1
|
Laymouna M, Ma Y, Lessard D, Engler K, Therrien R, Schuster T, Vicente S, Achiche S, El Haj MN, Lemire B, Kawaiah A, Lebouché B. Needs-Assessment for an Artificial Intelligence-Based Chatbot for Pharmacists in HIV Care: Results from a Knowledge-Attitudes-Practices Survey. Healthcare (Basel) 2024; 12:1661. [PMID: 39201222 PMCID: PMC11353819 DOI: 10.3390/healthcare12161661] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2024] [Revised: 08/14/2024] [Accepted: 08/15/2024] [Indexed: 09/02/2024] Open
Abstract
BACKGROUND Pharmacists need up-to-date knowledge and decision-making support in HIV care. We aim to develop MARVIN-Pharma, an adapted artificial intelligence-based chatbot initially for people with HIV, to assist pharmacists in considering evidence-based needs. METHODS From December 2022 to December 2023, an online needs-assessment survey evaluated Québec pharmacists' knowledge, attitudes, involvement, and barriers relative to HIV care, alongside perceptions relevant to the usability of MARVIN-Pharma. Recruitment involved convenience and snowball sampling, targeting National HIV and Hepatitis Mentoring Program affiliates. RESULTS Forty-one pharmacists (28 community, 13 hospital-based) across 15 Québec municipalities participated. Participants perceived their HIV knowledge as moderate (M = 3.74/6). They held largely favorable attitudes towards providing HIV care (M = 4.02/6). They reported a "little" involvement in the delivery of HIV care services (M = 2.08/5), most often ART adherence counseling, refilling, and monitoring. The most common barriers reported to HIV care delivery were a lack of time, staff resources, clinical tools, and HIV information/training, with pharmacists at least somewhat agreeing that they experienced each (M ≥ 4.00/6). On average, MARVIN-Pharma's acceptability and compatibility were in the 'undecided' range (M = 4.34, M = 4.13/7, respectively), while pharmacists agreed to their self-efficacy to use online health services (M = 5.6/7). CONCLUSION MARVIN-Pharma might help address pharmacists' knowledge gaps and barriers to HIV treatment and care, but pharmacist engagement in the chatbot's development seems vital for its future uptake and usability.
Collapse
Affiliation(s)
- Moustafa Laymouna
- Department of Family Medicine, Faculty of Medicine and Health Sciences, McGill University, Montreal, QC H3S 1Z1, Canada; (M.L.)
- Centre for Outcomes Research and Evaluation, Research Institute of the McGill University Health Centre, Montreal, QC H4A 3S5, Canada
- Infectious Diseases and Immunity in Global Health Program, Research Institute of McGill University Health Centre, Montreal, QC H4A 3S5, Canada
| | - Yuanchao Ma
- Centre for Outcomes Research and Evaluation, Research Institute of the McGill University Health Centre, Montreal, QC H4A 3S5, Canada
- Infectious Diseases and Immunity in Global Health Program, Research Institute of McGill University Health Centre, Montreal, QC H4A 3S5, Canada
- Chronic Viral Illness Service, Division of Infectious Diseases, Department of Medicine, McGill University Health Centre, Montreal, QC H4A 3J1, Canada
- Department of Biomedical Engineering, Polytechnique Montréal, Montreal, QC H3T 1J4, Canada
| | - David Lessard
- Centre for Outcomes Research and Evaluation, Research Institute of the McGill University Health Centre, Montreal, QC H4A 3S5, Canada
- Infectious Diseases and Immunity in Global Health Program, Research Institute of McGill University Health Centre, Montreal, QC H4A 3S5, Canada
- Chronic Viral Illness Service, Division of Infectious Diseases, Department of Medicine, McGill University Health Centre, Montreal, QC H4A 3J1, Canada
| | - Kim Engler
- Centre for Outcomes Research and Evaluation, Research Institute of the McGill University Health Centre, Montreal, QC H4A 3S5, Canada
- Infectious Diseases and Immunity in Global Health Program, Research Institute of McGill University Health Centre, Montreal, QC H4A 3S5, Canada
| | - Rachel Therrien
- Department of Pharmacy and Chronic Viral Illness Service, Research Centre of the University of Montreal Hospital Centre, Montreal, QC H2X 0A9, Canada
| | - Tibor Schuster
- Department of Family Medicine, Faculty of Medicine and Health Sciences, McGill University, Montreal, QC H3S 1Z1, Canada; (M.L.)
| | - Serge Vicente
- Department of Family Medicine, Faculty of Medicine and Health Sciences, McGill University, Montreal, QC H3S 1Z1, Canada; (M.L.)
- Centre for Outcomes Research and Evaluation, Research Institute of the McGill University Health Centre, Montreal, QC H4A 3S5, Canada
- Infectious Diseases and Immunity in Global Health Program, Research Institute of McGill University Health Centre, Montreal, QC H4A 3S5, Canada
- Department of Mathematics and Statistics, University of Montreal, Montreal, QC H3T 1J4, Canada
| | - Sofiane Achiche
- Department of Biomedical Engineering, Polytechnique Montréal, Montreal, QC H3T 1J4, Canada
| | - Maria Nait El Haj
- Faculty of Pharmacy, University of Montreal, Montreal, QC H3C 3J7, Canada
| | - Benoît Lemire
- Chronic Viral Illness Service, Division of Infectious Diseases, Department of Medicine, McGill University Health Centre, Montreal, QC H4A 3J1, Canada
| | - Abdalwahab Kawaiah
- Centre for Outcomes Research and Evaluation, Research Institute of the McGill University Health Centre, Montreal, QC H4A 3S5, Canada
- Infectious Diseases and Immunity in Global Health Program, Research Institute of McGill University Health Centre, Montreal, QC H4A 3S5, Canada
- Chronic Viral Illness Service, Division of Infectious Diseases, Department of Medicine, McGill University Health Centre, Montreal, QC H4A 3J1, Canada
| | - Bertrand Lebouché
- Department of Family Medicine, Faculty of Medicine and Health Sciences, McGill University, Montreal, QC H3S 1Z1, Canada; (M.L.)
- Centre for Outcomes Research and Evaluation, Research Institute of the McGill University Health Centre, Montreal, QC H4A 3S5, Canada
- Infectious Diseases and Immunity in Global Health Program, Research Institute of McGill University Health Centre, Montreal, QC H4A 3S5, Canada
- Chronic Viral Illness Service, Division of Infectious Diseases, Department of Medicine, McGill University Health Centre, Montreal, QC H4A 3J1, Canada
| |
Collapse
|
2
|
Yao H, Wang L, Zhou X, Jia X, Xiang Q, Zhang W. Predicting the therapeutic efficacy of AIT for asthma using clinical characteristics, serum allergen detection metrics, and machine learning techniques. Comput Biol Med 2023; 166:107544. [PMID: 37866086 DOI: 10.1016/j.compbiomed.2023.107544] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2023] [Revised: 09/07/2023] [Accepted: 09/28/2023] [Indexed: 10/24/2023]
Abstract
Bronchial asthma is a prevalent non-communicable disease among children. The study collected clinical data from 390 children aged 4-17 years with asthma, with or without rhinitis, who received allergen immunotherapy (AIT). Combining these data, this paper proposed a predictive framework for the efficacy of mite subcutaneous immunotherapy in asthma based on machine learning techniques. Introducing the dispersed foraging strategy into the Salp Swarm Algorithm (SSA), a new improved algorithm named DFSSA is proposed. This algorithm effectively alleviates the imbalance between search speed and traversal caused by the fixed partitioning pattern in traditional SSA. Utilizing the fusion of boosting algorithm and kernel extreme learning machine, an AIT performance prediction model was established. To further investigate the effectiveness of the DFSSA-KELM model, this study conducted an auxiliary diagnostic experiment using the immunotherapy predictive medical data collected by the hospital. The findings indicate that selected indicators, such as blood basophil count, sIgE/tIgE (Der p) and sIgE/tIgE (Der f), play a crucial role in predicting treatment outcome. The classification results showed an accuracy of 87.18% and a sensitivity of 93.55%, indicating that the prediction model is an effective and accurate intelligent tool for evaluating the efficacy of AIT.
Collapse
Affiliation(s)
- Hao Yao
- Department of Pediatric Allergy and Immunology, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, 325027, China
| | - Lingya Wang
- Department of Pediatric Allergy and Immunology, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, 325027, China
| | - Xinyu Zhou
- Department of Pediatric Allergy and Immunology, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, 325027, China
| | - Xiaoxiao Jia
- Department of Pediatric Allergy and Immunology, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, 325027, China
| | - Qiangwei Xiang
- Department of Pediatric Allergy and Immunology, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, 325027, China.
| | - Weixi Zhang
- Department of Pediatric Allergy and Immunology, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, 325027, China.
| |
Collapse
|
3
|
Gilbert S, Fenech M, Hirsch M, Upadhyay S, Biasiucci A, Starlinger J. Algorithm Change Protocols in the Regulation of Adaptive Machine Learning-Based Medical Devices. J Med Internet Res 2021; 23:e30545. [PMID: 34697010 PMCID: PMC8579211 DOI: 10.2196/30545] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2021] [Revised: 08/23/2021] [Accepted: 09/22/2021] [Indexed: 01/29/2023] Open
Abstract
One of the greatest strengths of artificial intelligence (AI) and machine learning (ML) approaches in health care is that their performance can be continually improved based on updates from automated learning from data. However, health care ML models are currently essentially regulated under provisions that were developed for an earlier age of slowly updated medical devices—requiring major documentation reshape and revalidation with every major update of the model generated by the ML algorithm. This creates minor problems for models that will be retrained and updated only occasionally, but major problems for models that will learn from data in real time or near real time. Regulators have announced action plans for fundamental changes in regulatory approaches. In this Viewpoint, we examine the current regulatory frameworks and developments in this domain. The status quo and recent developments are reviewed, and we argue that these innovative approaches to health care need matching innovative approaches to regulation and that these approaches will bring benefits for patients. International perspectives from the World Health Organization, and the Food and Drug Administration’s proposed approach, based around oversight of tool developers’ quality management systems and defined algorithm change protocols, offer a much-needed paradigm shift, and strive for a balanced approach to enabling rapid improvements in health care through AI innovation while simultaneously ensuring patient safety. The draft European Union (EU) regulatory framework indicates similar approaches, but no detail has yet been provided on how algorithm change protocols will be implemented in the EU. We argue that detail must be provided, and we describe how this could be done in a manner that would allow the full benefits of AI/ML-based innovation for EU patients and health care systems to be realized.
Collapse
Affiliation(s)
- Stephen Gilbert
- Ada Health GmbH, Berlin, Germany.,Else Kröner-Fresenius Center for Digital Health, Faculty of Medicine Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
| | - Matthew Fenech
- Ada Health GmbH, Berlin, Germany.,Una Health GmbH, Berlin, Germany
| | - Martin Hirsch
- Ada Health GmbH, Berlin, Germany.,Institute for AI in Medicine, University Hospital of Giessen and Marburg, Marburg, Germany
| | | | - Andrea Biasiucci
- Laboratory for Investigative Neurophysiology, University Hospital Center and University of Lausanne, Lausanne, Switzerland.,confinis ag, Sursee, Switzerland
| | | |
Collapse
|