Risk Factors for Postoperative Hemorrhage Following Thyroid Surgery: Results of a Case-Control Study and Development...

Background: Postoperative haemorrhage (POH) is a rare but potentially life-threatening complication of thyroid surgery, with an incidence of 0.6-4%. Early identification of patients at increased risk is critical to guide perioperative management, especially in the context of evolving surgical practices and increasing demand for outpatient procedures. Methods: We conducted an explorative, retrospective, single-centre case-control study using a prospectively documented quality assurance dataset including 9158 thyroidectomies (2012-2019). POH requiring revision (n = 104) were compared to matched controls (n = 416; 1:4 ratio), matched by age, sex, type of procedure (uni- vs. bilateral), and year of surgery. Univariate analysis (Chi-square and t-test) was used to identify possible associations between candidate risk factors and POH. To supplement classical univariate statistics, we applied a Random Forest machine learning model to assess the relative importance of 25 potential variables derived from the clinical dataset based on previous literature. It was also planned to use the results to develop a proposal for a quantitative risk score, system, assigning weights to each factor (3, 1, or 0 points) depending on their relative importance for predicting POH. Patients were subsequently categorized into risk classes (low, intermediate, high) based on total point scores and reclassified. Results: High-impact risk factors confirmed in univariate analysis and Random Forest modelling included reoperative thyroidectomy, smoking, relevant comorbidities, medical treatment for hyperthyroidism and advanced age and were weighted with 3 points. Moderately associated variables such as regular alcohol consumption, Graves' disease, hyperthyroid state at surgery, duration of the procedure and thyroid weight were weighted 1 point. Factors with negligible predictive value (e.g., BMI, gender, ASA classification) were assigned 0 points. The average score among patients without haemorrhage was 5.21, whereas the average score among patients with haemorrhage was 7.61. Within the matched study cohort, patients with POH accumulated higher risk scores than controls, suggesting potential discriminatory capacity. These findings formed the basis for the development of an exploratory three-stage 'traffic light' risk stratification model that requires external validation. Conclusions: A simple, interpretable point-based scoring system derived from a large matched case-control cohort identified key predictors of postoperative hemorrhage (POH) after thyroid surgery and enabled risk stratification within the study population. By combining conventional statistical methods with machine-learning approaches, the score may support individualized perioperative monitoring, surgical planning, and institutional resource allocation. However, because the model was developed using a 1:4 matched case-control design, it should be considered an exploratory risk stratification tool rather than a fully validated prediction model, and it does not directly estimate absolute POH risk or population incidence. External and prospective validation in large, representative multicentre cohorts (e.g., StuDoQ, HEDOS) is ongoing and will be required to establish calibration, generalizability, and clinical utility.