Read AI × medicine research, better.
Tatakoto decodes scientific publications on artificial intelligence applied to health. Transformers for cancer detection, foundation models in medical imaging, LLMs in clinical reasoning. Each article tells what the study found, what it doesn't say, and what changes.
GPT-4 in radiology: why the format of an LLM's explanation changes physicians' diagnostic accuracy
Decryption of Spitzer et al.'s 2026 npj Digital Medicine paper: a randomized trial with 101 radiologists comparing three formats of GPT-4 explanation. Chain-of-thought adds 12.2 percentage points of accuracy, while differential diagnosis induces automation bias. Implications for the clinical deployment of LLMs.
Mirai in mammography at a safety-net hospital: what changes when AI risk stratification is prospectively deployed
Critical analysis of the npj Digital Medicine 2026 paper on the prospective deployment of Mirai at Zuckerberg San Francisco General. Expedited workflow for high-risk-flagged patients, 99% reduction in diagnostic delays, and what it really changes in a safety-net setting.
GigaPath in digital pathology: what changes when a foundation model is trained on 1.3 billion tiles
Critical analysis of the Nature 2024 paper on Prov-GigaPath, a transformer foundation model for digital pathology. Architecture, data, performance on 26 cancer benchmarks, and what it really changes for diagnosis.