Pharmaceutical analysis of inpatient prescriptions: systematic observations of hospital pharmacists' practices in the early user-centered design phase (Preprint) DOI
Jesse Butruille, Natalina Cirnat,

Mariem Alaoui

et al.

Published: Sept. 4, 2024

BACKGROUND The healthcare sector's digital transformation has accelerated, yet adverse drug events (ADEs) continue to rise, posing significant clinical and economic challenges. Clinical Decision Support Systems (CDSS), particularly those related medication, are crucial for improving patient care, identifying Drug-Related Problems (DRPs) reducing ADEs. Hospital pharmacists play a key role in utilizing CDSS management safety. Human Factors Ergonomics (HFE) methods essential designing effective, human-centered CDSS. HFE involves three phases: exploration, design, evaluation, with exploration being critical often overlooked literature. For medication-related CDSS, understanding hospital pharmacists' tasks challenges is vital creating user-centered solutions. OBJECTIVE aim of this study explore the actual practices identify needs analyzing electronic prescriptions. This focuses on preliminary stage design pharmacist-centered METHODS involved observing 16 across five hospitals mainland France, including university hospital, two large general hospitals, smaller specialized clinic. Pharmacists were selected regardless expertise. observation method used systematic situ shadowing posture, following as they analyzed Researchers recorded activities, tools used, verbalizations, behaviors, interruptions, using an grid. Data analysis focused modeling cognitive work, categorizing activities by action type, specificity, information source. Sequential time data distance matrices employed generate hierarchical clustering similarity groups among analysis. Each group described its typical sequences covariates. RESULTS validated prescriptions 140 patients, averaging 5.48 minutes per patient. They spend 91% their searching rather than transmitting it. Most comes from list but it's spent Electronic Medical Record (EMR) that dominates at heart Pharmaceutical interventions most frequently transmitted last third sequence. pharmaceutical grouped into four clusters: A (22%): Interventionist extensive crossing various sources almost interventions. B (52%): common focusing EMR biology results. C (13%): Logistical analysis, pharmacy workflow medication circuit. D Quick, trivial analyses based exclusively CONCLUSIONS process complex multifaceted. detectives, accessing wealth order discriminate DRPs respond accordingly. also carry out different types which lead require solutions exploratory prerequisite meeting challenge support pharmacists.

Language: Английский

Barriers and Facilitators of Artificial Intelligence Adoption in Healthcare: A Scoping Review (Preprint) DOI Creative Commons
Masooma Hassan, André Kushniruk, Elizabeth M. Borycki

et al.

JMIR Human Factors, Journal Year: 2024, Volume and Issue: 11, P. e48633 - e48633

Published: June 12, 2024

Artificial intelligence (AI) use cases in health care are on the rise, with potential to improve operational efficiency and outcomes. However, translation of AI into practical, everyday has been limited, as its effectiveness relies successful implementation adoption by clinicians, patients, other stakeholders.

Language: Английский

Citations

25
Effectiveness of Artificial Intelligence (AI) in Clinical Decision Support Systems and Care Delivery DOI
Khaled Ouanes, Nesren Farhah

Journal of Medical Systems, Journal Year: 2024, Volume and Issue: 48(1)

Published: Aug. 12, 2024

Language: Английский

Citations

18
N-of-1 medicine DOI Open Access
Peter Wang, Qiao Ying Leong, Ni Yin Lau

et al.

Singapore Medical Journal, Journal Year: 2024, Volume and Issue: 65(3), P. 167 - 175

Published: March 1, 2024

Abstract The fields of precision and personalised medicine have led to promising advances in tailoring treatment individual patients. Examples include genome/molecular alteration-guided drug selection, single-patient gene therapy design synergy-based combination development, these approaches can yield substantially diverse recommendations. Therefore, it is important define each domain delineate their commonalities differences an effort develop novel clinical trial designs, streamline workflow rethink regulatory considerations, create value healthcare economics assessments, other factors. These segments are essential recognise the diversity within domains accelerate respective workflows towards practice-changing healthcare. To emphasise points, this article elaborates on concept digital health medicine-enabled N-of-1 medicine, which individualises regimen dosing using a patient’s own data. We will conclude with recommendations for consideration when developing based emerging digital-based platforms.

Language: Английский

Citations

4
Healthcare professionals’ perspectives on artificial intelligence in patient care: a systematic review of hindering and facilitating factors on different levels DOI Creative Commons
Dennis Henzler, Sebastian Schmidt, Ayca Koçar

et al.

BMC Health Services Research, Journal Year: 2025, Volume and Issue: 25(1)

Published: May 1, 2025

Language: Английский

Citations

0
Clinicians’ perspectives on the adoption and implementation of EMR-integrated clinical decision support tools in primary care DOI Creative Commons
Debora Goetz Goldberg, Tulay G. Soylu,

Carolyn Faith Hoffman

et al.

Digital Health, Journal Year: 2025, Volume and Issue: 11

Published: April 1, 2025

Objective Understand the perceptions of primary care clinicians on challenges, barriers, and successful strategies for implementing disseminating clinical decision support (CDS) tools in care. Methods Qualitative research involving in-depth interviews with 32 practicing a range settings across United States. Semi-structured were conducted between July 2021 September 2023. Results All participants reported using CDS patient care, high variability frequency use type used. Fewer described machine learning-based systems risk assessment predictive analytics. Most favorable toward enhanced if used along judgment preferences. Clinicians tremendous barriers to adoption implementation EMR-integrated tools, including clinician resistance, organizational approval, lack infrastructure resources. stressed importance communicating evidence effectiveness integrating existing EMR systems, having an easy-to-navigate interface. Strategies included champion, technical assistance, education training. Conclusions have potential be valuable assets treating patients could improve diagnostic accuracy, enhance personalized treatment plans, ultimately advance quality There are many concerns that should considered tool's effectiveness, data security privacy protocols, workflow integration, burden.

Language: Английский

Citations

0
Artificial intelligence-driven clinical decision support systems for early detection and precision therapy in oral cancer: a mini review DOI Creative Commons

Manoj Kumar Karuppan Perumal,

Remya Rajan Renuka,

Suresh Kumar

et al.

Frontiers in Oral Health, Journal Year: 2025, Volume and Issue: 6

Published: April 28, 2025

Oral cancer (OC) is a significant global health burden, with life-saving improvements in survival and outcomes being dependent on early diagnosis precise treatment planning. However, planning are predicated the synthesis of complicated information derived from clinical assessment, imaging, histopathology patient histories. Artificial intelligence-based decision support systems (AI-CDSS) provides viable solution that can be implemented via advanced methodologies for data analysis, better diagnostic prognostic evaluation. This review presents AI-CDSS as promising through comprehensive analysis. In addition, it examines current implementations facilitate OC detection, staging, personalized by processing multimodal machine learning, computer vision, natural language processing. These effectively interpret results, identify critical disease patterns (including stage, site, tumor dimensions, histopathologic grading, molecular profiles), construct profiles. approach allows reduction delays improved intervention outcomes. Moreover, also optimizes plans basis unique parameters, stages risk factors, providing therapy.

Language: Английский

Citations

0
Personalized dose selection for the first Waldenström macroglobulinemia patient on the PRECISE CURATE.AI trial DOI Creative Commons
Agata Blasiak, Lester W. J. Tan, Li Ming Chong

et al.

npj Digital Medicine, Journal Year: 2024, Volume and Issue: 7(1)

Published: Aug. 27, 2024

Abstract The digital revolution in healthcare, amplified by the COVID-19 pandemic and artificial intelligence (AI) advances, has led to a surge development of technologies. However, integrating health solutions, especially AI-based ones, rare diseases like Waldenström macroglobulinemia (WM) remains challenging due limited data, among other factors. CURATE.AI, clinical decision support system, offers an alternative big data approaches calibrating individual treatment profiles based on that individual’s alone. We present case study from PRECISE CURATE.AI trial with WM patient, where, over two years, provided dynamic Ibrutinib dose recommendations clinicians (users) aimed at achieving optimal IgM levels. An 80-year-old male newly diagnosed requiring anemia was recruited for CURATE.AI-based dosing Bruton tyrosine kinase inhibitor Ibrutinib. primary secondary outcome measures were focused scientific logistical feasibility. Preliminary results underscore platform’s potential enhancing user patient engagement, addition efficacy. Based two-year-long enrollment into CURATE.AI-augmented treatment, this showcases how AI-enabled tools can management diseases, emphasizing integration AI enhance personalized therapy.

Language: Английский

Citations

3
Artificial intelligence, medications, pharmacogenomics, and ethics DOI
Susanne B. Haga

Pharmacogenomics, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 12

Published: Nov. 15, 2024

Artificial Intelligence (AI) and Machine Learning (ML) are revolutionizing various scientific clinical disciplines including pharmacogenomics (PGx) by enabling the analysis of complex datasets development predictive models. The integration AI ML with PGx has potential to provide more precise, data-driven insights into new drug targets, efficacy, selection, risk adverse events. While significant effort develop validate these tools remain, ongoing advancements in technologies, coupled improvements data quality depth is anticipated drive transition practice delivery individualized treatments improved patient outcomes. successful AI-assisted will require careful consideration ethical, legal, social issues (ELSI) research practice. This paper explores intersection AI, highlighting current applications, ELSI privacy, oversight, provider knowledge acceptance, impact on patient-provider relationship roles.

Language: Английский

Citations

2
Pharmaceutical analysis of inpatient prescriptions: systematic observations of hospital pharmacists' practices in the early user-centered design phase (Preprint) DOI Creative Commons
Jesse Butruille, Natalina Cirnat,

Mariem Alaoui

et al.

JMIR Human Factors, Journal Year: 2024, Volume and Issue: 12, P. e65959 - e65959

Published: Nov. 25, 2024

Abstract Background The health care sector’s digital transformation has accelerated, yet adverse drug events continue to rise, posing significant clinical and economic challenges. Clinical decision support systems (CDSSs), particularly those related medication, are crucial for improving patient care, identifying drug-related problems, reducing events. Hospital pharmacists play a key role in using CDSSs management safety. Human factors ergonomics (HFE) methods essential designing effective, human-centered CDSSs. HFE involves 3 phases—exploration, design, evaluation—with exploration being critical often overlooked the literature. For medication-related CDSSs, understanding hospital pharmacists’ tasks challenges is vital creating user-centered solutions. Objective This study aimed explore actual practices identify needs of analyzing electronic prescriptions. focused on preliminary stage design pharmacist-centered CDSS. Methods involved observing 16 across 5 hospitals mainland France (a university hospital, 2 large general hospitals, smaller specialized clinic). Pharmacists were selected regardless expertise. observation method—systematic situ with shadowing posture—involved following as they analyzed Researchers recorded activities, tools used, verbalizations, behaviors, interruptions, an grid. Data analysis modeling cognitive work, categorizing activities by action type, specificity, information source. Sequential time data distance matrices used generate hierarchical clustering similarity groups among analyses. Each group was described its typical sequences covariates. Results In total, validated prescriptions 140 patients, averaging 5.48 minutes per patient. They spend 91% their searching rather than transmitting it. Most comes from list prescriptions, but it spent medical records (EMRs) that dominates at heart analysis. Pharmaceutical interventions most frequently transmitted last third sequence. pharmaceutical analyses grouped into 4 clusters: (cluster A, 22%) interventionist extensive crossing various sources almost systematic interventions; B, 52%) common focusing EMRs biology results; C, 13%) logistical analysis, pharmacy workflow medication circuit; D, quick, trivial based exclusively Conclusions process complex multifaceted. detectives, accessing wealth discriminate problems respond accordingly. also carry out different types which lead require solutions exploratory prerequisite meeting challenge pharmacists.

Language: Английский

Citations

0
Initial Investigations into Physician Acceptance of Medical AI: Examining Trust, Resistance, Perceived Job Insecurity, and Usage Intentions DOI Creative Commons
Chia‐Jung Chen,

Chung-Feng Liu

Studies in health technology and informatics, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 22, 2024

This study evaluated physicians’ attitudes towards medical AI across three Taiwanese hospitals, focusing on constructs of trust, resistance, job insecurity, and adoption willingness, with a survey based the Dual-factor Model yielding 282 responses 94% response rate. Results showed positive trust in AI, low resistance insecurity concerns, high willingness to adopt indicating favorable view as supportive tool rather than replacement. Key factors were identified regulatory standards, accuracy, workflow integration, result clarity, providing valuable insights for future development medicine.

Language: Английский

Citations

0