Response accuracy of ChatGPT 3.5 Copilot and Gemini in interpreting biochemical laboratory data a pilot study.

With the release of ChatGPT at the end of 2022, a new era of thinking and technology use has begun. Artificial intelligence models (AIs) like Gemini (Bard), Copilot (Bing), and ChatGPT-3.5 have the potential to impact every aspect of our lives, including laboratory data interpretation. To assess the accuracy of ChatGPT-3.5, Copilot, and Gemini responses in evaluating biochemical data. Ten simulated patients' biochemical laboratory data, including serum urea, creatinine, glucose, cholesterol, triglycerides, low-density lipoprotein (LDL-c), and high-density lipoprotein (HDL-c), in addition to HbA1c, were interpreted by three AIs: Copilot, Gemini, and ChatGPT-3.5, followed by evaluation with three raters. The study was carried out using two approaches. The first encompassed all biochemical data. The second contained only kidney function data. The first approach indicated Copilot to have the highest level of accuracy, followed by Gemini and ChatGPT-3.5. Friedman and Dunn's post-hoc test revealed that Copilot had the highest mean rank; the pairwise comparisons revealed significant differences for Copilot vs. ChatGPT-3.5 (P = 0.002) and Gemini (P = 0.008). The second approach exhibited Copilot to have the highest accuracy of performance. The Friedman test with Dunn's post-hoc analysis showed Copilot to have the highest mean rank. The Wilcoxon Signed-Rank Test demonstrated an indistinguishable response (P = 0.5) of Copilot when all laboratory data were applied vs. the application of only kidney function data. Copilot is more accurate in interpreting biochemical data than Gemini and ChatGPT-3.5. Its consistent responses across different data subsets highlight its reliability in this context.

Changes of Certain Metabolic and Cardiovascular Markers Fructosamine, H-FABP and Lipoprotein (a) in Patients with Hypothyroidism.

BACKGROUND: Disorders of thyroid gland are common in general population, and it's the most common affecting the endocrine system after diabetes mellitus. Thyroid function regulates a wide range of metabolic parameters, as well as affects some cardiovascular disease risk factors. Fructosamine is produced by a reaction between albumin (protein) and glucose; it is used to monitor patients with diabetes for short-term glycemic changes. H-FABP is present in the cytoplasm of cardiac myocytes, and delivers fatty acids into these cells. It has been shown to increase in myocardial injury. Lipoprotein LP(a) is consist of a special apolipoprotein called apoprotein (a), and it's recognized as a cardiovascular disease independent risk factor. OBJECTIVE: To study whether certain metabolic and cardiovascular markers (fructosamine, H-FABP and lipoprotein (a) are changed in hypothyroid patients. METHODS: The current study included 280 overt hypothyroid, 272 with subclinical hypothyroidism compared with 270 healthy individuals of matched age and gender. For all subjects serum (TSH, T4, T3, FBS, HbA1c, fructosamine, triglycerides, cholesterol, lipoprotein (a), and Heart-type Fatty Acid-Binding Protein (H-FABP)) was measured. RESULTS: Serum fructosamine level significantly elevated (p value <0.05) in patient with hypothyroidism when compared with control group, and no significant change between subclinical and control groups. There is no significant change in serum H-FABP between study subjects. There is significant increase in lipoprotein (a) in patient with hypothyroidism and those with subclinical group when compared with control group. CONCLUSION: Serum fructosamine and level is significantly changed in patients with overt hypothyroidism when compared with euthyroid subjects. Also, we conclude that hypothyroidism increase risk of cardiovascular diseases by changing non-traditional marker such as lipoprotein (a), and no effect on H-FABP concentration.

Association of adiponectin gene polymorphism rs266729 with type two diabetes mellitus in Iraqi population. A pilot study.

BACKGROUND: Diabetes incidence is increasing worldwide. Many studies demonstrated that polymorphisms within the adiponectin gene could be associated with type 2 diabetes mellitus (T2DM). METHODS: A case-control study was conducted to find the association between SNP rs266729 and T2DM in Iraqi population. The study included 135 patients referring to diabetic clinic in Najaf city randomly selected based on World Health Organization (WHO) guidelines and 135 healthy controls. DNA was extracted from blood and genotyped by PCR-RFLP by using (HhaI) enzyme. Multinomial logistic regression was applied to compare the proportions of genotypes and alleles. The odds ratio for risk of developing T2DM was calculated with and without adjustment for age, sex, and BMI. RESULTS: The frequency of the G allele of rs266729 (C/G) polymorphism was significantly higher (p=0.00) in diabetic subjects (28%) compared to that in normal subjects (14%). The homozygous genotype (GG) significantly (OR=3.67, CI 95%(1.25-10.76), P=0.01) increased the risk of T2DM by three folds with respect to those of the wild type (CC) after adjustment for age, sex and BMI, furthermore the heterozygous CG genotype significantly (OR=2.45, CI 95%(1.41-4.26), P=0.001) raised the risk of T2DM by two folds. Homozygous and heterozygous genotypes of rs266729 polymorphism exhibited significant association with raised fasting insulin values (p=0.01), and decreased HDL levels (p=0.00). CONCLUSION: Adiponectin gene polymorphism rs266729 is involved in the pathogenesis of T2DM. In addition this SNP may play a role in the development of cardiovascular diseases and metabolic syndrome by affecting HDL and insulin levels.