Smoking is a predictor of complications in all types of surgery: a machine learning-based big data study.

BACKGROUND: Machine learning algorithms are promising tools for smoking status classification in big patient data sets. Smoking is a risk factor for postoperative complications in major surgery. Whether this applies to all surgery is unknown. The aims of this retrospective cohort study were to develop a machine learning algorithm for clinical record-based smoking status classification and to determine whether smoking and former smoking predict complications in all surgery types. METHODS: All surgeries performed in a Finnish hospital district from 1 January 2015 to 31 December 2019 were analysed. Exclusion criteria were age below 16 years, unknown smoking status, and unknown ASA class. A machine learning algorithm was developed for smoking status classification. The primary outcome was 90-day overall postoperative complications in all surgeries. Secondary outcomes were 90-day overall complications in specialties with over 10 000 surgeries and critical complications in all surgeries. RESULTS: The machine learning algorithm had precisions of 0.958 for current smokers, 0.974 for ex-smokers, and 0.95 for never-smokers. The sample included 158 638 surgeries. In adjusted logistic regression analyses, smokers had increased odds of overall complications (odds ratio 1.17; 95 per cent c.i. 1.14 to 1.20) and critical complications (odds ratio 1.21; 95 per cent c.i. 1.14 to 1.29). Corresponding odds ratios of ex-smokers were 1.09 (95 per cent c.i. 1.06 to 1.13) and 1.09 (95 per cent c.i. 1.02 to 1.17). Smokers had increased odds of overall complications in all specialties with over 10 000 surgeries. ASA class was the most important complication predictor. CONCLUSION: Machine learning algorithms are feasible for smoking status classification in big surgical data sets. Current and former smoking predict complications in all surgery types.

Periprosthetic Femoral Fracture Is a Leading Cause of Early Revision With Taper-Slip Stems in Primary Total Hip Arthroplasty: An Analysis of 2765 Total Hip Arthroplasties From a High-Volume Hospital.

BACKGROUND: In 2016, the CPT stem replaced the Exeter stem as the main cemented stem at our institution. We assessed the prevalence of revision for periprosthetic femoral fracture (PFF) in patients operated on with either CPT or Exeter stem and compared the risk for revision between these stems. METHODS: Primary total hip arthroplasties either performed in 2012-2015 with Exeter stem (n = 1443) or in 2017-2018 with CPT stem (n = 1322) were included. The prevalence of revision for PFF was compared. The Kaplan-Meier estimated survivorships were calculated for the 2 stem designs. The risk for revision was analyzed using the Cox proportional hazard regression model. RESULTS: At 2 years, PFF was the most common reason for revision in the study population (1.3% prevalence, comprising 35% of all revisions). Moreover, 1.6% (95% confidence interval [CI] 1.0-2.4) of the CPT and 1.0% (95% CI 0.6-1.6) of the Exeter stems had been revised due to PFF. The 3-year Kaplan-Meier probability estimates for all-cause revision were 4.8% for the CPT (95% CI 3.6-6.0) and 3.3% for the Exeter stem (95% CI 2.3-4.3). The hazard ratio for revision due to any reason was 1.1 (95% CI 0.3-3.8) during the first 2 weeks, and 1.8 (95% CI 1.2-2.7, P = .006) from 2 weeks onwards for the CPT compared with the Exeter stem. CONCLUSION: The considerable number of PFF revisions with taper-slip stems, especially with CPT stems, is a matter of concern. Alternative cemented stems should be considered in patients at high risk for PFF.

Increased risk for dislocation after introduction of the Continuum cup system: lessons learnt from a cohort of 1,381 THRs after 1-year follow-up.

Background and purpose - The introduction of new total hip replacements (THRs) is known to be associated with an increased risk for complications. On completion of a competitive procurement process, a new uncemented cup system was introduced into general use at our institution in 2016. We launched this study after the introduction to assess (1) the incidence of early dislocations of the old (Pinnacle) and the new (Continuum) cup systems, and (2) whether the cup design would affect the risk for dislocation.Patients and methods - We assessed the incidence of dislocations after 1,381 primary THRs performed at our institution during 2016. Also, the effect of the cup system (Pinnacle, Continuum with neutral liner, Continuum with elevated rim liner) on dislocation rates was analyzed using a multivariable regression model.Results - 47 (3.4%) early dislocations were identified. The incidence of dislocations was 1.3% for the Pinnacle, 5.1% for the Continuum with neutral liner, and 1.2% for the Continuum with elevated rim liner. The Continuum with neutral liner was found to have an increased risk for dislocations compared with the Pinnacle (aOR 5, 95% CI 1.4-17). However, when an elevated rim liner was used with the Continuum, the risk for dislocation between the Continuum and the Pinnacle was similar.Interpretation - Our results emphasize the need for both careful consideration before the introduction of new implants and the systematic monitoring of early outcomes thereafter. The elevated rim liner should be preferred for use with the Continuum cup because of the poor coverage of the neutral liner that may result in dislocations.