In modern medicine, laboratory tests play an important role in the diagnosis, treatment and monitoring of patients. However, the volume and complexity of the data obtained can create challenges for interpreting the results. In this paper, we present a study on the application of integrated automation of a medical laboratory using OpenAI for a more accurate and effective interpretation of laboratory results. Interpreting laboratory results through integrated automation using artificial intelligence (AI) and other digital technologies automatically analyzes and interprets laboratory results. This approach aims to streamline the process of interpreting laboratory results and provide more accurate, consistent and timely results to healthcare providers. Comprehensive automation of the interpretation of laboratory results can improve the efficiency and accuracy of laboratory results, leading to improved patient outcomes and better clinical decision-making. However, it is essential to note that AI models are imperfect and can still make mistakes. Therefore, healthcare professionals should always review automated interpretation results before diagnosing or treating. The work presented results in applying OpenAI to interpret laboratory results in the laboratory information system smartLAB Kazakhstan, which provides a complete cycle of automation of all medical laboratory processes. In the course of the study, an automated information system of a medical research complex using artificial intelligence was developed and implemented

This paper explores the feasibility of early-season crop classification based on Sentinel-2-time series using the TimeSen2Crop dataset (≈1 million pixels, 16 crops). The aim of the study was to evaluate the spectral-phenological separability of crops during the season and compare the performance of classical tabular algorithms, deep sequence models, and a seasonally oriented hybrid stacking scheme. Based on multispectral observations, a feature set was formed from 9 optical channels and 13 vegetation indices for 30 dates. F-criteria were calculated, confirming a sharp increase in interclass separability during the active vegetative growth phase and substantiating three time series truncation scenarios (early, early + mid-season, and full season). Random Forest (macro-F1: 0.46/0.74/0.75) was used as the base tabular model. LSTM, BiLSTM, GRU, 1D-CNN, and Transformer were trained in parallel, with Transformer showing the best results among the deep architectures (0.42/0.68/0.78). The main contribution of the work is a hybrid multi-layer stacking scheme combining heterogeneous base algorithms and OOF meta-features, which provides the highest quality (0.51/0.83/0.86) in all scenarios. The obtained results confirm the effectiveness of phenology-oriented selection of time windows, informative indices, and hybrid ensemble learning for improving the accuracy of early-season crop monitoring.

This article describes the practical using of QR codes [1] verification of laboratory studies results. QR codes have become widely used in all industries as quick identification of information and the implementation of transactional actions, where encrypted URL allows to quickly scanning by using a smartphone camera. Digitalization contributes to the transition to the online environment of healthcare, office workers, education and to receive more data on the spread of diseases, exchange information and quickly receive laboratory results without distortion. The presented solution is a component of the LIS SmartLAB platform [2], which performs complex automation of laboratories of the different profiles, observing all work processes to obtain reliable results by direct interaction with laboratory equipment according to international standards HL7 (Health Level 7 - "Seventh level"), ASTM (American Society for Testing and Materials - "American Society for Testing Materials") and automatic detection of deviations from standard values [3]. In 2019, there was a pilot implementation of QR verification of results based on the laboratory of the Skin and venereal dispensary of the Almaty, the results of which made it possible to introduce QR codes into other profiles of laboratory diagnostics, such as PCR (polymerase chain reaction), genetics, microbiology and clinical diagnostics. Now, due to the pandemic, all laboratory results for the detection of RNA of the COVID-19 virus must contain a QR code to avoid falsification of the results.

This study presents NORIA, an availability-aware multitask learning framework for clinical prediction from incomplete electronic health records (EHRs). We analyzed a public dataset of 77,724 patients and 107 numerical features. To prevent temporal leakage, predictors were grouped by availability, and training-only feature selection identified three baseline and two first-year variables. NORIA jointly predicts baseline and updated glycemic control, an HbA1c change index, and 21 medication labels using shared representations, masked training, and stage-specific prediction updates. Comparators included classical machine learning, gradient boosting, deep tabular models, and multitask architectures (MMoE and PLE). On the internal test set, NORIA achieved AUROCs of 0.8554 and 0.8888 for baseline and updated glycemic control, respectively, and medication macro-AP of 0.1854 versus 0.1879 for CatBoost. The predefined medication improvement criterion was not met. With 20% of baseline features artificially masked, updated-control AUROC declined by 0.0271 for NORIA, versus 0.0510 for CatBoost and 0.0542 for FT-Transformer. Ablation analyses indicated that masked training provided the clearest robustness benefit. NORIA thus demonstrated competitive accuracy and robustness in selected simulated missing-data scenarios, without establishing overall superiority.