Intelligent Pharmacy最新文献

{"title":"Advancements in transdermal drug delivery using ionic liquids: Design strategies, functional roles, mechanisms, and future challenges","authors":"Parwinder Kaur,&nbsp;Amanpreet Kaur,&nbsp;Rimpi","doi":"10.1016/j.ipha.2026.03.001","DOIUrl":"10.1016/j.ipha.2026.03.001","url":null,"abstract":"<div><div>One potential method for improving transdermal medication absorption is ionic liquids (ILs). However, further research is necessary to create effective ILs and clarify their methods of action because of the unique structural characteristics of ILs. This paper examines the basic design concepts of ideal ILs for transdermal drug delivery systems (TDDS), taking into account toxicity, skin permeability, and melting point, all of which are influenced by ion types, molar ratios, functional groups, and inter-ionic interactions. The functions of ILs in developing TDDS are also described in detail, including their use as novel solvents to improve drug solubility in carriers, as innovative skin penetration enhancers to increase transdermal drug absorption, as new active pharmaceutical ingredients (API-ILs) to control drug pharmacokinetics, skin permeability, solubility, and release, and as sophisticated polymers to develop smart medical materials. Additionally, a summary of several action pathways is provided, mainly focusing on the interactions between ILs, medications, polymers, and skin constituents. The discussion concludes with a discussion of ILs' future challenges, including determining quantitative structure-activity relationships, comprehending the intricate forces of interaction between anions, medications, polymers, and the skin microenvironment, guaranteeing long-term stability, and resolving <em>in vivo</em> safety issues. In conclusion, the purpose of this essay is to encourage the development of TDDS with ILs.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"4 3","pages":"Pages 199-210"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148546814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pediatric physiologically based pharmacokinetic models mediated by drug-metabolizing enzymes: Predictions, applications, and challenges","authors":"Juan Wu,&nbsp;Yawen Yuan,&nbsp;Haonan Li,&nbsp;Junyu Li,&nbsp;Cheng Jin","doi":"10.1016/j.ipha.2026.04.001","DOIUrl":"10.1016/j.ipha.2026.04.001","url":null,"abstract":"<div><div>Children, as a special population, exhibit significant age-specific characteristics and inter-individual variability in drug metabolism due to the influences of physiological development and genetic factors, bringing challenges to the efficacy and safety of clinical medication. Traditional pharmacokinetic studies are difficult to conduct in children and are constrained by numerous ethical limitations. Physiologically based pharmacokinetic (PBPK) modeling, as a mechanistic modeling tool, can integrate pediatric developmental physiological parameters, enzyme kinetic characteristics, and genetic polymorphism data. It has gradually become an important tool for predicting pediatric drug metabolism and optimizing dosing regimens. This review summarizes the key enzymatic characteristics of pediatric drug metabolism and the technological pathways and current application status of PBPK models in assessing pediatric drug metabolism. It discusses the major challenges, such as uncertainties in parameter extrapolation and the lack of pediatric-specific data. It further elaborates on the practical value of PBPK models in optimizing dosing regimens, supporting pediatric clinical trial design, and aiding regulatory decision-making. Finally, it proposes future directions for development by integrating artificial intelligence and multi-omics data. This review aims to provide a theoretical basis and practical reference for precision dosing in children and to promote the broader application of PBPK models in the pediatric pharmaceutical field.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"4 3","pages":"Pages 217-225"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148546866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reconstruction and optimization of the operational workflow model in an inpatient pharmacy before and after implementation of a wireless communication-based intelligent drug dispensing and traceability system","authors":"Xin-ling Liu,&nbsp;Ling Li,&nbsp;Xiao-ye Cao,&nbsp;Jia-ying Tu,&nbsp;Bo Yuan","doi":"10.1016/j.ipha.2026.03.002","DOIUrl":"10.1016/j.ipha.2026.03.002","url":null,"abstract":"<div><h3>Objective</h3><div>This study aimed to assess workflow changes and identify optimization strategies following the implementation of a wireless communication-based intelligent drug dispensing and traceability system (IDDTS) in an inpatient pharmacy setting, with the goal of improving operational efficiency and the accuracy of medication order processing and dispensing.</div></div><div><h3>Methods</h3><div>A pre–post observational study was conducted over two consecutive 30-working-day periods before and after IDDTS implementation to document changes in the medication order dispensing workflow. User Journey Mapping and Root Cause Analysis were employed to investigate potential causes of the low utilization of the IDDTS for processing one-time medication orders. Based on the findings, the workflow for one-time medication orders was redesigned and optimized.The effectiveness of these interventions was evaluated by comparing key performance indicators before and after the process reconstruction.</div></div><div><h3>Results</h3><div>The implementation of the IDDTS, together with workflow redesign and optimization, reduced redundant steps and improved medication order dispensing performance, including workflow efficiency and dispensing accuracy. Utilization of the system for one-time medication orders and overall staff satisfaction also improved.</div></div><div><h3>Conclusions</h3><div>The IDDTS shows considerable potential to streamline inpatient pharmacy dispensing operations and support workflow optimization for medication order processing and distribution. Further refinements are recommended to fully realize its benefits in routine practice.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"4 3","pages":"Pages 211-216"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148546865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence assisted design of nanomedicines for colorectal cancer diagnosis and therapy: Advances, challenges, and future directions","authors":"Yogananthan Dhanapal,&nbsp;Duraisamy Sridhar,&nbsp;Sulekha Khute,&nbsp;Paranthaman Subash,&nbsp;Subramaniam AnandaThangadurai","doi":"10.1016/j.ipha.2026.01.001","DOIUrl":"10.1016/j.ipha.2026.01.001","url":null,"abstract":"<div><div>Colorectal cancer (CRC) remains one of the leading causes of cancer-related morbidity and mortality worldwide, with an increasing incidence in both high- and low-income countries. Despite advances in colonoscopy, imaging, molecular biomarker testing, and multimodal therapeutic regimens, limitations in early detection, tumor heterogeneity, and resistance to conventional therapy continue to hinder effective management of CRC. Nanomedicine offers transformative opportunities for precision diagnosis and therapy by enabling targeted delivery, controlled drug release, and multimodal imaging. Concurrently, artificial intelligence (AI), including machine learning (ML), deep learning (DL), and emerging transformer-based architectures, has revolutionized the interpretation of biomedical data and guided the rational design of nanocarriers for drug delivery applications. The synergistic integration of artificial intelligence and nanotechnology has accelerated the discovery of CRC-specific biomarkers, improved formulation optimization, enabled predictive pharmacokinetic/pharmacodynamic modeling, and facilitated the design of adaptive clinical trials. Recent breakthroughs include AI-driven histopathology and imaging analysis for early CRC detection, with AI-assisted colonoscopy demonstrating sensitivity improvements of up to 94%–97% and accuracy gains of 10%–20% compared to standard methods. However, major challenges remain, including limited access to large, annotated CRC datasets, the interpretability of AI models in clinical decision-making, the reproducibility of complex nanoparticle synthesis, and regulatory gaps in nanomedicine. This review synthesizes the current advances in AI-assisted nanomedicine for CRC diagnosis and therapy, critically evaluates the translational barriers, and outlines future research trajectories. Ultimately, multidisciplinary collaboration across oncology, nanotechnology, the design of adaptive clinical trials, science, and regulatory science is essential to realize the full potential of AI-powered nanomedicine in CRC management</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"4 2","pages":"Pages 159-174"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148001587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correlation study on serum TT3 and FT3 levels with disease severity in elderly tuberculosis patients — Exploration of the value of thyroxine level-guided Anti-TB individualized medication","authors":"Lei Xuan,&nbsp;Xue Yu,&nbsp;Lei Ming,&nbsp;Wen Li","doi":"10.1016/j.ipha.2025.12.005","DOIUrl":"10.1016/j.ipha.2025.12.005","url":null,"abstract":"<div><h3>Background</h3><div>Tuberculosis (TB) remains a major global public health issue, with elderly patients (≥ 65 years) at higher risk of severe progression—driven by immune decline, polypharmacy, and impaired drug metabolism, which complicate anti-TB medication management in geriatrics. As the thyroid's primary active hormones, TT3 and FT3 regulate metabolism and immunity, both critical for medication tolerance, therapeutic response, and prognosis in elderly TB patients. Low TT3 and FT3 levels correlate with poor outcomes in elderly severe pulmonary TB, often alongside higher anti-TB toxicity and lower efficacy. Aligned with intelligent pharmacy's goal of optimizing high-risk care, this study explores the correlation between serum TT3 and FT3 and disease severity in elderly TB patients—and verifies T3 as a practical biomarker for geriatric anti-TB risk stratification and dose adjustments.</div></div><div><h3>Methods</h3><div>A retrospective observational study was conducted, enrolling 509 TB patients admitted to our hospital from January 2022 to December 2023. Patients were divided into a severe group (<em>n</em> = 270) and non-severe group (<em>n</em> = 239) based on severe TB development within 1 week of admission. Venous blood samples were collected on admission to measure serum TT3 and FT3; patient demographics and 1-week severe manifestations were recorded. TT3 and FT3 levels on admission were significantly lower in the severe group.</div></div><div><h3>Results</h3><div>Severe patients had significantly lower TT3 and FT3 than non-severe patients (both <em>P</em> &lt; 0.001). Pearson analysis showed a significant negative correlation between TT3 and FT3 and severe pulmonary TB (TT3: r = −0.541, <em>P</em> &lt; 0.001; FT3: r = −0.423, <em>P</em> &lt; 0.001). ROC curve analysis confirmed high evaluative value of TT3 and FT3 for severe TB (AUC = 0.841 and 0.827, respectively). Subgroup analysis revealed that negative correlations persisted in both elderly and non-elderly groups: TT3 correlation was slightly weaker in the elderly (r = −0.516 vs. non-elderly r = −0.529), while FT3 correlation was stronger (r = −0.491 vs. non-elderly r = −0.380).</div></div><div><h3>Conclusion</h3><div>Serum TT3 and FT3 levels are closely associated with disease severity in elderly TB patients and serve as potential biomarkers for geriatric anti-TB individualized medication. Notably, FT3's stronger correlation in the elderly makes it more reliable for guiding anti-TB risk stratification and dose adjustments.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"4 2","pages":"Pages 139-144"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148001715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploration of the mechanism of “Psoralea corylifolia Linn.-Epimedium brevicornu Maxim.” herb pair in the treatment of liver cancer based on network pharmacology","authors":"Meijun Yue ,&nbsp;Naiqiu Lin ,&nbsp;Shiqi Jia ,&nbsp;Qiong Gu ,&nbsp;Guohui Li ,&nbsp;Chunyu Li","doi":"10.1016/j.ipha.2026.02.001","DOIUrl":"10.1016/j.ipha.2026.02.001","url":null,"abstract":"<div><div>Liver cancer treatment remains challenging, and the anti-liver cancer mechanism of the “<em>Psoralea corylifolia</em> Linn.-<em>Epimedium brevicornu</em> Maxim.” herb pair is unclear. This study aims to elucidate its synergistic mechanism based on network pharmacology. Network pharmacology was used to screen the active components and targets of the herb pair, construct protein–protein interaction (PPI) and “herbs-components-targets-disease” networks, perform Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses, and validate findings via molecular docking. A total of 221 overlapping core targets between the “<em>Psoralea corylifolia</em> Linn.-<em>Epimedium brevicornu</em> Maxim.” herb pair and liver cancer were identified, among which TP53, AKT1, CYP1A1, UGT1A7, and UGT1A1 were the five key nodes crucial for the synergistic effects of the herb pair. KEGG enrichment analysis showed that “Chemical carcinogenesis - receptor activation” and “Lipid and atherosclerosis” are the core pathways through which this herb pair exerts its effects. Molecular docking confirmed stable binding between core components like kaempferol and key targets such as CYP1A1, supporting the potential for this herb pair to intervene in liver cancer progression via multiple targets and pathways. This study systematically elucidates how the “<em>Psoralea corylifolia</em> Linn.-<em>Epimedium brevicornu</em> Maxim.” herb pair exerts anti-liver cancer effects through a multi-target and multi-pathway network, establishing a molecular mechanism framework for the synergistic intervention of liver cancer using traditional Chinese medicine herb pairs.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"4 2","pages":"Pages 183-191"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148001717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generative artificial intelligence in pharmaceutical drug development: A systematic review of time and cost efficiency across discovery, preclinical, and clinical phases","authors":"Aaron Riemer ,&nbsp;Victoria Freund","doi":"10.1016/j.ipha.2025.12.006","DOIUrl":"10.1016/j.ipha.2025.12.006","url":null,"abstract":"<div><div>The pharmaceutical drug development process is notoriously complex, lengthy, and costly, often requiring more than a decade and billions of dollars to bring a single compound to market. Generative artificial intelligence (AI) has emerged as a disruptive technology with the potential to accelerate this process by designing novel molecules, predicting biological interactions, and generating synthetic data. This systematic review, conducted according to PRISMA 2020 guidelines, analyzes 100 peer-reviewed studies published between 2018 and early 2025 to examine how generative AI contributes to time and cost efficiency across the discovery, preclinical, and clinical phases of drug development. The findings reveal that AI demonstrates the greatest <strong>reported</strong> impact in early-stage discovery, significantly reducing timelines for molecule identification and lead optimization while lowering experimental costs, <strong>although much of this evidence is based on in-silico proof-of-concept studies.</strong> In preclinical development, AI shows potential for predictive toxicology and resource-efficient study design, though applications remain limited and <strong>prospective validation is sparse.</strong> Clinical adoption is still emerging, with efficiency gains primarily seen in cost reduction rather than time savings, <strong>and no robust evidence yet that computational acceleration translates into reduced attrition or regulatory progress.</strong> Overall, the review highlights hidden costs as well as methodological, regulatory, and ethical barriers that currently hinder broader adoption. Future research should focus on expanding AI applications to later stages of development, standardizing evaluation metrics, and ensuring responsible, explainable integration into pharmaceutical R&amp;D workflows.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"4 2","pages":"Pages 145-158"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148001716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Construction and application of an intelligent pharmacy based on robotic-arm automatic dispensing machines and a pre-dispensing mode","authors":"Pan Fei ,&nbsp;Li Yang ,&nbsp;Liu Xueying ,&nbsp;Jin Xuesong ,&nbsp;Li Siyao ,&nbsp;Cao Yanxiang ,&nbsp;Huang Mingjing ,&nbsp;Wang Hu ,&nbsp;Li Pengfei ,&nbsp;Jia Fei","doi":"10.1016/j.ipha.2026.02.002","DOIUrl":"10.1016/j.ipha.2026.02.002","url":null,"abstract":"<div><h3>Objective</h3><div>This study aimed to enhance pharmacy operational efficiency, reduce errors, and improve patient experience by constructing and evaluating an Intelligent Pharmacy system integrating robotic-arm automatic dispensing machines with a pre-dispensing mode.</div></div><div><h3>Methods</h3><div>Three robotic-arm dispensing machines were deployed and integrated with the Hospital Information System (HIS) for automated prescription management. The system featured multi-channel traceability code collection, dynamic window allocation, and environmental monitoring. Operational data from a traditional pharmacy period (April–June 2024) were compared with data from the Intelligent Pharmacy period (November 2024–February 2025) across multiple dimensions, including waiting time, pharmacist workload, and dispensing efficiency.</div></div><div><h3>Results</h3><div>The system significantly reduced patient waiting time, with a 22.24% average decrease for same-day pickups. The combined use of machines and near-window pharmacist dispensing served 65.29% of patients, alleviating pharmacist handling and walking burdens. A 99.40% automatic traceability code collection rate was achieved, alongside real-time error identification. Dispensing efficiency increased about 33% for a single machine serving one window and about 50% in total efficiency for one machine serving two windows. The system also enabled paperless prescriptions and intelligent drug management.</div></div><div><h3>Conclusion</h3><div>The integrated Intelligent Pharmacy system effectively automates and optimizes pharmacy operations, demonstrating marked improvements in service efficiency, medication safety, and resource allocation, providing a practical model for hospital pharmacy modernization.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"4 2","pages":"Pages 192-198"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148001586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The risk of hyperammonemic encephalopathy on epilepsy and psychiatric patients: insight from FAERS data and published case reports","authors":"Gaoyang Lin ,&nbsp;Difan Duan ,&nbsp;Mengying Qian ,&nbsp;Qing Shan ,&nbsp;Ping Ma ,&nbsp;Yan Chen ,&nbsp;Jinmin Guo","doi":"10.1016/j.ipha.2026.01.002","DOIUrl":"10.1016/j.ipha.2026.01.002","url":null,"abstract":"<div><h3>Objective</h3><div>Valproate-associated hyperammonemic encephalopathy (VHE) is a serious adverse event. However, its risk profiles and clinical features remain poorly characterized across different patient populations. This study aimed to compare the incidence, clinical presentation, and outcomes of VHE between patients with epilepsy and those with psychiatric disorders.</div></div><div><h3>Method</h3><div>This study integrates pharmacovigilance data derived from the US FDA Adverse Event Reporting System (FAERS; January 2013-September 2024), with a systematic review of case reports from PubMed and Embase (up to Feb 2025). Emphasize the distinctions in demographic profiles, clinical indicators, and duration of recovery observed between the two cohorts.</div></div><div><h3>Result</h3><div>For 549 VHE cases in the FAERS database, 312 case involved epilepsy and 237 involved psychiatric. After adjusting for age and sex, psychiatric exhibited a significantly lower risk of VHE ([OR] = 0.60, 95% [CI]: 0.51-0.70). Analysis of 134 literature-derived cases revealed that elevated blood ammonia was more common in psychiatric (100% vs. 80.2%), although their serum valproate levels were lower (Median 142.0 vs. 237.3 μg/mL). Kaplan–Meier analysis indicated a shorter median recovery time in psychiatric (2 vs. 5 days). Cox regression further confirmed this result (HR = 2.47), particularly in adults (HR = 2.55) and females (HR = 3.34).</div></div><div><h3>Conclusion</h3><div>The type of indication significantly influences the risk and prognosis of VHE. Individuals with epilepsy exhibit greater sensitivity to VPA and experience a prolonged recovery period in comparison to psychiatric. Customized monitoring strategies informed by specific diagnoses are essential to enhance the safety profile of VPA.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"4 2","pages":"Pages 175-182"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148001714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CARE-Cirrhosis: A multi-level explainability framework integrating predictive modeling and personalized clinical recommendation in cirrhosis care","authors":"Deepak Kumar ,&nbsp;Brijesh Bakariya ,&nbsp;Chaman Verma ,&nbsp;Zoltan Illes","doi":"10.1016/j.ipha.2025.12.003","DOIUrl":"10.1016/j.ipha.2025.12.003","url":null,"abstract":"<div><h3>Objective</h3><div>This study introduces CARE-Cirrhosis (Cirrhosis Ascites Risk Prediction and Explainability with Recommendation Engine), a unified methodological framework that systematically integrates predictive modeling, multi-level explainability, and a personalized recommendation engine into a single, deployable clinical decision-support architecture. Rather than applying interpretability tools in isolation, the framework embeds Explainable AI (XAI) methods like SHapley Additive exPlanations (SHAP), Local Interpretable Model agnostic Explanations (LIME), and counterfactual reasoning within an operational pipeline that transforms predictive outputs into transparent, actionable, patient-specific clinical guidance. Thus, it is advancing the methodological foundations of interpretable machine learning(ML) for biomedical applications.</div></div><div><h3>Methods</h3><div>Data from the Mayo Clinic Primary Biliary Cirrhosis (PBC) cohort (<em>n</em> = 418) were analyzed using Logistic Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (XGB), evaluated under stratified 5-fold cross-validation(CV). Multi-level interpretability was achieved through XAI methods like global attribution (SHAP), local surrogate reasoning (LIME), and counterfactual analysis (DiCE). These layers were synthesized within a unified interpretability framework, linked to a rule-based recommendation engine for generating patient-specific, physiologically plausible “what-if” scenarios. The pipeline was implemented as a mobile application to demonstrate translational applicability and real-time deployment feasibility.</div></div><div><h3>Results</h3><div>All models demonstrated strong discriminative performance (AUROC 0.90–0.92). SHAP identified albumin, platelets, prothrombin, and edema as consistent global predictors, while counterfactual reasoning delineated clinically meaningful feature thresholds (probability 0.3–0.4). The interpretability synthesis enabled cross-validation of feature attributions across explanation paradigms, improving transparency and robustness. The integrated recommendation module generated individualized monitoring strategies and actionable insights.</div></div><div><h3>Conclusion</h3><div>CARE-Cirrhosis establishes a generalizable methodological approach for unifying predictive modeling, explainability, and clinical recommendation within a single, deployable framework. By demonstrating a reproducible process for multi-level interpretability integration, it advances the methodological scope of biomedical informatics beyond model development toward transparent, interpretable, and actionable decision-support systems applicable across clinical domains.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"4 1","pages":"Pages 109-125"},"PeriodicalIF":0.0,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147413024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}