Artificial intelligence in medical imaging: switching from radiographic pathological data to clinically meaningful endpoints

Abstract

Artificial intelligence (AI) is a disruptive technology that involves the use of computerised algorithms to dissect complicated data. Among the most promising clinical applications of AI is diagnostic imaging, and mounting attention is being directed at establishing and fine-tuning its performance to facilitate detection and quantification of a wide array of clinical conditions. Investigations leveraging computer-aided diagnostics have shown excellent accuracy, sensitivity, and specificity for the detection of small radiographic abnormalities, with the potential to improve public health. However, outcome assessment in AI imaging studies is commonly defined by lesion detection while ignoring the type and biological aggressiveness of a lesion, which might create a skewed representation of AI's performance. Moreover, the use of non-patient-focused radiographic and pathological endpoints might enhance the estimated sensitivity at the expense of increasing false positives and possible overdiagnosis as a result of identifying minor changes that might reflect subclinical or indolent disease. We argue for refinement of AI imaging studies via consistent selection of clinically meaningful endpoints such as survival, symptoms, and need for treatment.

Artificial intelligence in medical imaging practice in Africa: a qualitative content analysis study of radiographers’ perspectives

“…Healthcare is quickly evolving, and current technological developments are centred largely on the increasing integration of complex computerised algorithms into equipment modalities [ 1 – 3 ]. Artificial intelligence (AI) is a key component of these complex algorithms and is currently applied innovatively in healthcare because of its reported advantages and the potential to improve patient care [ 2 , 4 ].…”

Randomized Controlled Trials in Medical AI A Methodological Critique

“…However, relying on a surrogate endpoint may backfire. A particular worry is that the involvement of AI systems leads to overtreatment (Oren, Gersh and Bhatt 2020). While an AI system may spot tumours more accurately than even expert clinicians, these previously overlooked tumours may be clinically irrelevant.…”

“…Most existing studies are retrospective and performed outside of clinical environments (Topol 2020). Moreover, outcomes used to evaluate AI performance tend to be only surrogates for meaningful clinical endpoints (Oren, Gersh and Bhatt 2020). Finally, only a handful of 1 Joint first authorship.…”

The Role of AI in Cervical Cancer Screening

“…The contemporary artificial intelligence techniques such as machine learning applications were widely used in medicine and achieved the substantial success, particularly in radiology, in the recent years [1,2]. Most of the technologies to support AI in pathology are still in development phase or are at the state of an observational study [3].…”