screen for clinically significant nephrolithiasis (kidney stone > 2 mm) in overweight and obese populations (body mass index, BMI ≥ 25 kg/m2) using gender, age, BMI, gout, diabetes mellitus, estimated glomerular filtration rate, bacteriuria, urine pH, urine red blood cell counts, and urine specific gravity. The data were collected from hospitals in Kaohsiung, Taiwan between 2012 and 2021. RESULTS: Of the 2928 subjects we enrolled, 1148 (39.21%) had clinically significant nephrolithiasis and 1780 (60.79%) did not. The testing dataset consisted of data collected from 574 subjects, 235 (40.94%) with clinically significant nephrolithiasis and 339 (59.06%) without. One model had a testing area under curve of 0.965 (95% CI, 0.9506-0.9794), a sensitivity of 0.860 (95% CI, 0.8152-0.9040), a specificity of 0.947 (95% CI, 0.9230-0.9708), a positive predictive value of 0.918 (95% CI, 0.8820-0.9544), and negative predictive value of 0.907 (95% CI, 0.8756-0.9371). CONCLUSION: This ML-based model was found able to effectively distinguish the overweight and obese subjects with clinically significant nephrolithiasis from those without. We believe that such a model can serve as an easily accessible and reliable screening tool for nephrolithiasis in overweight and obesity populations and make possible early intervention such as lifestyle modifications and medication for prevention stone complications.

Primary antibiotic resistance of Helicobacter pylori in the Asia-Pacific region between 1990 and 2022: an updated systematic review and meta-analysis.

BACKGROUND: We previously showed rising primary antibiotic resistance of Helicobacter pylori during 1990-2015 in the Asia-Pacific region. However, whether primary antibiotic resistance continues to rise is unknown. Therefore, we aimed to assess the latest prevalence of H pylori antibiotic resistance in this region. METHODS: We did an updated systematic review and meta-analysis of observational studies and randomised controlled trials published in PubMed, Embase, and Cochrane Library between Jan 1, 1990, and July 12, 2023. Studies investigating primary H pylori resistance to clarithromycin, metronidazole, levofloxacin, amoxicillin, or tetracycline in individuals naive to eradication therapy in the Asia-Pacific region (as defined by the UN geoscheme) were eligible for inclusion. There were no language restrictions. Studies that focused on specific subpopulations (eg, children) were excluded. Using a standardised extraction form, two authors independently reviewed and extracted summary data from all eligible articles. The updated prevalence of antibiotic resistance was generated by meta-analysis under a random-effects model and subgroup analyses were done by countries and periods of study. Between-study variability was assessed by use of I2. The study is registered in PROSPERO, CRD42022339956. FINDINGS: A total of 351 studies, including 175 new studies and 176 studies from our previous analysis, were included in this meta-analysis. The overall prevalence of primary antibiotic resistance of H pylori between 1990 and 2022 was 22% (95% CI 20-23; I2=96%) for clarithromycin, 52% (49-55; I2=99%) for metronidazole, 26% (24-29; I2=96%) for levofloxacin, 4% (3-5; I2=95%) for tetracycline, and 4% (3-5; I2=95%) for amoxicillin. Prevalence varied considerably between countries and across study periods. From 1990 to 2022, the prevalence of primary resistance increased for clarithromycin, metronidazole, and levofloxacin but remained stable for amoxicillin and tetracycline. The latest primary resistance prevalences were 30% (95% CI 28-33; I2=93%) for clarithromycin, 61% (55-66; I2=99%) for metronidazole, 35% (31-39; I2=95%) for levofloxacin, 4% (2-6; I2=96%) for tetracycline, and 6% (4-8; I2=96%) for amoxicillin in the Asia-Pacific region. INTERPRETATION: Treatment guidelines should be adapted in response to the rising primary resistance of key antibiotics for H pylori eradication. A global policy to control and monitor the antibiotic resistance of H pylori is urgently needed. FUNDING: Ministry of Health and Welfare of Taiwan, National Science and Technology Council of Taiwan, and National Taiwan University. TRANSLATION: For the Chinese translation of the abstract see Supplementary Materials section.