Objective To determine if sufficient nurse staffing reduced in‐hospital fractures in acute care hospitals. Data Sources/Study Setting The Japanese Diagnosis Procedure Combination inpatient (DPC) database from July 2010 to March 2014 linked with the Surveys for Medical Institutions. Study Design We conducted a retrospective cohort study to examine the association of inpatient nurse‐to‐occupied bed ratio (NBR) with in‐hospital fractures. Multivariable logistic regression with generalized estimating equations was performed, adjusting for patient characteristics and hospital characteristics. Data Collection/Extraction Methods We identified 770,373 patients aged 50 years or older who underwent planned major surgery for some forms of cancer or cardiovascular diseases. We used ICD‐10 codes and postoperative procedure codes to identify patients with in‐hospital fractures. Hospital characteristics were obtained from the “Survey of Medical Institutions and Hospital Report” and “Annual Report for Functions of Medical Institutions.” Principal Findings Overall, 662 (0.09 percent) in‐hospital fractures were identified. Logistic regression analysis showed that the proportion of in‐hospital fractures in the group with the highest NBR was significantly lower than that in the group with the lowest NBR (adjusted odd ratios, 0.67; 95 percent confidence interval, 0.44–0.99; p = .048). Conclusions Sufficient nurse staffing may be important to reduce postsurgical in‐hospital fractures in acute care hospitals.