Search

Frailty has been shown to adversely impact outcomes in a number of surgical disciplines. In head and neck reconstructive surgery, frailty may represent a significant risk factor in predicting post-operative outcomes due to the common characteristics of the patient population undergoing these procedures.To summarize the available evidence about frailty as a predictor of post-operative complications, length of hospital stay and quality of life in patients undergoing head and neck reconstructive surgery.Systematic Review.The study protocol was registered with PROSPERO, registration CRD42022302899. Methodology was in keeping with the PRISMA Guidelines for Systematic Reviews. MEDLINE, SCOPUS, EMBASE, Web of Science and CENTRAL were the databases searched. Qualitative synthesis of the included studies was carried out, and quality assessment was performed.Nine studies that reported data on 10,457 patients undergoing reconstruction of the head and neck were included in the review. A number of different tools were used to assess frailty, with the modified frailty index being the most frequently used. In total, 8 studies reported increased rates of complications in patients with increased levels of frailty, irrespective of the frailty tool used, with varied levels of statistical significance across the studies.An association is observed between increased rates of perioperative complications and increased levels of frailty in patients undergoing head and neck reconstruction. Frailty tools may represent a useful method to risk stratify patients undergoing reconstructive head and neck surgery.

The study used machine learning to predict The American Spinal Injury Association Impairment Scale (AIS) scores for newly injured spinal cord injury patients at hospital discharge time from hospital admission data. Additionally, machine learning was used to analyze the best model for feature importance to validate the criticality of the AIS score and highlight relevant demographic details. The data used for training machine learning models was from the National Spinal Cord Injury Statistical Center (NSCISC) database of U.S. spinal cord injury patient details. Eighteen real features were used from 417 provided features, which mapped to 53 machine learning features after processing. Eight models were tuned on the dataset to predict AIS scores, and Shapely analysis was performed to extract the most important of the 53 features. Patients within the NSCISC database who sustained injuries were between 1972 and 2016 after data cleaning (n = 20,790). Outcomes were test set multiclass accuracy and aggregated Shapely score magnitudes. Ridge Classifier was the best performer with 73.6% test set accuracy. AIS scores and neurologic category at the time of admission were the best predictors of recovery. Demographically, features were less important, but age, sex, marital status, and race stood out. AIS scores on admission are highly predictive of patient outcomes when combined with patient demographic data. Promising results in terms of predicting recovery were seen, and Shapely analysis allowed for the machine learning model to be probed as a whole, giving insight into overall feature trends.