Comparative evaluation of a language model and human specialists in the application of European guidelines for the management of inflammatory bowel diseases and malignancies.

BACKGROUND: Society guidelines on colorectal dysplasia screening, surveillance, and endoscopic management in inflammatory bowel disease (IBD) are complex, and physician adherence to them is suboptimal. We aimed to evaluate the use of ChatGPT, a large language model, in generating accurate guideline-based recommendations for colorectal dysplasia screening, surveillance, and endoscopic management in IBD in line with European Crohn's and Colitis Organization (ECCO) guidelines. METHODS: 30 clinical scenarios in the form of free text were prepared and presented to three separate sessions of ChatGPT and to eight gastroenterologists (four IBD specialists and four non-IBD gastroenterologists). Two additional IBD specialists subsequently assessed all responses provided by ChatGPT and the eight gastroenterologists, judging their accuracy according to ECCO guidelines. RESULTS: ChatGPT had a mean correct response rate of 87.8%. Among the eight gastroenterologists, the mean correct response rates were 85.8% for IBD experts and 89.2% for non-IBD experts. No statistically significant differences in accuracy were observed between ChatGPT and all gastroenterologists (P=0.95), or between ChatGPT and the IBD experts and non-IBD expert gastroenterologists, respectively (P=0.82). CONCLUSIONS: This study highlights the potential of language models in enhancing guideline adherence regarding colorectal dysplasia in IBD. Further investigation of additional resources and prospective evaluation in real-world settings are warranted.

Diagnosis and Classification of 17 Diseases from 1404 Subjects via Pattern Analysis of Exhaled Molecules.

We report on an artificially intelligent nanoarray based on molecularly modified gold nanoparticles and a random network of single-walled carbon nanotubes for noninvasive diagnosis and classification of a number of diseases from exhaled breath. The performance of this artificially intelligent nanoarray was clinically assessed on breath samples collected from 1404 subjects having one of 17 different disease conditions included in the study or having no evidence of any disease (healthy controls). Blind experiments showed that 86% accuracy could be achieved with the artificially intelligent nanoarray, allowing both detection and discrimination between the different disease conditions examined. Analysis of the artificially intelligent nanoarray also showed that each disease has its own unique breathprint, and that the presence of one disease would not screen out others. Cluster analysis showed a reasonable classification power of diseases from the same categories. The effect of confounding clinical and environmental factors on the performance of the nanoarray did not significantly alter the obtained results. The diagnosis and classification power of the nanoarray was also validated by an independent analytical technique, i.e., gas chromatography linked with mass spectrometry. This analysis found that 13 exhaled chemical species, called volatile organic compounds, are associated with certain diseases, and the composition of this assembly of volatile organic compounds differs from one disease to another. Overall, these findings could contribute to one of the most important criteria for successful health intervention in the modern era, viz. easy-to-use, inexpensive (affordable), and miniaturized tools that could also be used for personalized screening, diagnosis, and follow-up of a number of diseases, which can clearly be extended by further development.

Programmed Nanoparticles for Tailoring the Detection of Inflammatory Bowel Diseases and Irritable Bowel Syndrome Disease via Breathprint.

Chemical sensors based on programmable molecularly modified gold nanoparticles are tailored for the detection and discrimination between the breathprint of irritable bowel syndrome (IBS) and inflammatory bowel diseases (IBD). The sensors are examined in both lab- and real-world clinical conditions. The results reveal a discriminative power accuracy of 81% between IBD and IBS and 75% between Crohn's and Colitis states.

Rac1 Polymorphisms and Thiopurine Efficacy in Children With Inflammatory Bowel Disease.

OBJECTIVES: Thiopurines are effective for maintenance of remission in inflammatory bowel disease (IBD) in only about half of patients. Predictors of response may assist in selecting the most appropriate patients for thiopurine therapy. Thiopurines inhibit Rac1, a GTPase that exerts an antiapoptotic effect on T-lymphocytes. A genetic association was recently demonstrated between a Rac1 single nucleotide polymorphism (SNP) and poorer response to thiopurines in adult patients with Crohn disease. We aimed to determine whether Rac1 SNPs are associated with response to thiopurines in children with IBD. METHODS: Children with IBD treated with thiopurines were prospectively followed for 1 year and were genotyped for 3 Rac1 SNPs previously found to be relevant to IBD: rs10951982, rs4720672, and rs34932801. The rate of sustained steroid-free remission (SSFR) without treatment escalation by 12 months was compared between wild types (WTs) and heterozygotes. RESULTS: A total of 59 patients were studied (63% boys, 80% having Crohn disease, mean age 13 ±â€Š4.1). Nineteen of the 41 WT (46%) and 9 of the 15 (60%) heterozygotes for rs10951982 were in SSFR (P = 0.55). Similarly, 21 of the 45 (47%) WT and 8 of the 12 (67%) heterozygotes for rs4720672 were in remission (P = 0.33). Finally, 21 of the 45 (47%) WT and 3 of the 5 (60%) heterozygotes for rs34932801 were in remission (P = 0.66). All of the 3 comparisons remained nonsignificant in a sensitivity analysis of only the patients with Crohn disease. CONCLUSIONS: We did not find an association between 3 Rac1 SNPs and thiopurine effectiveness by 12 months in a prospective study of children with IBD. Other predictors of response should be sought to optimize patient selection for thiopurine therapy.

Risk factors for serious adverse effects of thiopurines in patients with Crohn's disease.

PURPOSE: Thiopurines are effective in attaining and maintaining remission in patients with inflammatory bowel diseases (IBD). The major drawback of these drugs are their serious adverse effects (SAE), highlighting the importance of preemptive identification of patients at risk. We aimed to examine whether gene polymorphisms in GSTM1, GSTT1 and TPMT, combined with various clinical parameters, can predict thiopurine induced SAE. METHODS: A retrospective cohort of 176 Crohn's Disease (CD) patients treated with thiopurines (131 with 6MP and 45 with azathioprine) was genotyped for common polymorphisms in GSTM1, GSTT1 and TPMT. Clinical data including SAE, age, ethnicity, gender and smoking status were extracted from patient charts. SAEs evaluated were myelosuppression, hepatotoxicity and pancreatitis. Associations between demographic, clinical, and genetic variables and thiopurine induced SAE were assessed. RESULTS: Twenty-four patients (14%) developed SAE, revealing a significant association between thiopurine induced SAE and GSTM1-null genotype (P=0.05), older age (P=0.016) and active smoking status (P=0.043) and SAE. On multi-variant analysis, past or current smokers were at increased risk for developing thiopurine related SAE (OR 2.915, CI 95%: 1.199- 7.084), specifically pancreatitis (p<0.001). No association was found between TPMT or GSTT1 polymorphisms and the development of SAE. CONCLUSIONS: Active smoking and GSTM1-null genotype appear to be risk factors for thiopurine induced SAEs (i.e. myelosuppression, hepatotoxicity and pancreatitis) in patients with CD. Corroboration of these associations in larger cohorts is warranted.

Thiopurine effectiveness in patients with Crohn's disease: a study of genetic and clinical predictive factors.

BACKGROUND: Thiopurines are efficacious in the treatment of Crohn's disease and were recently shown to induce T-cell apoptosis by modulation of Rac1 activation. To assess whether polymorphisms in Rac1 and other apoptosis-related genes, combined with clinical parameters, can predict response to thiopurines. METHODS: A retrospective cohort of 156 thiopurine-treated patients with Crohn's disease was genotyped for 11 single-nucleotide polymorphisms (SNPs): 9 SNPs in Rac1, 1 SNP in the Fas ligand -843 T>C, and 1 SNP in the Caspase-9 93 C>T. Clinical data were extracted from the medical charts. Odds ratios (ORs) and 95% confidence intervals (CIs) of the association between demographic, clinical, and genetic variables and thiopurine response rates were calculated. RESULTS: The overall response rate to thiopurines was 74% (115/156). The Rac1 SNP rs34932801 heterozygote genotype GC was associated with a lower response rate compared with the wild-type GG genotype (46% versus 76%; OR = 0.26; 95% CI, 0.08-0.91; P = 0.036). Only wild-type homozygotes were found for 5 Rac1 SNPs. None of the other 3 Rac1 SNPs were associated with response to thiopurines. Patients with Montreal B3 behavior pattern responded worse than those with a B1 behavior pattern (59%, versus 80%; OR = 0.37; 95% CI, 0.17-0.83; P = 0.016). Sephardic Jews had a lower response rate to thiopurines compared with Jews of Ashkenazi or mixed ancestry (60% versus 82%; OR = 0.32; 95% CI, 0.15-0.69, P = 0.003). CONCLUSIONS: Rac1 SNP rs34932801carriage, Montreal B3 disease behavior, and a Sephardic Jewish origin were associated with unfavorable response to thiopurines. Corroboration of these associations in larger cohorts is warranted.

Proactive screening in Israel identifies alarming prevalence of malnutrition among hospitalized patients--action is needed.

OBJECTIVE: Malnourished patients suffer from higher morbidity and mortality rates than well-nourished patients do. However, few studies have controlled the outcomes for the underlying illnesses. Our aim was to determine the prevalence of malnutrition among patients admitted to the internal medicine ward and to determine whether malnutrition is an independent risk factor for adverse outcomes in these settings. METHODS: Consecutive patients screened for malnutrition with the MUST (Malnutrition Universal Screening Tool), admitted to an internal medicine department, were included in this study. Demographic data, background disease, laboratory results, length of stay, and mortality rates were retrieved from the computerized file and Charlson Comorbidity Index (CCI) was calculated. Univariate and multivariate analyses were used to check for the association of malnutrition and outcome measures. RESULTS: One thousand consecutive patients were included in the study. Mean age was 67.6 y; 25.4% of patients were found to be at high risk for malnutrition. Patients at high risk for malnutrition had significantly longer length of stay and mortality rates than well-nourished patients (9.7 d versus 6.2 d and 19.3% versus 3.2%; accordingly [P < 0.001]). On multivariate analyses, increased mortality was found to be associated with a high risk for malnutrition as well as pneumonia, acute myocardial infarction, acute renal failure, or shock on admission and a high CCI score. CONCLUSION: The prevalence of malnutrition among hospitalized patients, as measured by the MUST score, is common. Malnutrition is prevalent and represents an independent and significant risk factor for in-hospital mortality and increased length of stay in patients admitted to the internal medicine ward.