Aim: Cemented hemiarthroplasty has been recently shown to be an effective treatment in patients with an intracapsular hip fracture. However, it remains unclear which patient groups benefit most from the use of cemented hemiarthroplasty. Knowledge about treatment effect heterogeneity is crucial for decision makers to target interventions towards specific subgroups that have the greatest benefit. We evaluate heterogeneity in the treatment effect of cemented hemiarthroplasty in the WHiTE 5 multicentre, randomized, controlled trial conducted in England and Wales using a machine learning approach. Causal Forest (CF) analysis was used to compare cemented with modern, uncemented hemiarthroplasty in patients 60 years of age or older with an intracapsular hip fracture. Methods: We used CF to estimate subgroup- and individual-level treatment effects to compare cemented with modern, uncemented hemiarthroplasty. We used the EuroQol Group 5-Dimension (EQ-5D) multi-attribute utility scores as the main outcome measure at 1 month, 4 and 12 months follow up. Results: Our analysis revealed a complex landscape of response to cemented hemiarthroplasty over a 12-month period. Findings suggest greater variability in treatment effects at the 1-month mark than at subsequent follow-up periods, with particular regard to subgroups based on age. Results showed that conclusions regarding heterogeneity of effects with respect to baseline characteristics, including age, health status, and lifestyle factors like alcohol consumption depend on the timepoint considered. However, in almost all cases the overall effect estimates lies within the confidence intervals for subgroups estimates. Conclusion: With regard to cemented versus uncemented hemiarthroplasty for hip fracture, treatment effects appear to be homogeneous by subgroup and timepoint. This study highlights the potential of causal forest analysis to investigate different treatment effects in subgroups of participants and across different timepoints.