Background/Objectives: Reliable skin-lesion AI requires evaluation beyond the development distribution. This study assessed whether a source-developed multi-class system preserves discrimination and reliability when transferred to an unseen smartphone-acquired domain. Methods: A source-only multimodal four-class classifier was developed using HAM10000 and Derm7pt and evaluated on PAD-UFES-20 without target-domain adaptation. Reliability was assessed using class-specific calibration, uncertainty-based error detection, class-conditional conformal prediction, selective classification, demographic subgroup auditing, controlled ablation, and an independent DDI out-of-distribution (OOD) and explainability (XAI) audit. Results: Across five prespecified seeds, macro-F1 decreased from 74.27 ± 1.36% on the source domain to 54.92 ± 2.60% on PAD-UFES-20. Calibration, conformal efficiency, and selective coverage also deteriorated externally, although macro-AUROC remained comparatively preserved. The independent DDI audit showed limited OOD separation, while explanation stability was interpreted only as descriptive evidence. Ablation analysis indicated that clinical metadata contributed importantly to external performance. Conclusions: Internally reproducible discrimination did not guarantee reliable external behavior. These findings support explicit external reliability auditing and specialist-supervised selective decision support before cross-device deployment.

Human-Centered Artificial Intelligence (HCAI) has emerged as a promising paradigm to increase transparency, usability, and trust in AI-driven Decision Support Systems (DSS). However, existing research lacks technically detailed accounts of how HCAI principles can be operationalized, implemented, and empirically validated in real decision environments. This study proposes a technically grounded HCAI-oriented DSS framework and presents a concrete prototype implemented in two high-stakes domains: clinical decision support and financial risk assessment. The architecture integrates interpretable machine learning models, SHAP-based explanations, structured user-feedback loops, and governance mechanisms aligned with the EU Trustworthy AI Guidelines. We trained and evaluated domain-specific models using publicly available medical and financial datasets, describing all data preprocessing, model selection, and hyperparameter settings to ensure reproducibility. An empirical study involving 30 domain experts (15 clinicians, 15 financial analysts) compared the HCAI-DSS with a functionally identical black-box DSS. Statistical analyses (paired t-tests with 95% confidence intervals and Cohen’s d) revealed that the HCAI-DSS significantly improved trust (d = 1.23), transparency and understanding (+1.76 mean difference), usability (SUS difference = +15.4), and decision accuracy (+10.2%), without a significant increase in decision time (p = 0.08). Qualitative feedback further demonstrated that explanations, control, and human-in-the-loop features increased confidence and reduced uncertainty. The results provide empirical evidence that HCAI principles tangibly enhance DSS effectiveness and user acceptance. The study contributes (1) a reproducible technical implementation, (2) a validated HCAI-DSS architecture, and (3) multi-domain evidence of improved decision quality. These findings support sustainable and trustworthy AI adoption across sectors and align with emerging regulatory frameworks such as the EU AI Act.

With the exponential rise in digital information, the need for an effective multi-document text summarization technique which can provide concise, informative, coherent and reduce redundant information is growing increasingly. The conventional extractive summarization methods are used separately to generate the sentences maximization or sentence ranking based on statistical methods, which is hard to get the accurate estimation about the importance of sentences and to set suitable weights for the features that determine it. This paper aims to overcome these drawbacks and introduces a hybrid Fuzzy–Whale Optimization Algorithm (F-WOA) model for extractive multi-document text summarization. The Whale Optimization Algorithm (WOA) is used to optimize the weights of the extracted features, and the Mamdani Fuzzy Inference System (MFIS) uses the weighted features to estimate the importance of each sentence. First, all the input documents are preprocessed, and eight linguistic and statistical features are extracted. Each candidate weight vector is evaluated by passing the weighted features through the MFIS and measuring the topic relevance, cohesion, and readability of the resulting summary. The best weights are then used by the MFIS to score the sentences, and the top-ranked non-redundant sentences form the final summary. The experiments were performed on the benchmark datasets DUC-2002, DUC-2004, DUC-2006, and DUC-2007 with the ROUGE-1, ROUGE-2, and ROUGE-L evaluation metrics. Experimental results achieved ROUGE-1, ROUGE-2, and ROUGE-L F-scores of up to 50.79, 25.60, and 31.75, respectively. Comparative analysis shows that the integration of fuzzy logic into WOA enhances the quality of the summaries compared to the WOA-only variant that scores sentence with a weighted sum of the features.