Search Results (303)

Background: Spinal cord stimulation (SCS) is an established intervention for refractory chronic neuropathic pain, but response to trial stimulation and long-term benefit remain heterogeneous. Clinicians need practical tools to document patient-selection domains discussed in the neuromodulation literature without overstating the precision of currently available evidence. Methods: We conducted a narrative synthesis of randomized trials, cohort studies, registry analyses, systematic reviews, and consensus recommendations addressing SCS outcomes and candidate selection. The objective was not to derive or validate a multivariable prediction model, but to construct a transparent, bedside-oriented framework organizing clinically accessible domains relevant to SCS trial candidacy. Results: Six domains were incorporated into the proposed SCS Trial Success Score (STSS): primary indication, psychological status, smoking status, opioid burden, body mass index, and pain duration. The resulting 0 to 12 point score is presented as an evidence-informed clinical profile rather than a validated prognostic instrument. Three descriptive categories are proposed: more favorable profile, optimization-sensitive profile, and less favorable profile. These categories are intended to guide documentation, shared decision-making, and optimization of modifiable factors, not to determine eligibility automatically. Conclusions: Pending prospective validation, checklist-mode use is the preferred interim application of the STSS. The framework may support structured pre-trial assessment, identification of modifiable factors, and shared decision-making. It should not be used as a standalone numerical decision rule, to deny access to neuromodulation, or to replace multidisciplinary judgment. Prospective derivation, calibration, external validation, and decision-curve analysis are required before the STSS can be considered a clinical prediction rule. Full article

Background/Objectives: Pes planus and pes cavus are common foot deformities, which may lead to pain, functional limitations, and impairment of foot biomechanics. While calcaneal pitch, talar declination, and Meary angles, commonly used in diagnosis, provide objective information, their lack of a gold standard and the observer’s dependence on manual measurements limit their reliability. Therefore, in this study, these angles obtained from weight-bearing lateral foot radiographs were evaluated according to literature references, and the aim was to determine the model that provides the most accurate prediction in the diagnosis of pes planus using machine learning algorithms. It should be emphasized that, because the diagnostic labels were derived from literature-based thresholds of these same angles, the machine-learning task addressed here is the automated reproduction and standardization of expert, angle-threshold-based classification, rather than an independent clinical diagnosis from raw images. Methods: This retrospective study was conducted using weight-bearing lateral foot radiographs of 697 male patients obtained from the archives of public hospitals in Gaziantep. Calcaneal pitch, Meary angle, and talar declination angles were evaluated in both feet, and the data were labeled as normal, pes planus, and pes cavus. The dataset, consisting of a total of 1394 feet, was divided into training and test groups and analyzed using Random Forest, XGBoost, Logistic Regression, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) algorithms; the diagnostic performance of the models was compared using measures such as accuracy, F1 score, sensitivity, and specificity. Results: A total of 1394 feet from 697 male patients (mean age 24.8 ± 5.57 years) were analyzed using five machine learning algorithms with calcaneal pitch angle (CPA), Meary angle (MA), and talar declination angle (TDA) as reference labels. Ensemble-based methods showed superior performance, with XGBoost achieving perfect classification (Accuracy = 1.000) under all three labels for the left foot and 0.996–1.000 for the right foot, while Random Forest reached 0.986–1.000 across all experiments. Logistic Regression and SVM yielded moderate accuracies (0.905–0.973), whereas KNN consistently performed the weakest (0.905–0.964), particularly in the pes cavus subgroup. The near-perfect accuracy obtained when the labeling angle was itself included among the predictors reflects, at least in part, the algebraic reconstruction of the threshold rule from a same-source variable rather than genuine diagnostic generalization; results should therefore be interpreted with this in mind. Conclusions: This study demonstrates that machine learning, particularly ensemble methods such as XGBoost and Random Forest, provides high accuracy and consistency in diagnosing foot arch deformities based on radiographic angle measurements. Traditional models, such as Logistic Regression, still hold value in terms of clinical interpretability despite their lower performance. The findings suggest that machine learning-based approaches can offer objective, rapid, and reliable decision support tools for diagnosing pes planus and pes cavus, but external validation studies are necessary for clinical generalizability. Full article

The innate–adaptive immune interface is a decisive control point determining whether therapeutic interventions induce durable protection, antitumor immunity, inflammatory, or immune tolerance. Many immunotherapies fail in translation because immunity is often treated as a single-output system rather than a spatially and temporally organized network shaped by tissue context, antigen-presenting cell fate, biomolecular conditioning, and metabolic state. This review introduces the immunoscape framework as a nanobiotechnology-oriented model for linking immune-state mapping with controllable translational variables, including delivery route, release kinetics, first-contact immune cells, lymphatic routing, biomolecular corona identity, antigen-presenting cell fate, and safety-gate assessment. Unlike systems immunology, which primarily describes immune networks, or conventional immune engineering, which often focuses on selected payloads, targets, or platforms, the immunoscape framework provides a design layer for predicting context-dependent immune outcomes. We discuss two converging strategies for reprogramming this interface: natural biologics, including beta-glucans, polyphenols, microbial metabolites, and extracellular vesicles; and smart nanomaterials, including lipid nanoparticles, biomimetic vesicles, lymph node-targeted platforms, and stimulus-responsive nanoarchitectures. We further propose translational design rules to guide clinically realistic immune-reprogramming nanomedicines for cancer, infectious, inflammatory, and regenerative applications. Full article

Background/Objectives: Oral potentially malignant disorders (OPMDs) require accurate risk stratification to identify patients at the highest risk for severe oral epithelial dysplasia (OED) or oral squamous cell carcinoma (OSCC). We developed and internally validated the oral cancer numerical index (OCNI), a quantitative risk score derived from clinical features and deep learning-based brush cytology measurements. Methods: This retrospective model development and internal validation study was conducted using data from the multicenter Grand Opportunity study. Prospectively recruited subjects with OPMD with complete data were divided at the subject level into a training set (n = 384) and a holdout test set (n = 164) using a 70:30 diagnosis-stratified split. The primary endpoint was severe OED or OSCC versus benign diagnoses, and mild and moderate OED. Predictors included age, sex, tobacco history, lesion color, lesion size, multiple lesions, ulcerative morphology, and the percentages of differentiated squamous epithelial and small round cells derived from deep learning-based cytology. Prespecified rule-out and rule-in thresholds were selected in the training set to target 90% sensitivity and 90% specificity, respectively, and then applied to the holdout test set. Results: At the prespecified rule-out threshold (OCNI ≤ 37.6), sensitivity was 92% and negative predictive value was 97%. At the rule-in threshold (OCNI > 60.0), specificity was 89% and positive predictive value was 67%. Calibration was good in the holdout set (intercept, −0.07; slope, 1.13; Hosmer–Lemeshow p = 0.36), and OCNI increased significantly with worsening histopathologic severity. Conclusions: OCNI provided an objective, clinically interpretable estimate of risk for severe OED or OSCC, with strong rule-out and rule-in performance and good calibration. These findings support further external validation of OCNI as an adjunctive tool for oral lesion risk stratification. Full article

Objectives: To assess whether [^99mTc]Tc-UBI 29-41 SPECT/CT combined with a standardized target-to-liver ratio can reliably support clinical decision-making in patients with difficult-to-diagnose bacterial infections and to establish a reproducible diagnostic threshold applicable across four infectious scenarios. Methods: This prospective diagnostic accuracy study, conducted following STARD guidelines, included 156 consecutive patients (346 lesions) with clinical suspicion of infected arthroplasty, spondylodiscitis, osteomyelitis, or fever of unknown origin. Target-to-liver total count ratios were calculated from SPECT/CT images. Diagnostic performance was assessed using bootstrap-resampled ROC analysis, Fagan nomograms, and penalized logistic regression. Results: All four conditions showed good discriminatory capacity (AUC: 0.965–0.979). At a cutoff ratio ≥ 1.5, specificities exceeded 95% and negative predictive values were ≥97.8% across all subgroups. Post-test probability after a negative scan decreased to 2–3% in every condition, consistent with clinically meaningful rule-out capability across all four scenarios. Penalized logistic regression confirmed significant associations between elevated ratios and confirmed infection (OR: 22.02–245.53; all p ≤ 0.003). Conclusions: [^99mTc]Tc-UBI 29-41 SPECT/CT with target-to-liver ratio analysis provides clinically meaningful diagnostic support across four distinct infectious scenarios, with particular strength as a rule-out test. A threshold of ≥1.5 offers a standardized, potentially reproducible criterion that may guide clinical decisions and reduce reliance on invasive confirmatory procedures. Prospective multicentre validation is warranted to establish this bacteria-specific approach as a practical complement to existing diagnostic algorithms. Full article

Background/Objectives: Medication-related osteonecrosis of the jaw (MRONJ) is a serious complication of bisphosphonate therapy, whose risk is currently assessed through qualitative staging systems that do not integrate pharmacological determinants of cumulative drug exposure. The aim of this study is to present the Bisphosphonate Accumulation Index (BAI), a pharmacologically derived, dimensionless scalar quantifying cumulative exposure to bone-targeted antiresorptive agents by integrating relative potency, administered dose, dosing frequency, route-specific bioavailability, and treatment duration, for use as a pre-procedural assessment tool in patients receiving bisphosphonates. Methods: The BAI combines five pharmacologically grounded parameters from peer-reviewed literature: (1) relative antiresorptive potency referenced to etidronate; (2) dose per administration (mg); (3) monthly dosing frequency; (4) bioavailability route; and (5) years of treatment within the preceding 10-year window. The model includes nine bisphosphonates registered in Italy. Results: The BAI spans approximately five orders of magnitude (from <1000 for short-term oral therapy to >120,000 for monthly intravenous zoledronic acid). Four analyses support the model: sensitivity analysis identifies relative potency as the main source of variance; ecological calibration against nine MRONJ incidence data points yielded r = 0.911 (p = 0.0006, R² = 0.829), indicating that the BAI accounts for approximately 83% of the population-level variance in published incidence rates across heterogeneous regimens (ecological correlation; this does not establish individual-level predictive validity); Monte Carlo simulation on 10,000 patients generated a plausible exposure-strata distribution (6.1% low, 66.6% moderate, 27.3% high); and concordance analysis with a DDD-based metric showed discordance in 7/8 regimens. Conclusions: The BAI is a transparent, reproducible, pharmacologically grounded metric of cumulative antiresorptive exposure addressing the quantitative gap identified in the AAOMS 2022 Position Paper. The BAI measures pharmacological exposure, which is a necessary but insufficient component of MRONJ risk; clinical modifiers such as corticosteroid co-administration, diabetes, renal function, and procedure type are not integrated and must be evaluated independently. The provisional exposure strata reported here (<1000, 1000–10,000, >10,000) are hypothesis-generating and intended solely to guide the design of validation studies; they should not be used as clinical decision rules until prospective patient-level validation has been completed. Full article

Precision medicine in prostate cancer (PCa) is increasingly best understood as a continuum linking risk-adapted detection, multimodal diagnosis and phenotyping, and implementation-ready decision pathways. Contemporary clinical guidelines emphasize structured diagnostic strategies, appropriate use of advanced imaging, and selective deployment of biomarkers when results can alter management. Upstream risk enrichment using polygenic risk scores and multivariable prediction models may improve the yield of clinically significant disease while mitigating harms related to overdiagnosis. At the point of suspicion, magnetic resonance imaging-first pathways and reflex biomarker testing provide practical tools to reduce unnecessary biopsy while maintaining safeguards for the detection of clinically important disease. Beyond diagnosis, prostate-specific membrane antigen positron emission tomography refines disease-state phenotyping in initial staging, biochemical recurrence, and limited-burden presentations, while standardized acquisition and reporting improve reproducibility and multidisciplinary communication. Germline and tumor-based molecular profiling should be operationalized as a longitudinal care process with clear consent, turnaround targets, and test-to-action rules that define what each result enables at specific decision nodes. Finally, longitudinal monitoring approaches, including liquid biopsy and artificial intelligence-enabled pathology, are evolving rapidly and require transparent reporting and rigorous risk-of-bias appraisal before broad clinical adoption. This narrative review synthesizes key evidence across the precision continuum and outlines a decision-node-based, test-to-action framework for maximizing clinical benefit, maintaining quality, and ensuring equitable access. Full article

Tooth extraction and maximum anchorage assessment are key decision points in orthodontic treatment planning, yet existing machine learning models for orthodontic decision support often lack transparency, limiting their clinical interpretability and trustworthiness. In this study, we developed and externally validated an explainable orthodontic treatment decision-support model that integrates expert-derived Analytic Hierarchy Process (AHP) weighting with machine learning. A diagnostic indicator framework comprising 18 orthodontic variables was established through a literature review, clinical data analysis, and two rounds of expert surveys. A retrospective cohort of 485 patients receiving fixed-appliance orthodontic treatment was used for model development and internal validation. AHP-derived composite scores were incorporated into the machine learning models for two prediction tasks, namely tooth extraction and maximum anchorage requirement, and an expert-informed fuzzy-rule score was calculated from pretreatment indicators for the maximum anchorage task to capture clinically interpretable anchorage tendencies. Model performance was evaluated using ROC-AUC, F1 score, precision, recall, PR-AUC, calibration analysis, and decision curve analysis, while SHAP was applied to interpret feature contributions. The AHP-RF extraction model and AHP-enhanced LR maximum anchorage model achieved the highest AUCs among the compared models (0.864 and 0.822, respectively), although paired DeLong tests showed no significant differences from the closest competing models. SHAP analysis identified lower lip-to-E-line distance, U1-NA, and the AHP composite score as important predictors, indicating consistency between model outputs and clinical reasoning. In the external validation cohort, the extraction model correctly classified 57 of 74 cases, and the maximum anchorage model correctly classified 24 of 29 cases, supporting the preliminary transportability of the proposed framework. These results suggest that integrating AHP-derived expert knowledge with machine learning provides an explainable and clinically interpretable decision-support model for orthodontic treatment planning, with potential value in improving standardized, evidence-informed, and patient-specific orthodontic decision-making. Full article

The introduction of rapid, high-sensitivity cardiac troponin (hs-cTn)-based algorithms has markedly changed the work-up of patients admitted to the emergency department (ED) with suspected acute coronary syndrome (ACS). However, when applied to real-world ED populations, these algorithms perform worse than in clinical studies of derivation and validation. The main reasons for this discrepancy are that patients tested for hs-cTn in real-world settings tend to be older and less clinically preselected. Nevertheless, ACS must often be ruled out in patients with atypical presentations. Routine patients also more frequently have impaired renal function and pre-existing cardiac diseases, such as atrial fibrillation, heart failure, or coronary artery disease. These conditions do not necessarily cause the actual acute ED presentation. Using the standard decision limits of the 0 h, 0/1 h, or 0/2 h algorithms does not hinder the exclusion of ACS in the ED. However, using them in real-world conditions substantially decreases the positive predictive value for acute myocardial infarction (AMI) and classifies a higher percentage of patients into the “observe (gray) zone” than reported in clinical studies. Patients classified with a working diagnosis of “rule-in AMI” often require hospital admission for other reasons, though their discharge diagnosis may differ from AMI. A major challenge in real-world EDs is the high proportion of gray zone hs-cTn concentrations in approximately 50% of tested patients. Therefore, additional hs-cTn sampling at 3 h after admission is often necessary to rule out acute myocardial injury. This review summarizes and critically discusses the evidence for adjusting hs-cTn ED algorithm decision limits according to age, sex, and renal function. It also discusses the critical differential diagnosis of acute and chronic myocardial injury in the ED. Full article

Background: Early identification of metabolic health risk is important for preventive intervention, but routine laboratory testing is not always available in everyday health-management environments. Artificial intelligence models can estimate risk from accessible variables, but purely data-driven models may provide limited clinical interpretability. Objective: This study presents the Advanced Hybrid Inference Model (AIM), a clinically interpretable screening support framework that combines biomarker estimation, Random Forest-based risk prediction, and rule-based clinical interpretation. Methods: AIM was intentionally implemented as a three-stage, Random Forest-centered pipeline: (1) Selected anthropometric and demographic variables were used to estimate clinically relevant metabolic biomarkers when direct measurements were unavailable. (2) A Random Forest model generated metabolic risk estimates from measured or estimated biomarkers and clinical variables. (3) Rule-based interpretation mapped the model outputs and biomarker thresholds to clinically meaningful risk-support messages. Results: Experimental validation was conducted using clinically collected datasets under class-imbalanced conditions. The results indicate that the proposed framework showed exploratory potential for identifying high-risk patterns. These findings suggest that the AIM framework may be useful as a screening-oriented approach. Conclusions: AIM should be interpreted as an exploratory clinical screening support framework that prioritizes interpretability, structured rule-based reasoning, and risk prioritization rather than a diagnostic classifier or universally superior prediction model. Full article

Background/Objectives: Providing optimized and accurate treatment to cancer patients remains a major challenge in oncology care. The emergence of precision medicine tools to match the correct therapy to the patient has significantly advanced treatment modalities in the last few years. While genomics has been shown to be critical in selecting targeted therapies for a specific somatic mutation, the overall clinical benefit of broad genomic sequencing has been found lacking. Here, we evaluate the utility of our previously clinically validated ex vivo functional assay across different treatment scenarios, demonstrating its ability to transform predicted non-responders into predicted responders, rule out ineffective treatments, provide multiple treatment options, and validate physician choices. Methods: The evaluation was performed on a post-market surveillance study analyzing 312 patients, from which 278 patients had successful test reports (an 89.1% test success rate), with clinical outcomes available from 45 of those patients. Results: We show that in the group of patients with clinical response data, the tests yield a PPV of 91.18% and NPV of 90.91% with clinical utility impacting physician decision in 51.1% of cases. Further analysis of the entire cohort showed the potential of clinical utility to reach up to 59.3% on a large group of patients. Conclusions: The accurate prediction of patient response using the test suggests the potential for the platform to improve patient treatment in clinical practice by reducing ineffective drug use and optimizing personalized patient drug regiments. Full article

Background/Objectives: Access to neurosurgical care remains limited in many trauma systems worldwide, particularly in low- and middle-income countries (LMICs). The Brain Injury Guidelines (BIG) were developed to guide the management of traumatic brain injury (TBI) and optimize resource utilization; however, their applicability in resource-limited environments without on-site neurosurgical coverage remains unclear. The aim of this study was to evaluate the performance and applicability of the BIG in a trauma center without neurosurgical support. Methods: We performed a retrospective analysis of adult patients with TBI admitted to a trauma center without neurosurgical support in São Paulo, Brazil, between 2013 and 2017. Patients were classified according to the BIG criteria (BIG 1–3) based on clinical and radiological findings. Primary outcomes were clinical and radiological deterioration and mortality; secondary outcomes included neurosurgical transfer, repeat computed tomography (CT) utilization, and length of stay. Results: A total of 178 patients were included: 12 (6.7%) BIG 1, 53 (29.8%) BIG 2, and 113 (63.5%) BIG 3. No patient classified as BIG 1 or BIG 2 experienced clinical or radiological deterioration, required neurosurgical intervention, or died; adverse outcomes were confined to the BIG 3 cohort, with a mortality rate of 11.5%. The combined BIG 1–2 group showed a sensitivity and negative predictive value (NPV) of 100% for identifying patients without deterioration or need for neurosurgical intervention. Despite the absence of adverse events in the BIG 1–2 group, 76.4% of patients underwent transfer for neurosurgical evaluation, and repeated CT imaging was frequently performed. Conclusions: In this single-center retrospective cohort, the BIG demonstrated excellent discriminatory ability for identifying low-risk TBI patients in a setting without neurosurgical coverage. BIG 1 and BIG 2 categories reliably ruled out the need for neurosurgical intervention, supporting selective non-transfer strategies to optimize resource utilization. Full article

Background: Predicting rehabilitation outcomes at admission supports tailored therapy plans and efficient use of resources for patients undergoing intensive inpatient rehabilitation, including those with stroke, orthopedic, and other neurological conditions. Nonetheless, current machine learning (ML) methods face limitations, including the ceiling effect in absolute functional gain measures, the uniform treatment of diverse patient groups, and reliance on black-box models that lack clinical transparency. Methods: This retrospective observational study analyzed a fully anonymized, publicly available dataset of 3419 patients admitted to the intensive rehabilitation unit at IRCCS San Raffaele Hospital, Rome, Italy, from 2015 to 2018. To mitigate the ceiling effect, a normalized Barthel Index gain metric was developed. K-means clustering (K = 2, trained solely on the training set) identified patient admission profiles based on functionality, which were then used as predictive features. Eight machine learning classifiers were tested across three groups (All Patients, Orthopedic, Neurological). SHAP-based explainability was employed at four levels: global, diagnostic group, patient functional profile, and individual. Finally, clinical decision rules and bedside stratification profiles were derived and validated with an internal held-out test set (n = 684). Results: Normalization significantly increased the correlation between admission BI and gain (r = 0.130 to r = 0.520), supporting the presence of a ceiling-related limitation in absolute gain metrics. Two distinct functional admission profiles with statistically significant group differences were identified—High-Burden (38% below-median recovery) and Moderate-Burden (21%)—with cluster membership the third most important predictor (13.9% SHAP importance). The highest AUC-ROC values were 0.831 for all patients (XGBoost), 0.864 for neurological patients (Gradient Boosting), and 0.839 for orthopedic patients (Gradient Boosting). Multilevel SHAP analysis showed age as the primary predictor for neurological patients (mean |SHAP| = 0.360) but the third for orthopedic patients (0.350), highlighting clinical relevance. Validation using SHAP values from the Gradient Boosting model showed a Spearman correlation of ρ = 0.925 (p = 1.13 × 10⁻³⁰), with eight of the top ten features overlapping, indicating that these patterns are not model-specific but reflect the underlying data. Risk zone stratification found 80.7% of patients in high-confidence zones (accuracy > 80%). The clinical decision rules achieved 70.8% accuracy with full transparency, and the elderly (≥75 years) combined with a low BI (<25) profile showed an 89.6% model accuracy with only 10.4% recovery above the median. Conclusions: This explainable, profile-informed ML pipeline addresses key methodological limitations in predicting rehabilitation outcomes. It also provides a foundation for integrating models into clinical practice, pending prospective, external validation of the results. Before clinical implementation, validation across multicenter cohorts is essential. Full article

Introduction: The global aging population has led to a rapid increase in patients aged ≥ 80 years experiencing out-of-hospital cardiac arrest (OHCA). This study used data from three domestic university hospitals to analyze the clinical characteristics and prognoses of elderly patients and evaluate the validity of age-based criteria for termination of resuscitation (TOR). Methods: This study included 1234 adult patients with nontraumatic OHCA who presented to the emergency departments of three hospitals between 2015 and 2021. The patients were categorized as non-elderly (<65 years), elderly (65–79 years), or super-elderly (≥80 years), and outcomes, including return of spontaneous circulation (ROSC), survival to discharge, and favorable neurological outcomes (Cerebral Performance Category 1–2), were analyzed. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) with Wilson 95% confidence intervals (CIs), and the area under the ROC curve (AUC) of the W−/D−/R− (unwitnessed/non-shockable/no prehospital ROSC) rule were calculated for both the full cohort and the super-elderly subgroup. Results: The super-elderly patients (n = 466) had significantly lower rates of ROSC, survival to discharge, and favorable neurological outcomes than the other age groups. Multivariate analysis revealed that extreme old age was a strong negative predictor of favorable neurological outcomes. For super-elderly patients as a whole (n = 466), the survival rate was only 2.4%, and the favorable neurological outcome rate was only 0.6%. Conclusions: Although the prognosis for super-elderly patients with OHCA is extremely poor, the possibility of survival is not entirely “zero.” Therefore, applying a multifactorial ED TOR rule that comprehensively considers whether the arrest was witnessed, the initial rhythm, and whether on-scene ROSC occurred, rather than relying solely on age criteria, would be more rational and aid in ethical decision-making. Full article

The rising threat of antimicrobial resistance necessitates the search for novel bioactive molecules from natural sources. This study investigated the phytochemical composition, antibacterial potency, and molecular docking interactions of Citrus aurantium peel ethanol extract against Escherichia coli outer-membrane and topoisomerase proteins and Staphylococcus aureus toxins as drug target proteins. Qualitative and quantitative phytochemical compositions were examined using standard analytical methods, chemical compounds were evaluated and qualified using Gas Chromatography–Mass Spectrometry (GC-MS), and antibacterial effects were investigated in silico and validated in vitro. Qualitative and quantitative analyses revealed high concentrations of flavonoids (4.54 ± 0.11%), alkaloids (1.6 ± 0.03%), terpenoids (1.35 ± 0.01%), tannins (1.02 ± 0.05%), phenols (0.97 ± 0.07%), and saponins (0.80 ± 0.01%). GC–MS profiling identified several dominant compounds, including β-D-glucopyranose, neo-inositol, 8-(2,3-dihydroxy-3-methylbutyl)-7-methoxy-2H-chromen-2-one, and D-allose. In silico docking studies against bacterial druggable proteins (PDB IDs: 4C56 and 3MFG, which are S. aureus toxins; 1BXW and 3FV5, which are E. coli outer-membrane and topoisomerase proteins) revealed strong binding affinities (−6.477 to −8.774 kcal/mol), comparable to standard antibiotics. ADMET predictions confirmed favorable pharmacokinetic and safety profiles, with most lead compounds displaying high intestinal absorption, low hepatotoxicity, and compliance with Lipinski’s rule of five. The extract exhibited stronger antibacterial activity, producing inhibition zones of 25.11 ± 0.017 and 23.04 ± 0.25 mm against clinical isolates of S. aureus and E. coli, respectively, at a concentration of 10 mg/mL, comparable to ciprofloxacin (30.35 ± 0.26 mm). These findings highlight C. aurantium peel phytoconstituents as promising scaffolds for antibacterial drug development and justify further in vivo validation for combating multidrug-resistant pathogens. Full article