Development of a machine learning-based model for the prediction and progression of diabetic kidney disease: A single centred retrospective study.

BACKGROUND: Diabetic kidney disease (DKD) is a diabetic microvascular complication often characterized by an unpredictable progression. Hence, early detection and recognition of patients vulnerable to progression is crucial. OBJECTIVE: To develop a prediction model to identify the stages of DKD and the factors contributing to progression to each stage using machine learning. METHODOLOGY: A retrospective study was conducted in a South Indian tertiary care hospital and collected the details of patients diagnosed with DKD from January 2017 to January 2022. Bayesian optimization-based machine learning techniques such as classification and regression were employed. The model was developed with the help of an optimization framework that effectively balances classification, prediction accuracy, and explainability. RESULTS: Of the 311 patients diagnosed with DKD, 227 were selected for the study. A system for predicting DKD has been created for a patient dataset utilizing a variety of machine-learning approaches. The eXtreme gradient (XG) Boost method excelled, achieving 88.75% accuracy, 88.57% precision, 91.4% sensitivity,100% specificity, and 89.49% F1-score. An interpretable data-driven method highlights significant features for early DKD diagnosis. The best explainable prediction model uses the XG Boost classifier, revealing serum uric acid, urea, phosphorous, red blood cells, calcium, and absolute eosinophil count as the major predictors influencing the progression of DKD. In the case of regression models, the gradient boost regressor performed the best, with an R2 score of 0.97. CONCLUSION: Machine learning algorithms can effectively predict the stages of DKD and thus help physicians in providing patients with personalized care at the right time.

White Light Emissive Eu(III) Complexes through Ligand Engineering and their Applications in Cool Near Ultraviolet White Light Emitting Diodes and Thermometer.

In pursuit of enhancing white light quality for solid-state lighting (SSL) applications, an attempt has been made to design novel imidazo-bipyridyl ligands as an ancillary ligand to obtain multiple emissions (mimic sunlight) in the Eu-complex. By strategically modifying the phenanthroline core with imidazo-bipyridyl incorporation with 1 or 2-Napthyl groups at the C1 position, the excitation spectral line is successfully shifted from Ultraviolet (UV) to near UV/visible spectrum (where the LED emission occurs). The ligands showed greenish blue emission in solid and solution. Density Functional Theory (DFT) calculations were utilized to understand the energy transfer processes from ligand to Eu ion in the Eu complexes. The analysis revealed that the energy transfer is incomplete, primarily attributed to the proximity of triplet state energy levels to the resonance level of Eu(III) ions as reflected in solvatochromism. These complexes exhibit a unique dual emissive behavior (emitting multi-color) including white light across various solvents. These complexes hold great promise as single-component white light-emissive materials, with potential applications in white light-emitting diodes (WLED). The fabricated white LED showed an excellent color rendering index (CRI ~93 %). Beyond lighting, this distinctive property opens avenues for temperature sensing ([Eu(DBM)31-Naph] shows the highest sensitivity of Sr=10.97 %, and [Eu(DBM)32-Naph] shows the highest sensitivity of Sr=5.5 % at 333 K) and vapoluminescent (acid-base on-off-on luminescence) studies. This research pioneers the development of these complexes as potential single-component materials for superior white LEDs, underlining their multifaceted utility in cutting-edge lighting and sensing technologies.