Microvascular complications are one of the key causes of mortality among type 2 diabetic patients. This study was sought to investigate the use of a novel machine learning approach for predicting these complications using only the patient demographic, clinical, and laboratory profiles. A total of 96 Bangladeshi participants with type 2 diabetes were recruited during their routine hospital visits. All patient profiles were assessed by using a chi-squared (χ²) test to statistically determine the most important markers in predicting three microvascular complications: cardiac autonomic neuropathy (CAN), diabetic peripheral neuropathy (DPN), and diabetic retinopathy (RET). A machine learning approach based on logistic regression, random forest (RF), and support vector machine (SVM) algorithms was then developed to ensure automated clinical testing for microvascular complications in diabetic patients. The highest prediction accuracies were obtained by RF using diastolic blood pressure, albumin–creatinine ratio, and gender for CAN testing (98.67%); microalbuminuria, smoking history, and hemoglobin A1C for DPN testing (67.78%); and hemoglobin A1C, microalbuminuria, and smoking history for RET testing (84.38%). This study suggests machine learning as a promising automated tool for predicting microvascular complications in diabetic patients using their profiles, which could help prevent those patients from further microvascular complications leading to early death.

This study investigated the binding affinities of a newly synthesized 5-HT2 antagonist, AT-1015 (N-[2-[4-(5H-dibenzo[a,d]cyclohepten-5-ylidene)-piperidino]ethyl]-1-formyl-4-piperidinecarboxamide monohydrochloride monohydrate) for [3H]ketanserin bindings to 5-HT2 receptors in the rabbit cerebral cortex membranes using the radioligand binding assay method. The affinity of this compound was also compared with other 5-HT2-selective antagonists such as ketanserin, sarpogrelate, cyproheptadine and ritanserin, and the results showed that AT-1015 has a high pKi value for the 5-HT2 receptor. The rank order of these antagonists are: ritanserin > ketanserin approximately equal to AT-1015 > cyproheptadine approximately equal to sarpogrelate. We also evaluated the dissociation ability (slow or rapid) of AT-1015 in the rabbit cerebral cortex membrane and compared it with other 5-HT2 antagonists using the radioligand binding assay method. The blockade of [3H]ketanserin binding sites in the rabbit cerebral cortex induced by ketanserin and sarpogrelate was readily reversed by washing, whereas the inhibition by AT-1015, cyproheptadine and ritanserin was not readily reversed by washing. The % of control after washing are 76.10% and 49.55% for AT-1015 at 10(-7.5) and 10(-7.0) M, 67.32% and 50.17% for cyproheptadine at 10(7.5) and 10(-7.0) M, and 72.38% and 39.80% for ritanserin at 10(-9.5) and 10(-9.0) M concentrations, respectively. Thus, these findings suggest that AT-1015 has antagonistic properties towards the 5-HT2 receptor and also shows that AT-1015 slowly dissociates from the 5-HT2 receptor, whereas, ketanserin and sarpogrelate dissociate rapidly from the 5-HT2 receptor, which do not correlate with their affinity.

The aim of the present study was to investigate the binding affinities and dissociation potencies of several 5-HT₂ antagonists in M₂ muscarinic receptor of rat heart membranes using [³H]QNB as a radioligand. The 5-HT₂ antagonists used in this study were sarpogrelate, ketanserin and cyproheptadine. The results showed that sarpogrelate and ketanserin had very weak binding affinities to M₂ muscarinic receptor, whereas cyproheptadine had higher binding affinity to this receptor than the muscarinic receptor antagonist, atropine. All of these three 5-HT₂ antagonists as well as muscarinic receptor antagonists (atropine and pirenzepine) were readily dissociated from M₂ muscarinic receptor in rat heart membranes after washing. Therefore, the findings of the present investigation suggest that the dissociation potencies of neither 5-HT₂ antagonists nor muscarinic antagonists used correlate with their binding affinities to M₂ muscarinic receptors in rat heart.

Microvascular complications are one of the key causes of mortality among type-2 diabetic patients. This study was sought to investigate the use of a novel machine learning approach for predicting these complications from patient demographic, clinical, and laboratory profiles only. A total of 96 Bangladeshi participants having type-2 diabetes were recruited during their routine hospital visits. All patient profiles were assessed by using a Chi-squared (2) test to statistically determine the most important markers in predicting four microvascular complications; namely cardiac autonomic neuropathy (CAN), diabetic peripheral neuropathy (DPN), diabetic nephropathy (NEP), and diabetic retinopathy (RET). A machine learning approach based on random forest (RF) and support vector machine (SVM) was then developed to ensure automated clinical testing for microvascular complication in diabetic patients. The highest prediction accuracies were obtained by RF using diastolic blood pressure, Albumin-Creatinine ratio, and gender for CAN testing (98.67%), Microalbuminuria, smoking history, and hemoglobin A1C for DPN testing (67.78%), Albumin-Creatinine ratio for NEP testing (100%), and hemoglobin A1C, Microalbuminuria, and smoking history for RET testing (84.38%). This study suggests machine learning as a promising automated tool for predicting microvascular complications in diabetic patients using their profiles, which could help prvent those patients from further microvascular complications leading to early death.

Objective: The aim of this study was to investigate the associations of makers from demographic, clinical, and laboratory profiles with microvascular complications in a cohort of type II diabetic population in Bangladesh. Methods: In this cross-sectional study 103 participants [47 Men and 56 Women; Age 40~70 years] having type II diabetes for more than 10 years were randomly recruited during their routine visits to a major Diabetic Hospital in Dhaka, Bangladesh. The associations of prevalence of microvascular complications [Cardiac Autonomic Neuropathy(CAN), Diabetic Peripheral Neuropathy(DPN), Diabetic Nephropathy(Nep), Diabetic Retinopathy(Ret)] with demographic, clinical, and laboratory profiles were assessed by multivariate logistic regression (p 1.0). Results: The prevalence rates of CAN, DPN, Ret and Nep were 68%, 43.69%, 6.8%, and 4.8% respectively. The overall prevalence of diabetic-associated microvascular complication is 94.36% in this cohort of diabetic patients. BMI (p=0.0330, OR=1.90) and HbA1c (p=0.0535, OR=3.08) were found to be the most significant risk factors in the development of all microvascular complications. However, HbA1c for CAN; HbA1c, Microalbuminuria and Urinary creatinine for DPN; years of Diabetes, Systolic blood pressure and albumin creatinine ratio for Nep, HbA1c and Microalbuminuria for Ret were found to be most significantly associated in this Diabetes patients’ cohort. Conclusion: The proportion of microvascular complications was found to be significantly high among patients with Type II diabetes mellitus in this cohort. Controlling HbA1c could help reduce all four types of complications. However, controlling microalbuminuria could prevent DPN and Ret. This emphasizes the need for screening and prevention program toward early, symptomless identification of type II diabetes microvascular complications.