Evaluating AI in Healthcare: Implementing Approaches
By Sumona Bose
March 7, 2024
Introduction
Artificial intelligence (AI) holds great potential in healthcare by enhancing clinical decision-making and patient outcomes. However, a significant gap exists between the development of AI models and their successful integration into clinical practice. Despite the proliferation of AI-based clinical decision support systems (AICDSS), only a meager 2% of these models progress beyond the prototyping stage, leaving the actual clinical impact largely unexplored.
Evaluating Clinical Value through Rigorous Trials
The evaluation of AICDSS through randomised controlled trials (RCTs) stands as a critical step in determining their true clinical value. While some RCTs have been conducted, their outcomes paint a nuanced picture. Although these trials showcase promising statistical performance of AI, nearly half of them fail to demonstrate improved patient outcomes. This discrepancy underscores the complexity of assessing AI solely based on quantitative metrics like accuracy. This may not capture the practical utility of these systems in real-world healthcare settings. Table 1 unpacks the definitions associated with interpreting the patient outcomes. This helps clinicians and researchers shift from the arbitrariness that hinders real-world settings.
Reported in N (%)
Implementation outcomea
Clinical explanation
Implementation stage
RCTs (N = 64)
Guidelinesb (N = 5)
Appropriateness
Is the AI compatible with the clinical workflow and is it useful?
Early
5 (8)
0 (0)
Acceptability
Is the AI acceptable, agreeable, or satisfactory for the users?
Ongoing
10 (16)
0 (0)
Feasibility
Can the AI be successfully used as intended by the manufacturer?
Early
16 (25)
0 (0)
Adoption
Do the users express the initial decision, or action to try or employ the AI?
Ongoing
6 (9)
0 (0)
Fidelity
Is the AI implemented as intended by the manufacturer?
Ongoing
31 (48)
0 (0)
Implementation cost
What is the cost impact of implementing the AI system?
Late
4 (6)
0 (0)
Penetration
Has the AI been adopted by all groups of trained users?
Late
0 (0)
0 (0)
Sustainability
Is the AI maintained within ongoing clinical operations over time?
Late
1 (2)
0 (0)
Table 1: AI in RCTs, Definitions of implementation outcomes were adapted from the taxonomy of implementation outcomes by Proctor et al (2011).
The Need for a Holistic Evaluation Approach
A comprehensive understanding of AI’s role in clinical practice necessitates a multi-faceted evaluation strategy. Current guidelines like Developmental and Exploratory Clinical Investigations of DEcision support systems driven by Artificial Intelligence (DECIDE-AI) and Consolidated Standards of Reporting Trials–Artificial Intelligence (CONSORT-AI), fall short in providing robust measures for assessing AI implementation success. To address this gap, a mixed-methods evaluation approach, proves invaluable in dissecting the various dimensions of AICDSS implementation.
Bridging the Gap in Implementation Evaluation
Despite the increasing focus on RCTs evaluating AICDSS in clinical settings, a gap exists in the comprehensive evaluation of implementation outcomes. While metrics like ‘fidelity’ are commonly reported using quantitative measures, aspects such as ‘acceptability’ and ‘appropriateness’ that demand qualitative scrutiny are often overlooked. This imbalance underscores the need for a more holistic approach towards evaluating the implementation of AICDSS, encompassing factors beyond statistical performance. Figure 1 reiterates the comprehensive value of integrating implementation outcomes in AI in healthcare, revealing an innovative future in the field.
Figure 1: a In the current situation, AI-CDSS, are clinically deployed, after going through multiple preclinical validations (e.g., external and temporal algorithm validation) to assess their clinical utility and effectiveness. b To enhance comprehension of factors that contributed to successful implementation or failure at the bedside, implementation outcomes should be systematically integrated in future clinical trials evaluating AICDSS in real-world clinical settings. *Implementation outcomes as described by Proctor et al.
Conclusion
While the efficacy of AICDSS in healthcare settings is crucial, understanding the contextual nuances is imperative. Enhanced systematic reporting of implementation outcomes alongside effectiveness metrics can bridge the existing gap in comprehensively assessing the impact of clinical AI. Embracing an inclusive evaluation framework will not only validate the effectiveness of AICDSS but also shed light on the intricate interplay between AI technology and healthcare delivery.
💡 *What happens when a country decides to withdraw from global health organizations?*
Argentina’s President Javier Milei has made the bold move to withdraw from the WHO, citing significant disagreements over health management during the pandemic. This decision raises questions about national sovereignty, cooperation, and the future of global health initiatives. Dive into the implications of Argentina’s stance and what it means for international health governance.
💉 Ready to protect our future generations from cervical cancer?
The Gauteng HPV vaccination campaign aims to vaccinate grade 5, 6, and 7 girls against the virus that causes most cervical cancers. By leveraging a single-dose regimen, this initiative not only enhances access to life-saving vaccines but also strives to meet ambitious global health targets.
Explore how this campaign is reshaping health outcomes in South Africa and why parental consent is key to its success.
🌍 What if a single vaccine could significantly change the landscape of pneumococcal disease prevention in adults?
The European Medicines Agency has just recommended Merck’s Capvaxive, an innovative 21-valent pneumococcal conjugate vaccine! With robust data from multiple phase 3 trials, this potential approval marks a pivotal step in the fight against invasive Streptococcus pneumoniae infections in the EU. Look into how Capvaxive could enhance public health outcomes and offer extensive serotype coverage.
#SyenzaNews #pharmaceuticals #healthcarepolicy
When you partner with Syenza, it’s like a Nuclear Fusion.
Our expertise are combined with yours, and we contribute clinical expertise and advanced degrees in
health policy, health economics, systems analysis, public finance, business, and project management.
You’ll also feel our high-impact global and local perspectives with cultural intelligence.