In natural language processing, short-text semantic similarity (STSS) is a very prominent field. It has a significant impact on a broad range of applications, such as question–answering systems, information retrieval, entity recognition, text analytics, sentiment classification, and so on. Despite their widespread use, many traditional machine learning techniques are incapable of identifying the semantics of short text. Traditional methods are based on ontologies, knowledge graphs, and corpus-based methods. The performance of these methods is influenced by the manually defined rules. Applying such measures is still difficult, since it poses various semantic challenges. In the existing literature, the most recent advances in short-text semantic similarity (STSS) research are not included. This study presents the systematic literature review (SLR) with the aim to (i) explain short sentence barriers in semantic similarity, (ii) identify the most appropriate standard deep learning techniques for the semantics of a short text, (iii) classify the language models that produce high-level contextual semantic information, (iv) determine appropriate datasets that are only intended for short text, and (v) highlight research challenges and proposed future improvements. To the best of our knowledge, we have provided an in-depth, comprehensive, and systematic review of short text semantic similarity trends, which will assist the researchers to reuse and enhance the semantic information.

Keyword extraction is a critical task that enables various applications, including text classification, sentiment analysis, and information retrieval. However, the lack of a suitable dataset for semantic analysis of keyword extraction remains a serious problem that hinders progress in this field. Although some datasets exist for this task, they may not be representative, diverse, or of high quality, leading to suboptimal performance, inaccurate results, and reduced efficiency. To address this issue, we conducted a study to identify a suitable dataset for keyword extraction based on three key factors: dataset structure, complexity, and quality. The structure of a dataset should contain real-time data that is easily accessible and readable. The complexity should also reflect the diversity of sentences and their distribution in real-world scenarios. Finally, the quality of the dataset is a crucial factor in selecting a suitable dataset for keyword extraction. The quality depends on its accuracy, consistency, and completeness. The dataset should be annotated with high-quality labels that accurately reflect the keywords in the text. It should also be complete, with enough examples to accurately evaluate the performance of keyword extraction algorithms. Consistency in annotations is also essential, ensuring that the dataset is reliable and useful for further research.

Entity-aware quality assessment may reduce false interpretations of electronic health record (EHR) data, but evidence from small, rule-aligned benchmarks cannot establish operational effectiveness. We revised H-StreamQ as a proof-of-concept framework and evaluated its laboratory component using the complete MIMIC-IV v3.1 labevents file (158,374,764 events; 313,442 patients). Ten thousand patients were sampled across laboratory-activity quintiles and split at patient level into training (6000), threshold-calibration (2000), and test (2000) groups. The independent test set contained 918,651 numeric laboratory events. Without excluding naturally alerted records, 54,788 mutually exclusive defects were introduced using subtle value shifts, unit/scale errors, mapping errors, delayed records, and patient-clustered correlated defects. Rules, a context-aware Isolation Forest, their union (Hybrid), a context-free Isolation Forest, Local Outlier Factor (LOF), and linear and radial-basis-function (RBF) One-Class support vector machines (OCSVMs) were compared at a threshold fixed by a 2.5% calibration alert budget. Patient-cluster bootstrap intervals and event-micro and patient-macro results were reported. Rules alone achieved the highest event-micro F1-score (0.637; 95% confidence interval [CI] 0.547–0.722), followed by Hybrid (0.576; 0.484–0.668) and RBF One-Class SVM (0.559; 0.433–0.670). Hybrid increased recall over rules by only 0.004 (95% CI 0.003–0.006) while reducing F1 by 0.061 and increasing the background-alert rate by 0.015. Context conditioning did not improve aggregate Isolation Forest performance. In six batch-level drift simulations, an exponentially weighted moving average (EWMA) and a fixed-window monitor detected 97–100% and 98–100% of changes, respectively, whereas a custom Hoeffding adaptive-window detector was more conservative and often missed smaller or recurrent changes. These results support H-StreamQ as an explainable research framework, not as a validated clinical or production system. Patient-macro F1, which weights every patient equally, was substantially lower than event-micro F1 for every method (rules 0.395 versus 0.637; Hybrid 0.320 versus 0.576), indicating that event-level performance is weighted towards high-activity patients. Precision and F1 are computed relative to injected synthetic labels and are not clinically adjudicated estimates. The entity-aware architecture spans patients, admissions, diagnoses, transfers, and dictionaries, but the quantitative detection benchmark evaluates the numeric laboratory component only; other entities are used for linkage and contextual attachment and are audited descriptively rather than evaluated against labels.

Semantic answer caching reduces inference cost by reusing previous responses but may repeatedly serve incorrect answers. Prior research primarily addresses cache matching, verification, and freshness, whereas this study investigates an error-attribution problem: grouping multiple request surfaces under shared source keys can concentrate incorrect answer exposure without proportionally increasing the total number of errors. We evaluated 500 category-balanced MMLU-Pro questions, six instruction-and-format variants, and two instruction-tuned models using fixed multiple-choice predictions. On 400 TEST questions, pairwise answer disagreement was 27.12% for Qwen2.5-3B and 26.90% for Mistral-7B. At a DEV-selected threshold of 0.96, TEST same-question matching achieved 98.59% precision and 99.97% recall. Semantic caching avoided 91.69–92.31% of modeled inference-token cost. Under Zipf demand, mean maximum cumulative wrong reuse per source key rose from 146.8 to 783.2 for Qwen and from 153.3 to 820.1 for Mistral. These approximately fivefold increases partly reflect different cache-key granularities: at the underlying-question level, maxima were 726.0 versus 783.2 and 745.8 versus 820.1, respectively. Net additional wrong labels relative to fresh computation were only 22.1 and 37.55 per 4800 requests. Exposure-aware refresh did not consistently improve accuracy or control-concentrated errors. Reliable cache evaluation should jointly consider correctness, computational cost, error exposure, and aggregation level.

Background/Objectives: Acute kidney injury (AKI) is common in critical care, yet predictive artificial intelligence studies often differ in outcome definitions, validation, calibration, and interpretability. We developed and internally validated machine learning models for newly observed serum-creatinine-defined AKI after a fixed 24 h ICU landmark and then audited how stable the selected model was to clinically important observation and timing choices. Methods: Using MIMIC-IV v3.1, we retained one first ICU stay per adult patient, required adequate pre-landmark creatinine observation, excluded coded end-stage kidney disease, documented dialysis before the landmark, and observed AKI by the landmark. The outcome was a new creatinine rise within the next 48 h using KDIGO-aligned creatinine change thresholds, with follow-up truncated at ICU exit, hospital discharge, or death. The ascertainable cohort (n = 15,231) was split 60%/15%/10%/15% into training, calibration, validation, and test sets. Logistic regression, random forests, and histogram gradient boosting were calibrated with a separate calibration set; thresholds were fixed on validation data to target at least 80% sensitivity. The test set was evaluated once. A later post hoc audit reused frozen test risks without retraining. Results: Histogram gradient boosting was selected by validation average precision. In 2286 test patients (664 events; 29.0%), AUROC was 0.726 (95% CI, 0.701–0.749), average precision 0.523 (0.478–0.565), and Brier score 0.179 (0.171–0.187). At the fixed threshold, sensitivity was 78.5%, specificity 52.2%, positive predictive value 40.2%, and false alerts 33.9 per 100 patients. Mean predicted risk was 0.290 versus an observed event fraction of 0.290; calibration intercept and slope were 0.023 and 1.022. The AUROC difference versus full logistic regression was +0.0197 (95% CI, 0.00235–0.03571). Frozen-model sensitivity analyses produced AUROCs from 0.697 to 0.733 in most observation and measurement subsets. However, 15,900 otherwise eligible patients had indeterminate outcomes and showed substantially shorter follow-up and fewer post-landmark creatinine measurements. Conclusions: The selected model showed moderate discrimination and close aggregate calibration under internal validation. Discrimination was similar across several post hoc subsets, although calibration and threshold-based performance changed under stricter observation rules. The main limitation was observation-dependent outcome ascertainment. This work supports transparent model auditing as part of trustworthy AI evaluation, but it does not provide external validation, patient-level explanation validation, or evidence of clinical benefit. Multicenter temporal validation and prospectively defined observation rules are needed before clinical use.