Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 109 for “"balanced accuracy"”.

  1. Machine Learning Approaches for Cognitive Disorder Detection using Administrative Health Data

    … outcomes. Performance was assessed using balanced accuracy, using bootstrapping to compute confidence intervals. Permutation feature importance was used to identify key predictors. Results: ML models achieved reasonable performance differentiating NCD from dementia with a balanced accuracy …

    calgary Repository record for Machine Learning Approaches for Cognitive Disorder Detection using Administrative Health Data (opens in a new tab)

  2. On the applicability and utility of machine learning in the field of neuropsychology

    … between Alzheimer’s Dementia (DAT) and DEP (Balanced accuracy of 87 %) as well as for the discrimination between DEP and DEM (Balanced accuracy of 80.8%) were high across all algorithms and test batteries used, suggesting that ML algorithms in combination with comprehensive neuropsychological …

    lmu-germany Repository record for On the applicability and utility of machine learning in the field of neuropsychology (opens in a new tab)

  3. Μελέτη της κλινικής έκβασης χειρουργημένων ασθενών με εφαρμογή αλγορίθμων Μηχανικής Μάθησης

    … όπως η Σταθμισμένη Ισορροπημένη Ακρίβεια (Balanced Accuracy Weighted), η ευαισθησία (recall), η ακρίβεια (precision), το F1-score και ο συντελεστής Cohen’s kappa, λαμβάνοντας υπόψιν το πρόβλημα της ανισορροπίας κλάσεων που χαρακτήριζε τα κλινικά δεδομένα. Επιπλέον, διερευνήθηκε η επίδραση …

    athens Repository record for Μελέτη της κλινικής έκβασης χειρουργημένων ασθενών με εφαρμογή αλγορίθμων Μηχανικής Μάθησης (opens in a new tab)

  4. Using Explainability to Improve Predictive Modeling Performance

    … SEPM demonstrates up to a 7% increase in balanced accuracy and a 13% improvement in F1 score compared with conventional models trained on the full dataset. LSSW complements SEPM by retaining the entire dataset, yet reweighting observations according to latent structures captured by their …

    ku Repository record for Using Explainability to Improve Predictive Modeling Performance (opens in a new tab)

  5. Deep learning framework for classification of neuroendocrine neoplasm whole slide images

    … The H&E portion of the framework achieved a balanced accuracy of 72.1% across 6-folds for three-class classification (G1, G2, G3). We demonstrated that the survival outcomes for computer assigned grades are comparable to those based on pathologist assessment, with c-index values of 0.63 and …

    ubc Repository record for Deep learning framework for classification of neuroendocrine neoplasm whole slide images (opens in a new tab) Download PDF for Deep learning framework for classification of neuroendocrine neoplasm whole slide images (opens in a new tab)

  6. Multi-modal Multi-Level Neuroimaging Fusion with Modality-Aware Mask-Guided Attention and Deep Canonical Correlation Analysis to Improve Dementia Risk Prediction

    … proposed MRI+PET (MAMGA+DCCA) model achieves a balanced accuracy of 0.998 and an AUC-ROC of 0.999 in distinguishing stable normal cognition (sNC) from stable Alzheimer's Disease (sDAT). For the more challenging task of separating stable and progressive MCI (sMCI vs. pMCI), the best-performing …

    vt Repository record for Multi-modal Multi-Level Neuroimaging Fusion with Modality-Aware Mask-Guided Attention and Deep Canonical Correlation Analysis to Improve Dementia Risk Prediction (opens in a new tab)

  7. Non-Visual Human Eye Gaze Tracking Using Radar and Artificial Intelligence for Robust Driver Monitoring Systems

    … dataset show that the model achieves 85.7% balanced accuracy for four-direction classification with azimuth and elevation errors of 7.82◦ and 3.15◦. Under strict cross-session evaluation, few-shot calibration with three to five labelled events per direction yields 82.1% balanced accuracy, …

    chalmers Repository record for Non-Visual Human Eye Gaze Tracking Using Radar and Artificial Intelligence for Robust Driver Monitoring Systems (opens in a new tab)

  8. Quantitative Nuclear Grading to Increase Reliability and Consistency in Bladder Cancer Diagnoses: Model Construction and Validation

    … differentiate between the two grades with > 80% balanced accuracy. In contrast, there were large discrepancies in mitotic index and shape-related features between cohorts which may be a result of technical errors or sampling differences. We used the first cohort to train a variety of …

    queens Repository record for Quantitative Nuclear Grading to Increase Reliability and Consistency in Bladder Cancer Diagnoses: Model Construction and Validation (opens in a new tab)

  9. Integrating environmental conditions into machine learning models for predicting bridge maintenance deterioration

    … the most consistent top performance, achieving balanced accuracies between 0.972 and 0.978 and Matthews Correlation Coefficient (MCC) values around 0.97 across all bridge components. DTs achieved the single highest metric value for decks (balanced accuracy = 0.9875). The addition of climatic …

    colostate Repository record for Integrating environmental conditions into machine learning models for predicting bridge maintenance deterioration (opens in a new tab)

  10. Διαγνωστικά μοντέλα γεροντικής κατάθλιψης βασισμένα στην απεικόνιση της λευκής ουσίας του εγκεφάλου με μαγνητικό συντονισμό

    … was evaluated using appropriate measures of accuracy and sensitivity, the F1 score, and the Area Under the Receiving Operative Curve (ROC-AUC). The statistical significance of the classifier was tested using standard permutation testing with cross validation. The classifier achieved a …

    greece Repository record for Διαγνωστικά μοντέλα γεροντικής κατάθλιψης βασισμένα στην απεικόνιση της λευκής ουσίας του εγκεφάλου με μαγνητικό συντονισμό (opens in a new tab)

  11. ON-FARM UTILIZATION OF PRECISION DAIRY MONITORING: USEFULNESS, ACCURACY, AND AFFORDABILITY

    … A secondary objective was calculating the accuracy of technology-generated disease alerts compared against observed disease events. A final objective was determining the economic viability of investing in a precision dairy monitoring technology for detecting estrus and diseases. A year-long …

    uky-thes Repository record for ON-FARM UTILIZATION OF PRECISION DAIRY MONITORING: USEFULNESS, ACCURACY, AND AFFORDABILITY (opens in a new tab)

  12. Towards reliable machine learning for ultrasound screening of aortic stenosis

    … from observer variability, yielding improved accuracy on two datasets. To mitigate bias against underrepresented cases, the model also undergoes additional training with deep feature reweighting to improve fairness across patient subgroups. We achieved balanced accuracy scores of 93.0% on a …

    ubc Repository record for Towards reliable machine learning for ultrasound screening of aortic stenosis (opens in a new tab) Download PDF for Towards reliable machine learning for ultrasound screening of aortic stenosis (opens in a new tab)

  13. Erstellung und Evaluation eines Raman-spektroskopischen Messkopfs zur Analyse von Hauttumoren und Auswertung von klinischen Studiendaten

    … normalen pigmentierten Naevi (PN) erzielte eine Balanced Accuracy (Mittelwert von Sensitivität und Spezifität) von 91%. Die Diskriminierung von BCC bzw. SCC zu normaler unpigmentierter Haut (nor) ergab eine Balanced Accuracy von 73% bzw. 85%. Diese Ergebnisse liegen in der Größenordnung des …

    fu-berlin Repository record for Erstellung und Evaluation eines Raman-spektroskopischen Messkopfs zur Analyse von Hauttumoren und Auswertung von klinischen Studiendaten (opens in a new tab)

  14. AI Analysis of Voice to Aid Laryngeal Cancer Diagnosis

    … upon previously published methods, achieving a balanced accuracy of 73.7%, sensitivity of 72.0%, and specificity of 75.4% using audio features only. Integrating demographic and symptom features improved these methods, achieving a balanced accuracy of 83.7%, sensitivity of 84.0%, and specificity …

    whiterose Download PDF for AI Analysis of Voice to Aid Laryngeal Cancer Diagnosis (opens in a new tab)

  15. Identifikace zvěře pomocí umělé inteligence

    … 95,8 %, zatímco při prahu maximalizujícím balanced accuracy činila tato metrika 88,1 %. Výsledky zároveň potvrdily schopnost modelu generalizovat na nové, dosud neviděné jedince, aniž by bylo nutné jej přeučovat.

    brno-tech Repository record for Identifikace zvěře pomocí umělé inteligence (opens in a new tab)

  16. The potential role of optical guidance for bone-related biomedical applications in orthopedics and neurosurgery

    … from each FS framework yielding promising balanced accuracy scores for the one-vs-rest binary classification task. For cortical bone versus the rest class labels, PCA, LDA, biPLS and ensemble -based FS framework computed balanced accuracy scores of 94.8 ± 3.47%, 98.2 ± 2.02%, 95.8 ± 3.04% …

    cork Repository record for The potential role of optical guidance for bone-related biomedical applications in orthopedics and neurosurgery (opens in a new tab)

  17. Using neural language models to predict the psychosocial needs of cancer patients

    … whether patients will see a psychiatrist with balanced accuracy and receiver-operator-area-under-curve (AUC) above 0.70. This is a similar performance to comparable prior work predicting mental health outcomes. We also predicted seeing a counsellor with AUC above 0.70, but predicting …

    ubc Repository record for Using neural language models to predict the psychosocial needs of cancer patients (opens in a new tab) Download PDF for Using neural language models to predict the psychosocial needs of cancer patients (opens in a new tab)

  18. Using Natural Language Processing to Detect Breast Cancer Recurrence in Clinical Notes: A Hierarchical Machine Learning Approach

    … was the best performing model which achieved a balanced accuracy of 0.924, with sensitivity of 0.867, specificity of 0.981, precision of 0.886 and ROC of 0.924. In addition, more data was collected from the years 2008 to 2012 in a similar cohort. This dataset was used to validate the performance …

    waterloo Repository record for Using Natural Language Processing to Detect Breast Cancer Recurrence in Clinical Notes: A Hierarchical Machine Learning Approach (opens in a new tab)

  19. Gaia žvaigždžių spiečių erdvinės struktūros analizė ir modeliavimas naudojant statistinius ir mašininio mokymosi metodus /

    … using a random forest classifier (up to 80.3% balanced accuracy). The model is then applied to distant clusters (0.22--3.3 kpc), and their structures are corrected using a Z-axis correction. The results show that machine learning can be applied to the analysis of cluster structures, however, …

    vilnius Repository record for Gaia žvaigždžių spiečių erdvinės struktūros analizė ir modeliavimas naudojant statistinius ir mašininio mokymosi metodus / (opens in a new tab)

  20. Bias Correction, Sample Size Estimation and Modeling for Swine Body Weight and Productivity Data

    … parity. The best classifier achieved 65% balanced accuracy without including BW and backfat thickness (BFT) data – variables that, when added, could further improve the predictive performance of the classifier. These results highlight the potential for BW and productivity models to boost …

    guelph Repository record for Bias Correction, Sample Size Estimation and Modeling for Swine Body Weight and Productivity Data (opens in a new tab)

Page 1 of 6