The field of clinical prediction and decision support is moving towards more transparent and explainable models. Recent developments have focused on incorporating knowledge graphs and chain-of-thought frameworks to generate clinically grounded and temporally consistent reasoning for disease prediction and outcome forecasting. These approaches have shown significant improvements in performance and have the potential to provide more accurate and trustworthy predictions for patient-level decision making. Notably, the integration of medical consensus guidelines into large language models has enabled the development of more faithful and transparent explanations. The use of process mining techniques has also been explored for adaptive identification and modeling of clinical pathways, allowing for more precise and standardized patient treatment. Noteworthy papers include: Knowledge Graph Augmented Large Language Models for Next-Visit Disease Prediction, which introduces a knowledge graph-guided chain-of-thought framework for disease prediction. COPE: Chain-Of-Thought Prediction Engine for Open-Source Large Language Model Based Stroke Outcome Prediction from Clinical Notes, which develops a reasoning-enhanced large language model framework for predicting stroke outcomes. Training and Evaluation of Guideline-Based Medical Reasoning in LLMs, which teaches large language models to follow medical consensus guidelines for improved explanation and prediction.