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 2
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.

Reference url

Recent Posts

defunding scientific research
      

Defunding Scientific Research: Implications and Misconceptions in Gawande’s Analysis of Harvard Funding Cuts

🚨 What happens when scientific research funding is threatened?

In his thought-provoking article, Atul Gawande highlights the dire implications of proposed federal funding cuts to elite institutions like Harvard. He argues that such actions could devastate not just innovation, but also patient care and public health across the nation.

Explore the complexities of research funding and the potential ripple effects on America’s scientific landscape. Don’t miss out on these critical insights!

#SyenzaNews #HealthcareInnovation #HealthEconomics #MarketAccess

perioperative immunotherapy bladder cancer
       

FDA Approves Perioperative Immunotherapy for Bladder Cancer: A Breakthrough in MIBC Treatment

🚀 Are we witnessing a new era in bladder cancer treatment?

The FDA’s recent approval of durvalumab as the first perioperative immunotherapy for muscle-invasive bladder cancer (MIBC) could revolutionize outcomes for patients facing this formidable diagnosis. With significant improvements in event-free survival and overall survival over standard chemotherapy, this groundbreaking treatment offers new hope 🎉.

Curious about how this could shape the future of cancer care? Dive into the full article to uncover the potential impacts on clinical practice and health economics.

#SyenzaNews #oncology #HealthEconomics

value-based drug pricing
      

Optimizing Value-Based Drug Pricing in Japan with MARIE Framework

🔍 Are we pricing drugs based on true value?

The introduction of the MARIE framework in Japan revolutionizes value-based drug pricing by considering not just costs, but the actual benefits drugs provide to patients and society. This innovative approach significantly adjusts prices based on updated clinical data and allows for more equitable access to therapies.

Curious about how MARIE can reshape drug pricing and pharmaceutical innovation? Dive into the full article for insights!

#SyenzaNews #HealthEconomics #MarketAccess

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.

SPEAK WITH US

CORRESPONDENCE ADDRESS

1950 W. Corporate Way, Suite 95478
Anaheim, CA 92801, USA

© 2025 Syenza™. All rights reserved.