In spite of impressive advances, the biggest unmet needs for metastatic TNBC is the lack of good targeted treatments and the heavy reliance on chemotherapy, or chemotherapy-based approaches. It is the most malignant subtype of breast cancer with a poor prognosis. There is a need for new therapies, but it is difficult to find drugs with clinical benefits. TNBC includes many signaling pathways and genes that regulate malignant transformation, prevention of apoptosis, cause drug resistance, metastasis, cell growth, survival, proliferation and migration (EGFR, VEGF, PI3K, mTOR, AKT, K-RAS, etc.). Many targets and agents are involved in the current treatment of TNBC, to mention a few: immune cells, tumor stroma, cell surface and intracellular receptors, pathways, DNA damage response, cell cycle checkpoint, germline mutations in BRCA1/2 (gBRCA1/2), etc. Information about TNBC is included in voluminous non multimodal and multimodal data. AI is adept at analyzing immense complex interactions between a large number of variables in vast datasets to drive actionable insights, resulting in the discovery of new drugs and robust biomarkers. What adds to the complexity of the treatment is its dependence on TNBC subtypes and the stage of the disease. 

The hype around AI has led to the impression that AI is an easy solution to all problems. This is a fallacy. The effectiveness of an AI solution depends on the nature of the problem and the required accuracy.