1 December 2024 in Health Technology Assessment
Background: Hybrid closed-loop systems are a new class of technology to manage type 1 diabetes mellitus. The system includes a combination of real-time continuous glucose monitoring from a continuous glucose monitoring device and a control algorithm to direct insulin delivery through an insulin pump. Evidence suggests that such technologies have the potential to improve the lives of people with type 1 diabetes mellitus and their families. Aim: The aim of this appraisal was to assess the clinical effectiveness and cost-effectiveness of hybrid closed-loop systems for managing glucose in people who have type 1 diabetes mellitus and are having difficulty managing their condition despite prior use of at least one of the following technologies: continuous subcutaneous insulin infusion, real-time continuous glucose monitoring or flash glucose monitoring (intermittently scanned continuous glucose monitoring). Methods: A systematic review of clinical effectiveness and cost-effectiveness evidence following predefined inclusion criteria informed by the aim of this review. An independent economic assessment using iQVIA CDM to model cost-effectiveness. Results: The clinical evidence identified 12 randomised controlled trials that compared hybrid closed loop with continuous subcutaneous insulin infusion + continuous glucose monitoring. Hybrid closed-loop arm of randomised controlled trials achieved improvement in glycated haemoglobin per cent [hybrid closed loop decreased glycated haemoglobin per cent by 0.28 (95% confidence interval −0.34 to −0.21), increased per cent of time in range (between 3.9 and 10.0 mmol/l) with a MD of 8.6 (95% confidence interval 7.03 to 10.22), and significantly decreased time in range (per cent above 10.0 mmol/l) with a MD of −7.2 (95% confidence interval −8.89 to −5.51), but did not significantly affect per cent of time below range (< 3.9 mmol/l)]. Comparator arms showed improvements, but these were smaller than in the hybrid closed-loop arm. Outcomes were superior in the hybrid closed-loop arm compared with the comparator arm. The cost-effectiveness search identified six studies that were included in the systematic review. Studies reported subjective cost-effectiveness that was influenced by the willingness-to-pay thresholds. Economic evaluation showed that the published model validation papers suggest that an earlier version of the iQVIA CDM tended to overestimate the incidences of the complications of diabetes, this being particularly important for severe visual loss and end-stage renal disease. Overall survival’s medium-term modelling appeared good, but there was uncertainty about its longer-term modelling. Costs provided by the National Health Service Supply Chain suggest that hybrid closed loop is around an annual average of £1500 more expensive than continuous subcutaneous insulin infusion + continuous glucose monitoring, this being a pooled comparator of 90% continuous subcutaneous insulin infusion + intermittently scanned continuous glucose monitoring and 10% continuous subcutaneous insulin infusion + real-time continuous glucose monitoring due to clinical effectiveness estimates not being differentiated by continuous glucose monitoring type. This net cost may increase by around a further £500 for some systems. The Evidence Assessment Group base case applies the estimate of −0.29% glycated haemoglobin for hybrid closed loop relative to continuous subcutaneous insulin infusion + continuous glucose monitoring. There was no direct evidence of an effect on symptomatic or severe hypoglycaemia events, and therefore the Evidence Assessment Group does not include these in its base case. The change in glycated haemoglobin results in a gain in undiscounted life expectancy of 0.458 years and a gain of 0.160 quality-adjusted life-years. Net lifetime treatment costs are £31,185, with reduced complications leading to a net total cost of £28,628. The cost-effectiveness estimate is £179,000 per quality-adjusted life-year. Conclusions: Randomised controlled trials of hybrid closed-loop interventions in comparison with continuous subcutaneous insulin infusion + continuous glucose monitoring achieved a statistically significant improvement in glycated haemoglobin per cent in time in range between 3.9 and 10 mmol/l, and in hyperglycaemic levels. Study registration: This study is registered as PROSPERO CRD42021248512. Funding: This award was funded by the National Institute for Health and Care Research (NIHR) Evidence Synthesis programme (NIHR award ref: NIHR133547) and is published in full in Health Technology Assessment; Vol. 28, No. 80. See the NIHR Funding and Awards website for further award information.
1 May 2025 in Health Technology Assessment
Background: Lung cancer is one of the most common types of cancer and the leading cause of cancer death in the United Kingdom. Artificial intelligence-based software has been developed to reduce the number of missed or misdiagnosed lung nodules on computed tomography images. Objective: To assess the accuracy, clinical effectiveness and cost-effectiveness of using software with artificial intelligence-derived algorithms to assist in the detection and analysis of lung nodules in computed tomography scans of the chest compared with unassisted reading. Design: Systematic review and de novo cost-effectiveness analysis. Methods: Searches were undertaken from 2012 to January 2022. Company submissions were accepted until 31 August 2022. Study quality was assessed using the revised tool for the quality assessment of diagnostic accuracy studies (QUADAS-2), the extension to QUADAS-2 for assessing risk of bias in comparative accuracy studies (QUADAS-C) and the COnsensus-based Standards for the selection of health status Measurement INstruments (COSMIN) checklist. Outcomes were synthesised narratively. Two decision trees were used for cost-effectiveness: (1) a simple decision tree for the detection of actionable nodules and (2) a decision tree reflecting the full clinical pathways for people undergoing chest computed tomography scans. Models estimated incremental cost-effectiveness ratios, cost per correct detection of an actionable nodule, and cost per cancer detected and treated. We undertook scenario and sensitivity analyses. Results: Twenty-seven studies were included. All were rated as being at high risk of bias. Twenty-four of the included studies used retrospective data sets. Seventeen compared readers with and without artificial intelligence software. One reported prospective screening experiences before and after artificial intelligence software implementation. The remaining studies either evaluated stand-alone artificial intelligence or provided only non-comparative evidence. (1) Artificial intelligence assistance generally improved the detection of any nodules compared with unaided reading (three studies; average per-person sensitivity 0.43–0.68 for unaided and 0.79–0.99 for artificial intelligence-assisted reading), with similar or lower specificity (three studies; 0.77–1.00 for unaided and 0.81–0.97 for artificial intelligence-assisted reading). Nodule diameters were similar or significantly larger with semiautomatic measurements than with manual measurements. Intra-reader and inter-reader agreement in nodule size measurement and in risk classification generally improved with artificial intelligence assistance or were comparable to those with unaided reading. However, the effect on measurement accuracy is unclear. (2) Radiologist reading time generally decreased with artificial intelligence assistance in research settings. (3) Artificial intelligence assistance tended to increase allocated risk categories as defined by clinical guidelines. (4) No relevant clinical effectiveness and cost-effectiveness studies were identified. (5) The de novo cost-effectiveness analysis suggested that for symptomatic and incidental populations, artificial intelligence-assisted computed tomography image analysis dominated the unaided radiologist in cost per correct detection of an actionable nodule. However, when relevant costs and quality-adjusted life-years from the full clinical pathway were included, artificial intelligence-assisted computed tomography reading was dominated by the unaided reader. For screening, artificial intelligence-assisted computed tomography image analysis was cost-effective in the base case and all sensitivity and scenario analyses. Limitations: Due to the heterogeneity, sparseness, low quality and low applicability of the clinical effectiveness evidence and the major challenges in linking test accuracy evidence to clinical and economic outcomes, the findings presented here are highly uncertain and provide indicators/frameworks for future assessment. Conclusions: Artificial intelligence-assisted analysis of computed tomography scan images may reduce variability of and improve consistency in the measurement and clinical management of lung nodules. Artificial intelligence may increase nodule and cancer detection but may also increase the number of patients undergoing computed tomography surveillance unnecessarily. No direct comparative evidence was found, and nor was any direct evidence found on clinical outcomes and cost-effectiveness. Artificial intelligence-assisted image analysis may be cost-effective in screening for lung cancer but not for symptomatic populations. However, reliable estimates of cost-effectiveness cannot be obtained with current evidence. Study registration: This study is registered as PROSPERO CRD42021298449. Funding: This award was funded by the National Institute for Health and Care Research (NIHR) Evidence Synthesis programme (NIHR award ref: NIHR135325) and is published in full in Health Technology Assessment; Vol. 29, No. 14. See the NIHR Funding and Awards website for further award information.
1 January 2024 in BJR|Artificial Intelligence
Objectives: Accurate measurement of lung nodules is pivotal to lung cancer detection and management. Nodule size forms the main basis of risk categorization in existing guidelines. However, measurements can be highly variable between manual readers. This article explores the impact of potentially improved nodule size measurement assisted by generic artificial intelligence (AI)-derived software on clinical management compared with manual measurement. Methods: The simulation study created a baseline cohort of people with lung nodules, guided by nodule size distributions reported in the literature. Precision and accuracy were simulated to emulate measurement of nodule size by radiologists with and without the assistance of AI-derived software and by the software alone. Nodule growth was modelled over a 4-year time frame, allowing evaluation of management strategies based on existing clinical guidelines. Results: Measurement assisted by AI-derived software increased cancer detection compared to an unassisted radiologist for a combined solid and sub-solid nodule population (62.5% vs 61.4%). AI-assisted measurement also correctly identified more benign nodules (95.8% vs 95.4%); however, it was associated with over an additional month of surveillance on average (5.12 vs 3.95 months). On average, with AI assistance people with cancer are diagnosed faster, and people without cancer are monitored longer. Conclusions: In this simulation, the potential benefits of improved accuracy and precision associated with AI-based diameter measurement is associated with additional monitoring of non-cancerous nodules. AI may offer additional benefits not captured in this simulation, and it is important to generate data supporting these, and adjust guidelines as necessary. Advances in knowledge: This article shows the effects of greater measurement accuracy associated with AI assistance compared with unassisted measurement.
15 October 2026 in PharmacoEconomics