1
|
Vithlani J, Hawksworth C, Elvidge J, Ayiku L, Dawoud D. Economic evaluations of artificial intelligence-based healthcare interventions: a systematic literature review of best practices in their conduct and reporting. Front Pharmacol 2023; 14:1220950. [PMID: 37693892 PMCID: PMC10486896 DOI: 10.3389/fphar.2023.1220950] [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: 05/11/2023] [Accepted: 07/25/2023] [Indexed: 09/12/2023] Open
Abstract
Objectives: Health economic evaluations (HEEs) help healthcare decision makers understand the value of new technologies. Artificial intelligence (AI) is increasingly being used in healthcare interventions. We sought to review the conduct and reporting of published HEEs for AI-based health interventions. Methods: We conducted a systematic literature review with a 15-month search window (April 2021 to June 2022) on 17th June 2022 to identify HEEs of AI health interventions and update a previous review. Records were identified from 3 databases (Medline, Embase, and Cochrane Central). Two reviewers screened papers against predefined study selection criteria. Data were extracted from included studies using prespecified data extraction tables. Included studies were quality assessed using the National Institute for Health and Care Excellence (NICE) checklist. Results were synthesized narratively. Results: A total of 21 studies were included. The most common type of AI intervention was automated image analysis (9/21, 43%) mainly used for screening or diagnosis in general medicine and oncology. Nearly all were cost-utility (10/21, 48%) or cost-effectiveness analyses (8/21, 38%) that took a healthcare system or payer perspective. Decision-analytic models were used in 16/21 (76%) studies, mostly Markov models and decision trees. Three (3/16, 19%) used a short-term decision tree followed by a longer-term Markov component. Thirteen studies (13/21, 62%) reported the AI intervention to be cost effective or dominant. Limitations tended to result from the input data, authorship conflicts of interest, and a lack of transparent reporting, especially regarding the AI nature of the intervention. Conclusion: Published HEEs of AI-based health interventions are rapidly increasing in number. Despite the potentially innovative nature of AI, most have used traditional methods like Markov models or decision trees. Most attempted to assess the impact on quality of life to present the cost per QALY gained. However, studies have not been comprehensively reported. Specific reporting standards for the economic evaluation of AI interventions would help improve transparency and promote their usefulness for decision making. This is fundamental for reimbursement decisions, which in turn will generate the necessary data to develop flexible models better suited to capturing the potentially dynamic nature of AI interventions.
Collapse
Affiliation(s)
- Jai Vithlani
- National Institute for Health and Care Excellence, London, United Kingdom
| | - Claire Hawksworth
- National Institute for Health and Care Excellence, Manchester, United Kingdom
| | - Jamie Elvidge
- National Institute for Health and Care Excellence, Manchester, United Kingdom
| | - Lynda Ayiku
- National Institute for Health and Care Excellence, Manchester, United Kingdom
| | - Dalia Dawoud
- National Institute for Health and Care Excellence, London, United Kingdom
- Faculty of Pharmacy, Cairo University, Cairo, Egypt
| |
Collapse
|
2
|
Farrell SF, Kho PF, Lundberg M, Campos AI, Rentería ME, de Zoete RMJ, Sterling M, Ngo TT, Cuéllar-Partida G. A Shared Genetic Signature for Common Chronic Pain Conditions and its Impact on Biopsychosocial Traits. THE JOURNAL OF PAIN 2023; 24:369-386. [PMID: 36252619 DOI: 10.1016/j.jpain.2022.10.005] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/10/2022] [Revised: 09/28/2022] [Accepted: 10/06/2022] [Indexed: 11/11/2022]
Abstract
The multiple comorbidities & dimensions of chronic pain present a formidable challenge in disentangling its aetiology. Here, we performed genome-wide association studies of 8 chronic pain types using UK Biobank data (N =4,037-79,089 cases; N = 239,125 controls), followed by bivariate linkage disequilibrium-score regression and latent causal variable analyses to determine (respectively) their genetic correlations and genetic causal proportion (GCP) parameters with 1,492 other complex traits. We report evidence of a shared genetic signature across chronic pain types as their genetic correlations and GCP directions were broadly consistent across an array of biopsychosocial traits. Across 5,942 significant genetic correlations, 570 trait pairs could be explained by a causal association (|GCP| >0.6; 5% false discovery rate), including 82 traits affected by pain while 410 contributed to an increased risk of chronic pain (cf. 78 with a decreased risk) such as certain somatic pathologies (eg, musculoskeletal), psychiatric traits (eg, depression), socioeconomic factors (eg, occupation) and medical comorbidities (eg, cardiovascular disease). This data-driven phenome-wide association analysis has demonstrated a novel and efficient strategy for identifying genetically supported risk & protective traits to enhance the design of interventional trials targeting underlying causal factors and accelerate the development of more effective treatments with broader clinical utility. PERSPECTIVE: Through large-scale phenome-wide association analyses of >1,400 biopsychosocial traits, this article provides evidence for a shared genetic signature across 8 common chronic pain types. It lays the foundation for further translational studies focused on identifying causal genetic variants and pathophysiological pathways to develop novel diagnostic & therapeutic technologies and strategies.
Collapse
Affiliation(s)
- Scott F Farrell
- RECOVER Injury Research Centre, The University of Queensland, Herston, Queensland, Australia; NHMRC Centre of Research Excellence: Better Health Outcomes for Compensable Injury, The University of Queensland, Herston, Queensland, Australia; Tess Cramond Pain & Research Centre, Royal Brisbane & Women's Hospital, Herston, Queensland, Australia.
| | - Pik-Fang Kho
- Division of Cardiovascular Medicine, Department of Medicine, Stanford University School of Medicine, Stanford, California; Molecular Cancer Epidemiology Laboratory, Population Health Program, QIMR Berghofer Medical Research Institute, Herston, Queensland, Australia; School of Biomedical Sciences, Queensland University of Technology, Brisbane, Queensland, Australia
| | - Mischa Lundberg
- UQ Diamantina Institute, The University of Queensland & Translational Research Institute, Woolloongabba, Queensland, Australia; Transformational Bioinformatics, CSIRO Health & Biosecurity, North Ryde, New South Wales, Australia
| | - Adrián I Campos
- Institute for Molecular Bioscience, The University of Queensland, St Lucia, Queensland, Australia; Genetic Epidemiology Laboratory, Mental Health & Neuroscience Program, QIMR Berghofer Medical Research Institute, Herston, Queensland, Australia
| | - Miguel E Rentería
- Genetic Epidemiology Laboratory, Mental Health & Neuroscience Program, QIMR Berghofer Medical Research Institute, Herston, Queensland, Australia
| | - Rutger M J de Zoete
- School of Allied Health Science and Practice, The University of Adelaide, Adelaide, South Australia, Australia
| | - Michele Sterling
- RECOVER Injury Research Centre, The University of Queensland, Herston, Queensland, Australia; NHMRC Centre of Research Excellence: Better Health Outcomes for Compensable Injury, The University of Queensland, Herston, Queensland, Australia
| | - Trung Thanh Ngo
- RECOVER Injury Research Centre, The University of Queensland, Herston, Queensland, Australia
| | - Gabriel Cuéllar-Partida
- UQ Diamantina Institute, The University of Queensland & Translational Research Institute, Woolloongabba, Queensland, Australia
| |
Collapse
|