Postoperative delirium is a common complication after colorectal cancer surgery that hinders recovery. This observational study hypothesizes that a simple, practical risk tool can be developed by combining preoperative clinical conditions, blood tests (including the TyG index), and clinical subtypes identified via clustering analysis. Investigators will enroll patients undergoing elective colorectal cancer surgery, assess delirium twice daily for 7 days postoperatively using the 3D-CAM, and finalize the scoring scale. It will help doctors quickly identify high-risk patients for targeted care to improve recovery. Only data will be collected; patients receive standard clinical treatment.

This observational study aims to address the unmet clinical need for a simple, colorectal cancer-specific tool to predict postoperative delirium (POD), a prevalent complication linked to prolonged hospitalization and compromised recovery.

Eligible patients will undergo preoperative data collection, including demographic details, comorbidities, and laboratory tests (e.g., triglycerides, glucose for TyG index calculation, inflammatory and metabolic markers). Unsupervised K-means clustering will be applied to these multidimensional data to identify latent clinical subtypes, capturing complex interactions between metabolic status, inflammatory responses, and clinical characteristics that may influence POD risk.

Postoperatively, standardized POD assessment will be conducted twice daily for 7 days using the validated 3D-CAM tool, ensuring consistent identification of POD cases. No experimental interventions will be implemented-all participants receive routine preoperative evaluation, surgical care, and postoperative management per clinical guidelines.

Statistical analyses will first screen independent POD predictors via univariate and multivariate logistic regression. A scoring scale will then be developed by assigning weights to core predictors (clustering-derived subtypes, TyG index, and key clinical factors) based on their predictive strength (odds ratios). The scale's performance will be validated for discriminative ability (AUC) and calibration to ensure reliability in clinical practice.

The study's primary output is a user-friendly risk scoring tool that enables clinicians to rapidly assess POD risk preoperatively, facilitating targeted preventive strategies and improving patient outcomes without adding complexity to clinical workflows.

Inclusion Criteria:

• Histologically confirmed colorectal cancer (colon or rectal cancer) via - preoperative or postoperative pathology;
• Scheduled for elective surgical intervention (open or laparoscopic resection);
• Preoperative Mini Mental State Examination (MMSE) score ≥18 (no pre-existing cognitive impairment);
• Able to provide written informed consent (self or legal representative);
• Complete preoperative clinical and laboratory data.

Exclusion Criteria:

• Postoperative pathology confirmed non-malignant tumor;
• Age ≥90 years old;
• Presence of visual, cognitive, language, or speech impairment; or history of neuropsychiatric diseases (dementia, Parkinson's disease, cerebrovascular accidents);
• No preoperative cognitive function assessment or MMSE score <18;
• Emergency surgery or palliative surgery (non-curative resection);
• Postoperative admission to intensive care unit (ICU) (excluded due to different monitoring and intervention patterns);
• Missing key data >5% (e.g., incomplete TyG index calculation, missing clustering analysis variables);
• Refusal to participate or inability to complete 7-day postoperative follow-up.

The study population will be selected from patients who present to the First Hospital of Lanzhou University, and are scheduled for elective surgical resection of histologically confirmed colorectal cancer**. Eligible participants will be consecutively recruited during the study period, with selection strictly adhering to predefined inclusion and exclusion criteria to ensure homogeneity and relevance to the research objective of developing a colorectal cancer-specific postoperative delirium risk prediction tool.