1. Using generative AI to improve the performance and interpretability of rule-based diagnosis of Type 2 diabetes mellitusLeon Kopitar, Iztok Fister, Gregor Štiglic, 2024, original scientific article Abstract: Introduction: Type 2 diabetes mellitus is a major global health concern, but interpreting machine learning models for diagnosis remains challenging. This study investigates combining association rule mining with advanced natural language processing to improve both diagnostic accuracy and interpretability. This novel approach has not been explored before in using pretrained transformers for diabetes classification on tabular data. Methods: The study used the Pima Indians Diabetes dataset to investigate Type 2 diabetes mellitus. Python and Jupyter Notebook were employed for analysis, with the NiaARM framework for association rule mining. LightGBM and the dalex package were used for performance comparison and feature importance analysis, respectively. SHAP was used for local interpretability. OpenAI GPT version 3.5 was utilized for outcome prediction and interpretation. The source code is available on GitHub. Results: NiaARM generated 350 rules to predict diabetes. LightGBM performed better than the GPT-based model. A comparison of GPT and NiaARM rules showed disparities, prompting a similarity score analysis. LightGBM’s decision making leaned heavily on glucose, age, and BMI, as highlighted in feature importance rankings. Beeswarm plots demonstrated how feature values correlate with their influence on diagnosis outcomes. Discussion: Combining association rule mining with GPT for Type 2 diabetes mellitus classification yields limited effectiveness. Enhancements like preprocessing and hyperparameter tuning are required. Interpretation challenges and GPT’s dependency on provided rules indicate the necessity for prompt engineering and similarity score methods. Variations in feature importance rankings underscore the complexity of T2DM. Concerns regarding GPT’s reliability emphasize the importance of iterative approaches for improving prediction accuracy.
Keywords: GPT, association rule mining, classification, interpretability, diagnostics Published in DKUM: 26.11.2024; Views: 0; Downloads: 6
Full text (1,29 MB) This document has many files! More... |
2. Urinary metabolic biomarker profiling for cancer diagnosis by terahertz spectroscopy : review and perspectiveAndreja Abina, Tjaša Korošec, Uroš Puc, Mojca Jazbinšek, Aleksander Zidanšek, 2023, review article Abstract: In the last decade, terahertz (THz) technologies have been introduced to the detection, identification, and quantification of biomolecules in various biological samples. This review focuses on substances that represent important biomarkers in the urine associated with various cancers and their treatments. From a diagnostic point of view, urine liquid biopsy is particularly important because it allows the non-invasive and rapid collection of large volumes of samples. In this review, the THz spectral responses of substances considered metabolic biomarkers in urine and obtained in previous studies are collected. In addition, the findings from the relatively small number of prior studies that have already been carried out on urine samples are summarised. In this context, we also present the different THz methods used for urine analysis. Finally, a brief discussion is given, presenting perspectives for future research in this field, interpreted based on the results of previous studies. This work provides important information on the further application of THz techniques in biomedicine for detecting and monitoring urinary biomarkers for various diseases, including cancer. Keywords: terahertz spectroscopy, urinary biomarkers, metabolic biomarkers, cancer diagnostics, biomolecules, non-invasive detection, biomedical detection Published in DKUM: 14.03.2024; Views: 212; Downloads: 32
Full text (12,51 MB) This document has many files! More... |
3. |
4. |
5. Evaluation of the influence of the macro-environment on the social innovation activity of enterprisesLiliya Satalkina, Nestor Shpak, 2018, original scientific article Abstract: Background: Nowadays the emphasis on social components in the general mainstream of innovation activity is one of the strongest grounds for the successful functioning and development of enterprises. In several countries, social innovation activity is becoming a product of business in general, with associated expectations regarding profit.
Objectives: The goal of the article is to develop a toolkit for the evaluation of the influence of the macro-environment on the social innovation activity (SIA) of enterprises.
Method: The methodology includes elements of theoretical and empirical research with the implementation of methods such as a literature review, all types of analysis, and methods of aggregation and integration. Questionnaires were used as a means of data collection.
Results: The general methodological framework of diagnostics of the SIA macro-environment is distinguished. Based on a theoretical analysis of the SIA ecosystem and the experience of operating enterprises, the main factors of SIA macro-environment are determined. The general integrated index and its five-level interpretational model are proposed as a measure for the evaluation of the SIA macro-environment.
Conclusion: The results presented provide data necessary for the argumentation of SIA strategy and tactics, as well as investment policy in this sphere. Keywords: enterprise, social innovation activity, diagnostics, macro-environment, factors Published in DKUM: 07.05.2018; Views: 1517; Downloads: 338
Full text (1,18 MB) This document has many files! More... |
6. Automated diagnostics of damage to an aluminum alloy under the conditions of high-cycle fatigueP. O. Maruščak, Igor Konovalenko, Mykhailo Karuskevich, Vladimir Gliha, Tomaž Vuherer, 2013, original scientific article Abstract: An identification and quantitative analysis of the deformation relief of the aluminium alloy for an aircraft construction based on a digital-image processing has been performed. The behaviour of defects has been assessed on the basis of diagnostics results for individual stages of the deformation process. It has been established that the individual stages of the damage-accumulation process are characterised by the values of integral-image parameters. Based on the consecutive processing of the data on the surface cyclic deformation, the main regularities of the propagation of defects have been found. Theoretical preconditions have been substantiated and experimental results obtained. Keywords: fatigue, surface, digital image, diagnostics, accumulated damage, defect propagation, evaluation Published in DKUM: 10.07.2015; Views: 1503; Downloads: 111
Full text (414,57 KB) This document has many files! More... |
7. |
8. Using of acoustic models in mechanical diagnosticsMateja Ploj Virtič, Boris Aberšek, Uroš Župerl, 2008, original scientific article Abstract: This paper presents an acoustical model for control and diagnostics of single stage gear wheels. The model is based on various methods and procedures that as a result provide information about the generatorćs condition, the gear in particular. The acoustical model is part of a complex system that units' different models to meet diagnostics of single stage gear wheels as precise as possible. Using the adaptive FIR filter, acoustical model enables the calculation of impulse response for different notch lengths between 0 and ac. The acoustical model consists of digital FIR filter, modified by LMS algorithm, used to calculate impulse responses in non-linear systems, the model for the calculation of any impulse response and the frequency analysis with the use of FFT for the simulation of frequency spectrums. Frequency spectrum of the simulated sound signal enables an analysis of the error that can be used for calculating the remaining service life and/or determining the control cycle of maintenance. Keywords: mechanical fault diagnostics, acoustic models, impulse response, adaptive algorithm Published in DKUM: 31.05.2012; Views: 1747; Downloads: 47
Link to full text |
9. Crack identification in gear tooth root using adaptive analysisAleš Belšak, Jože Flašker, 2007, original scientific article Abstract: Problems concerning gear unit operation can result from various typical damages and faults. A crack in the tooth root, which often leads to failure in gear unit operation, is the most undesirable damage caused to gear units. This article deals with fault analyses of gear units with real damages. A laboratory test plant has been prepared. It has been possible to identify certain damages by monitoring vibrations. In concern to a fatigue crack in the tooth root significant changes in tooth stiffness are more expressed. When other faults are present, other dynamic parameters prevail. Signal analysis has been performed also in concern to a non-stationary signal, using the adaptive transformation to signal analysis. Keywords: machine elements, gears, fatigue crack, fault detection, vibrations, adaptive signal analysis, engineering diagnostics Published in DKUM: 31.05.2012; Views: 2206; Downloads: 81
Link to full text |