Evaluating the Clinical Utility of Artificial Intelligence Assistance and its Explanation on Glioma Grading Task
Bibliographic record
Abstract
Abstract Background As a fast-advancing technology, artificial intelligence (AI) has considerable potential to assist physicians in various clinical tasks from disease identification to lesion segmentation. Despite much research, AI has not yet been applied to neurooncological imaging in a clinically meaningful way. To bridge the clinical implementation gap of AI in neuro-oncological settings, we conducted a clinical user-based evaluation, analogous to the phase II clinical trial, to evaluate the utility of AI for diagnostic predictions and the value of AI explanations on the glioma grading task. Method Using the publicly-available BraTS dataset, we trained an AI model of 88.0% accuracy on the glioma grading task. We selected the SmoothGrad explainable AI Weina Jin and Mostafa Fatehi are co-first authors. algorithm based on the computational evaluation regarding explanation truthfulness among a candidate of 16 commonly-used algorithms. SmoothGrad could explain the AI model’s prediction using a heatmap overlaid on the MRI to highlight important regions for AI prediction. The evaluation is an online survey wherein the AI prediction and explanation are embedded. Each of the 35 neurosurgeon participants read 25 brain MRI scans of patients with gliomas, and gave their judgment on the glioma grading without and with the assistance of AI’s prediction and explanation. Result Compared to the average accuracy of 82.5 ± 8.7% when physicians perform the task alone, physicians’ task performance increased to 87.7 ± 7.3% with statistical significance ( p -value = 0.002) when assisted by AI prediction, and remained at almost the same level of 88.5 ± 7.0% ( p -value = 0.35) with the additional AI explanation assistance. Conclusion The evaluation shows the clinical utility of AI to assist physicians on the glioma grading task. It also reveals the limitations of applying existing AI explanation techniques in clinical settings. Key points Phase II evaluation with 35 neurosurgeons on the clinical utility of AI and its explanation AI prediction assistance improved physicians’ performance on the glioma grading task Additional AI explanation assistance did not yield a performance boost Importance of the study This study is the first phase II AI clinical evaluation in neuro-oncology. Evaluating AI is a prerequisite for its clinical deployment. The four phases of AI clinical evaluation are analogous to the four phases of clinical trials. Prior works that apply AI in neurooncology utilize phase I algorithmic evaluation, which do not reflect how AI can be used in clinical settings to support physician decision making. To bridge the research gap, we conducted the first clinical evaluation to assess the joint neurosurgeon-AI task performance. The evaluation also includes AI explanation as an indispensable feature for AI clinical deployment. Results from quantitative and qualitative data analysis are presented for a detailed examination of the clinical utility of AI and its explanation.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".