Machine learning models to predict length of stay and discharge destination in complex head and neck surgery

Predicting reoperation and readmission for head and neck free flap patients using machine learning

BACKGROUND

To develop machine learning (ML) models predicting unplanned readmission and reoperation among patients undergoing free flap reconstruction for head and neck (HN) surgery.

METHODS

Data were extracted from the 2012-2019 NSQIP database. eXtreme Gradient Boosting (XGBoost) was used to develop ML models predicting 30-day readmission and reoperation based on demographic and perioperative factors. Models were validated using 2019 data and evaluated.

RESULTS

Four-hundred and sixty-six (10.7%) of 4333 included patients were readmitted within 30 days of initial surgery. The ML model demonstrated 82% accuracy, 63% sensitivity, 85% specificity, and AUC of 0.78. Nine-hundred and four (18.3%) of 4931 patients underwent reoperation within 30 days of index surgery. The ML model demonstrated 62% accuracy, 51% sensitivity, 64% specificity, and AUC of 0.58.

CONCLUSION

XGBoost was used to predict 30-day readmission and reoperation for HN free flap patients. Findings may be used to assist clinicians and patients in shared decision-making and improve data collection in future database iterations.

Length of Stay Prediction Models for Oral Cancer Surgery: Machine Learning, Statistical and ACS-NSQIP

OBJECTIVE

Accurate prediction of hospital length of stay (LOS) following surgical management of oral cavity cancer (OCC) may be associated with improved patient counseling, hospital resource utilization and cost. The objective of this study was to compare the performance of statistical models, a machine learning (ML) model, and The American College of Surgeons National Surgical Quality Improvement Program's (ACS-NSQIP) calculator in predicting LOS following surgery for OCC.

MATERIALS AND METHODS

A retrospective multicenter database study was performed at two major academic head and neck cancer centers. Patients with OCC who underwent major free flap reconstructive surgery between January 2008 and June 2019 surgery were selected. Data were pooled and split into training and validation datasets. Statistical and ML models were developed, and performance was evaluated by comparing predicted and actual LOS using correlation coefficient values and percent accuracy.

RESULTS

Totally 837 patients were selected with mean patient age being 62.5 ± 11.7 [SD] years and 67% being male. The ML model demonstrated the best accuracy (validation correlation 0.48, 4-day accuracy 70%), compared with the statistical models: multivariate analysis (0.45, 67%) and least absolute shrinkage and selection operator (0.42, 70%). All were superior to the ACS-NSQIP calculator's performance (0.23, 59%).

CONCLUSION

We developed statistical and ML models that predicted LOS following major free flap reconstructive surgery for OCC. Our models demonstrated superior predictive performance to the ACS-NSQIP calculator. The ML model identified several novel predictors of LOS. These models must be validated in other institutions before being used in clinical practice.

LEVEL OF EVIDENCE

3 Laryngoscope, 134:3664-3672, 2024.

The efficacy of the National Surgical Quality Improvement Program surgical risk calculator in head and neck surgery: A meta-analysis

BACKGROUND

The National Surgical Quality Improvement Program surgical risk calculator (SRC) estimates the risk for postoperative complications. This meta-analysis assesses the efficacy of the SRC in the field of head and neck surgery.

METHODS

A systematic review identified studies comparing the SRC's predictions to observed outcomes following head and neck surgeries. Predictive accuracy was assessed using receiver operating characteristic curves (AUCs) and Brier scoring.

RESULTS

Nine studies totaling 1774 patients were included. The SRC underpredicted the risk of all outcomes (including any complication [observed (ob) = 35.9%, predicted (pr) = 21.8%] and serious complication [ob = 28.7%, pr = 17.0%]) except mortality (ob = 0.37%, pr = 1.55%). The observed length of stay was more than twice the predicted length (p < 0.02). Discrimination was acceptable for postoperative pneumonia (AUC = 0.778) and urinary tract infection (AUC = 0.782) only. Predictive accuracy was low for all outcomes (Brier scores ≥0.01) and comparable for patients with and without free-flap reconstructions.

CONCLUSION

The SRC is an ineffective instrument for predicting outcomes in head and neck surgery.

Artificial intelligence in head and neck surgery: Potential applications and future perspectives

Artificial intelligence (AI) has the potential to improve the surgical treatment of patients with head and neck cancer. AI algorithms can analyse a wide range of data, including images, voice, molecular expression and raw clinical data. In the field of oncology, there are numerous AI practical applications, including diagnostics and treatment. AI can also develop predictive models to assess prognosis, overall survival, the likelihood of occult metastases, risk of complications and hospital length of stay.

An introduction to machine learning and generative artificial intelligence for otolaryngologists-head and neck surgeons: a narrative review

PURPOSE

Despite the robust expansion of research surrounding artificial intelligence (AI) and machine learning (ML) and their applications to medicine, these methodologies often remain opaque and inaccessible to many otolaryngologists. Especially, with the increasing ubiquity of large-language models (LLMs), such as ChatGPT and their potential implementation in clinical practice, clinicians may benefit from a baseline understanding of some aspects of AI. In this narrative review, we seek to clarify underlying concepts, illustrate applications to otolaryngology, and highlight future directions and limitations of these tools.

METHODS

Recent literature regarding AI principles and otolaryngologic applications of ML and LLMs was reviewed via search in PubMed and Google Scholar.

RESULTS

Significant recent strides have been made in otolaryngology research utilizing AI and ML, across all subspecialties, including neurotology, head and neck oncology, laryngology, rhinology, and sleep surgery. Potential applications suggested by recent publications include screening and diagnosis, predictive tools, clinical decision support, and clinical workflow improvement via LLMs. Ongoing concerns regarding AI in medicine include ethical concerns around bias and data sharing, as well as the "black box" problem and limitations in explainability.

CONCLUSIONS

Potential implementations of AI in otolaryngology are rapidly expanding. While implementation in clinical practice remains theoretical for most of these tools, their potential power to influence the practice of otolaryngology is substantial.

LEVEL OF EVIDENCE: 4

Association Between Metabolic Syndrome and Outcomes in Complex Head and Neck Surgery

OBJECTIVES

We aim to evaluate the impact of MetS on the short-term postoperative outcomes of complex head and neck surgery patients.

METHODS

This is a retrospective cohort analysis of the 2005 to 2017 National Surgical Quality Improvement Program (NSQIP) database. NSQIP database was queried for 30-day outcomes of patients undergoing complex head and neck surgeries, defined as laryngectomy or mucosal resection followed by free tissue transfer, similar to prior NSQIP studies. Patients with hypertension, diabetes, and body mass index (BMI) >30 kg/m2 were defined as having MetS. Adverse events were defined as experiencing readmission, reoperation, surgical/medical complications, or mortality.

RESULTS

A total of 2764 patients (27.0% female) with a mean age of 62.0 ± 11.7 years were included. Patients with MetS (n = 108, 3.9%) were more likely to be female (P = .017) and have high ASA classification (P = .030). On univariate analysis, patients with MetS were more likely to require reoperation (25.9% vs 16.7%, P = .013) and experience medical complications (26.9% vs 15.4% P = .001) or any adverse events (61.1% vs 48.7%, P = .011) compared to patients without MetS. On multivariate logistic regression after adjusting for age, sex, race, ASA classification, and complex head and neck surgery type, MetS was an independent predictor of medical complications (odds ratio 2.34, 95% CI 1.28-4.27, P = .006).

CONCLUSION

Patients with MetS undergoing complex head and neck surgery are at increased risk of experiencing medical complications. Identifying patients with MetS can therefore aid surgeons in preoperative risk assessment and help improve postoperative management.

LEVEL OF EVIDENCE

N/A.

Development and validation of a prediction model for the prolonged length of stay in Chinese patients with lower extremity atherosclerotic disease: a retrospective study

OBJECTIVES

This study aims to develop and internally validate a prediction model, which takes account of multivariable and comprehensive factors to predict the prolonged length of stay (LOS) in patients with lower extremity atherosclerotic disease (LEAD).

DESIGN

This is a retrospective study.

SETTING

China.

PARTICIPANTS, PRIMARY AND SECONDARY OUTCOMES

Data of 1694 patients with LEAD from a retrospective cohort study between January 2014 and November 2021 were analysed. We selected nine variables and created the prediction model using the least absolute shrinkage and selection operator (LASSO) regression model after dividing the dataset into training and test sets in a 7:3 ratio. Prediction model performance was evaluated by calibration, discrimination and Hosmer-Lemeshow test. The effectiveness of clinical utility was estimated using decision curve analysis.

RESULTS

LASSO regression analysis identified age, gender, systolic blood pressure, Fontaine classification, lesion site, surgery, C reactive protein, prothrombin time international normalised ratio and fibrinogen as significant predictors for predicting prolonged LOS in patients with LEAD. In the training set, the prediction model showed good discrimination using a 500-bootstrap analysis and good calibration with an area under the receiver operating characteristic of 0.750. The Hosmer-Lemeshow goodness of fit test for the training set had a p value of 0.354. The decision curve analysis showed that using the prediction model both in training and tests contributes to clinical value.

CONCLUSION

Our prediction model is a valuable tool using easily and routinely obtained clinical variables that could be used to predict prolonged LOS in patients with LEAD and help to better manage these patients in routine clinical practice.

Using Machine Learning to Predict Operating Room Case Duration: A Case Study in Otolaryngology

OBJECTIVE

Optimizing operating room (OR) efficiency depends on accurate case duration estimates. Machine learning (ML) methods have been used to predict OR case durations in other subspecialties. We hypothesize that ML methods improve projected case lengths over existing non-ML techniques for otolaryngology-head and neck surgery cases.

METHODS

Deidentified patient information from otolaryngology surgical cases at 1 academic institution were reviewed from 2016 to 2020. Variables collected included patient, surgeon, procedure, and facility data known preoperatively so as to capture all realistic contributors. Available case data were divided into a training and testing data set. Several ML algorithms were evaluated based on best performance of predicted case duration when compared to actual case duration. Performance of all models was compared by the average root mean squared error and mean absolute error (MAE).

RESULTS

In total, 50,888 otolaryngology surgical cases were evaluated with an average case duration of 98.3 ± 86.9 minutes. Most cases were general otolaryngology (n = 16,620). Case features closely associated with OR duration included procedure performed, surgeon, subspecialty of case, and postoperative destination of the patient. The best-performing ML models were CatBoost and XGBoost, which reduced operative time MAE by 9.6 minutes and 8.5 minutes compared to current methods, respectively.

DISCUSSION

The incorporation of other easily identifiable features beyond procedure performed and surgeon meaningfully improved our operative duration prediction accuracy. CatBoost provided the best-performing ML model.

IMPLICATIONS FOR PRACTICE

ML algorithms to predict OR case time duration in otolaryngology can improve case duration accuracy and result in financial benefit.

Factors Impacting Discharge Destination Following Head and Neck Microvascular Reconstruction

OBJECTIVE

Determine which variables impact postoperative discharge destination following head and neck microvascular free flap reconstruction.

STUDY DESIGN

Retrospective review of prospectively collected databases.

METHODS

Consecutive patients undergoing head and neck microvascular free flap reconstruction between January 2010 and December 2019 (n = 1972) were included. Preoperative, operative and postoperative variables were correlated with discharge destination (home, skilled nursing facility [SNF], rehabilitation facility, death).

RESULTS

The mean age of patients discharged home was lower (60 SD ± 13, n = 1450) compared to those discharged to an SNF (68 SD ± 14, n = 168) or a rehabilitation facility (71 SD ± 14, n = 200; p < 0.0001). Operative duration greater than 10 h correlated with a higher percentage of patients being discharged to a rehabilitation or SNF (25% vs. 15%; p < 0.001). Patients were less likely to be discharged home if they had a known history of cardiac disease (71% vs. 82%; p < 0.0001). Patients were less likely to be discharged home if they experienced alcohol withdrawal (67% vs. 80%; p = 0.006), thromboembolism (59% vs. 80%; p = 0.001), a pulmonary complication (46% vs. 81%; p < 0.0001), a cardiac complication (46% vs. 80%; p < 0.0001), or a cerebral vascular event (25% vs. 80%; p < 0.0001). There was no correlation between discharge destination and occurrence of postoperative wound infection, salivary fistula, partial tissue necrosis or free flap failure. Thirty-day readmission rates were similar when stratified by discharge destination.

CONCLUSION

There was no correlation with the anatomic site, free flap donor selection, or free flap survival and discharge destination. Patient age, operative duration and occurrence of a medical complication postoperatively did correlate with discharge destination.

LEVEL OF EVIDENCE

4 Laryngoscope, 133:95-104, 2023.

Machine Learning Refinement of the NSQIP Risk Calculator: Who Survives the "Hail Mary" Case?

BACKGROUND

The American College of Surgeons (ACS) NSQIP risk calculator helps guide operative decision making. In patients with significant surgical risk, it may be unclear whether to proceed with "Hail Mary"-type interventions. To refine predictions, a local interpretable model-agnostic explanations machine (LIME) learning algorithm was explored to determine weighted patient-specific factors' contribution to mortality.

STUDY DESIGN

The ACS-NSQIP database was queried for all surgical patients with mortality probability greater than 50% between 2012 and 2019. Preoperative factors (n = 38) were evaluated using stepwise logistic regression; 26 significant factors were used in gradient boosted machine (GBM) modeling. Data were divided into training and testing sets, and model performance was substantiated with 10-fold cross validation. LIME provided individual subject mortality. The GBM-trained model was interpolated to LIME, and predictions were made using the test dataset.

RESULTS

There were 6,483 deaths (53%) among 12,248 admissions. GBM modeling displayed good performance (area under the curve = 0.65, 95% CI 0.636-0.671). The top 5 factors (% contribution) to mortality included: septic shock (27%), elevated International Normalized Ratio (22%), ventilator-dependence (14%), thrombocytopenia (14%), and elevated serum creatinine (5%). LIME modeling subset personalized patients by factors and weights on survival. In the entire cohort, mortality positive predictive value with 2 factor combinations was 53.5% (specificity 0.713), 3 combinations 64.2% (specificity 0.835), 4 combinations 72.1% (specificity 0.943), and all 5 combinations 77.9% (specificity 0.993). Conversely, mortality positive predictive value fell to 34% in the absence of 4 factors.

CONCLUSIONS

Through the application of machine learning algorithms (GBM and LIME), our model individualized predicted mortality and contributing factors with substantial ACS-NSQIP predicted mortality. USE of machine learning techniques may better inform operative decisions and family conversations in cases of significant surgical risk.