Andrzej Opaliński

Efficient management of medical diagnostic laboratories is critical for ensuring high-quality test results, optimal utilization of analytical resources, and continuity of services, particularly under conditions of increased and variable demand. This study addresses the problem of forecasting laboratory workload and supporting quality control processes using data-driven methods. A large-scale dataset comprising over 140 million laboratory tests performed on approximately 11 million patients was integrated into a unified analytical framework. Machine learning and time-series analysis methods were applied to model four key laboratory functions: prediction of the number of tests performed, estimation of reagent demand, detection of analyzer overloads, and assessment of the stability of measurement methods within quality control procedures. The proposed approach combines patient profiling, sequential pattern analysis, neural networks, and classical forecasting models such as ARIMA and exponential smoothing. The results demonstrate high predictive accuracy for both global test volumes and patient-based quality control indicators, with determination coefficients exceeding 90% for workload forecasting and classification accuracy above 98% for identifying unnecessary recalibrations. These findings indicate that the use of machine learning techniques enables effective optimization of laboratory operations by reducing reagent shortages, preventing analyzer overloads, and improving the efficiency of quality control processes. The presented methods support more reliable, cost-effective, and scalable management of modern diagnostic laboratories.

This manuscript presents a model of a system implementing individual stages of production for long steel products resulting from rolling. The system encompasses the order registration stage, followed by production planning based on information about the billet inventory status, then offers the possibility of scheduling orders for the melt shop in the form of melt sequences, manages technological knowledge regarding the principles of sequencing, and utilizes machine learning and optimization methods in melt sequencing. Subsequently, production according to the implemented plan is monitored using IoT and vision tracking systems for ladle tracking. During monitoring, predictions of energy demand and energy consumption in LMS processes are made concurrently, as well as predictions of metal overheating at the CST station. The system includes production optimization at two levels: optimization of the heat sequence and at the production level through the prediction of heating time. Optimization models and machine learning tools, including mainly neural networks, are utilized. The system described includes key components: optimization models for sequencing heats using Ant Colony Optimization (ACO) algorithms and neural network-based prediction models for power-on time. The manuscript mainly focuses on process modeling issues rather than implementation or deployment details. Machine learning models have significantly improved process efficiency and quality; the optimization of planning has reduced sequencing plan execution time; and power-on time prediction models estimate the main ladle heating time with 97% precision, enabling precise production control and reducing overheating. The system serves as an example of implementing the concept of a cyber–physical system.

The article presents an outline of the concept of a prototype system allowing for the optimization of inventory management in a diagnostic laboratory on the basis of patients results. The effectiveness of laboratory diagnostics depends largely on the appropriate management of resources and the quality of tests. A functional quality management system is an integral element of every diagnostic laboratory, ensuring reliability and appropriate work standards. This system includes maintaining correct and reliable analytical test results as well as the optimal use of the laboratory equipment’s processing capacity and the appropriate organization of the supply chain—both analytical material and reagents. It is extremely important to avoid situations in which tests cannot be performed due to a lack of reagents, the overloading of analyzers, or improper calibration. Therefore, the accurate prediction of the number of orders is crucial to optimize the laboratory’s operations, both in the short term—for the next few hours and minutes—and in the longer term, even monthly, which will allow for the appropriate planning of reagent stock. As part of the research presented in this article, machine learning methods were used to implement the above functionalities, which allowed for the development of a prototype of a laboratory optimization system using patient test results as a basis.

The article presents the potential for using artificial neural networks to support decisions related to the rebonding of green moulding sand. The basic properties of the moulding sand tested in foundries are discussed, especially compactibility as it gives the most information about the quality of green moulding sand. First, the data that can predict the compactibility value without the need for testing are defined. Next, a method for constructing an artificial neural network is presented and the network model which produced the best results is analysed. Additionally, two applications were designed to allow the investigation results to be searchable by determining the range of values of the moulding sand parameters.

Background and Objectives: Poor sleep quality in patients with obstructive sleep apnea (OSA) may be associated with different clinical and polysomnographic features. The aim of this study was to identify features associated with poor sleep quality in OSA patients. Materials and Methods: This was a cross-sectional study enrolling patients with OSA confirmed by polysomnography (PSG). In addition to gathering clinical data, patients were assessed using the Pittsburgh Sleep Quality Index (PSQI), the Epworth Sleepiness Scale (ESS), and the Clinical Global Impression Scale. Univariate and multivariable analyses were performed to identify factors associated with an increased risk of poor sleep quality in this population. Results: Among 505 enrolled patients (mean age of 57.1 years, 69.7% male) poor quality of sleep (PSQI score ≥ 5) was confirmed in 68.9% of them. Multivariable analysis revealed the following factors associated with poor sleep quality: chronic heart failure (OR 3.111; 95% CI, 1.083–8.941, p = 0.035), male sex (OR 0.396; 95% CI, 0.199–0.787, p = 0.008), total ESS score (OR 1.193; 95% CI, 1.124–1.266, p < 0.001), minimal saturation during sleep (OR 1.034; 95% CI, 1.002–1.066, p = 0.036), and N3 percentage of total sleep time (OR 1.110; 95% CI, 1.027–1.200, p = 0.009). Conclusions: Our study suggests that both the female sex and coexistence of heart failure are independent risk factors for poor sleep quality. Moreover, we hypothesize that nocturnal hypoxia may lead to a misperception of sleep quality and may explain the counterintuitive association between a higher proportion of deep sleep and poor sleep quality.

The presented article concerns the issue of supporting the ADI cast iron product manufacturing process and presents an IT system dedicated mainly to designers and technologists. Designers can be supported at the stage of selecting types of materials and technologies (including ADI cast iron) to produce products with required properties. Technologists can obtain support in determining the parameters (temperature and chemical) of the ADI cast iron manufacturing process in order to obtain products with specific properties. The system also contains an information resources (standards, documentation, examples) concerning ADI cast iron and products made of it. Examples of use by individual system users are presented as a case study.

The paper presents the system for the integration of heterogeneous data sources in the domain of Obstructive Sleep Apnea. The main goal of the system is to facilitate patient diagnose and treatment process by integration of the results of performed medical examinations and analyzes. Data source contains: clinical interviews, physical examinations, lab tests, and the data collected from the devices used to monitor patient's sleep parameters (PSG, CPAP). This article describes the concept of the system, its main functionalities, IT architecture and technology and some details of its implementation. Also the data sources and the methods of data acquisition from medical devices integrated with the system are characterized. In addition, basic methods of analyzing data gathered in the system are presented, which in the future can be developed towards automatic mechanisms supporting the process of diagnosis and treatment of patients in this domain.