Background

Artificial intelligence (AI) and machine learning (ML) are poised to transform infectious disease testing. Uniquely, infectious disease testing is technologically diverse spaces in laboratory medicine, where multiple platforms and approaches may be required to support clinical decision-making. Despite advances in laboratory informatics, the vast array of infectious disease data is constrained by human analytical limitations. Machine learning can exploit multiple data streams, including but not limited to laboratory information and overcome human limitations to provide physicians with predictive and actionable results. As a quickly evolving area of computer science, laboratory professionals should become aware of AI/ML applications for infectious disease testing as more platforms are become commercially available.

Content

In this review we: (a) define both AI/ML, (b) provide an overview of common ML approaches used in laboratory medicine, (c) describe the current AI/ML landscape as it relates infectious disease testing, and (d) discuss the future evolution AI/ML for infectious disease testing in both laboratory and point-of-care applications.

Summary

The review provides an important educational overview of AI/ML technique in the context of infectious disease testing. This includes supervised ML approaches, which are frequently used in laboratory medicine applications including infectious diseases, such as COVID-19, sepsis, hepatitis, malaria, meningitis, Lyme disease, and tuberculosis. We also apply the concept of "data fusion" describing the future of laboratory testing where multiple data streams are integrated by AI/ML to provide actionable clinical knowledge.

Introduction

Vertebral endplates, innervated by the basivertebral nerve (BVN), are a source of chronic low back pain correlated with Modic changes. A randomized trial comparing BVN ablation to standard care (SC) recently reported results of an interim analysis. Here, we report the results of the full randomized trial, including the 3-month and 6-month between-arm comparisons, 12-month treatment arm results, and 6-month outcomes of BVN ablation in the former SC arm.

Methods

Prospective, open label, 1:1 randomized controlled trial of BVN ablation versus SC in 23 US sites with follow-up at 6 weeks, 3, 6, 9, and 12 months. SC patients were re-baselined and followed up for 6 months post BVN ablation. The primary endpoint was the between-arm comparison of mean Oswestry Disability Index (ODI) change from baseline. Secondary endpoints were Visual Analog Scale (VAS), Short Form (SF-36), EuroQual Group 5 Dimension 5-Level Quality of Life (EQ-5D-5L), responder rates, and rates of continued opioid use.

Results

140 were randomized. Results from BVN ablation (n=66) were superior to SC (n=74) at 3 months for the primary endpoint (mean ODI reduction, difference between arms of -20.3 (CI -25.9 to -14.7 points; p<0.001)), VAS pain improvement (difference of -2.5 cm between arms (CI -3.37 to -1.64, p<0.001)) and quality of life outcomes. At 12 months, basivertebral ablation demonstrated a 25.7±18.5 point reduction in mean ODI (p<0.001), and a 3.8±2.7 cm VAS reduction (p<0.001) from baseline, with 64% demonstrating ≥50% reduction and 29% pain free. Similarly, the former SC patients who elected BVN ablation (92%) demonstrated a 25.9±15.5 point mean ODI reduction (p<0.001) from baseline. The proportion of opioid use did not change in either group (p=0.56).

Discussion/conclusion

BVN ablation demonstrates significant improvements in pain and function over SC, with treatment results sustained through 12 months in patients with chronic low back pain of vertebrogenic origin.