Healthcare systems worldwide generate vast amounts of data from many different sources. Although of high complexity for a human being, it is essential to determine the patterns and minor variations in the genomic, radiological, laboratory, or clinical data that reliably differentiate phenotypes or allow high predictive accuracy in health-related tasks. Convolutional neural networks (CNN) are increasingly applied to image data for various tasks. Its use for non-imaging data becomes feasible through different modern machine learning techniques, converting non-imaging data into images before inputting them into the CNN model. Considering also that healthcare providers do not solely use one data modality for their decisions, this approach opens the door for multi-input/mixed data models which use a combination of patient information, such as genomic, radiological, and clinical data, to train a hybrid deep learning model. Thus, this reflects the main characteristic of artificial intelligence: simulating natural human behavior. The present review focuses on key advances in machine and deep learning, allowing for multi-perspective pattern recognition across the entire information set of patients in spine surgery. This is the first review of artificial intelligence focusing on hybrid models for deep learning applications in spine surgery, to the best of our knowledge. This is especially interesting as future tools are unlikely to use solely one data modality. The techniques discussed could become important in establishing a new approach to decision-making in spine surgery based on three fundamental pillars: (1) patient-specific, (2) artificial intelligence-driven, (3) integrating multimodal data. The findings reveal promising research that already took place to develop multi-input mixed-data hybrid decision-supporting models. Their implementation in spine surgery may hence be only a matter of time.

Background: Decompression of the lumbar spine is one of the most common procedures performed in spine surgery. Hospital length of stay (LOS) is a clinically relevant metric used to assess surgical success, patient outcomes, and socioeconomic impact. This study aimed to investigate a variety of machine learning and deep learning algorithms to reliably predict whether a patient undergoing decompression of lumbar spinal stenosis will experience a prolonged LOS. Methods: Patients undergoing treatment for lumbar spinal stenosis with microsurgical and full-endoscopic decompression were selected within this retrospective monocentric cohort study. Prolonged LOS was defined as an LOS greater than or equal to the 75th percentile of the cohort (normal versus prolonged stay; binary classification task). Unsupervised learning with K-means clustering was used to find clusters in the data. Hospital stay classes were predicted with logistic regression, RandomForest classifier, stochastic gradient descent (SGD) classifier, K-nearest neighbors, Decision Tree classifier, Gaussian Naive Bayes (GaussianNB), support vector machines (SVM), a custom-made convolutional neural network (CNN), multilayer perceptron artificial neural network (MLP), and radial basis function neural network (RBNN) in Python. Prediction accuracy and area under the curve (AUC) were calculated. Feature importance analysis was utilized to find the most important predictors. Further, we developed a decision tree based on the Chi-square automatic interaction detection (CHAID) algorithm to investigate cut-offs of predictors for clinical decision-making. Results: 236 patients and 14 feature variables were included. K-means clustering separated data into two clusters distinguishing the data into two patient risk characteristic groups. The algorithms reached AUCs between 67.5% and 87.3% for the classification of LOS classes. Feature importance analysis of deep learning algorithms indicated that operation time was the most important feature in predicting LOS. A decision tree based on CHAID could predict 84.7% of the cases. Conclusions: Machine learning and deep learning algorithms can predict whether patients will experience an increased LOS following lumbar decompression surgery. Therefore, medical resources can be more appropriately allocated to patients who are at risk of prolonged LOS.

The integrity of the talus is crucial for the physiologic function of the feet. The present study sought to summarize the available evidence on clinical outcomes and complications following conservative and surgical treatment of talar fractures. We systematically searched Medline via OVID to find relevant studies with a follow-up of at least six months. Hereafter, the success and complication rates were extracted and analyzed in a random effects proportion meta-analysis. Complications were defined as avascular bone necrosis (AVN) and posttraumatic osteoarthritis (OA). Additionally, a subgroup analysis was performed for fracture localization (talar neck fractures (TN) and combined talar body/neck fractures (TN/TB)) and severity of the fracture. The quality of the included studies was assessed utilizing the Coleman Methodology Score (CMS). A total of 29 retrospective studies, including 987 fractures with a mean follow-up of 49.9 months, were examined. Success rates were 62%, 60%, and 50% for pooled fractures, TN, and TN/TB, respectively. The overall complication rate for AVN was 25%. The rate was higher for TN (43%) than TN/TB (25%). Talar fractures revealed a 43% posttraumatic osteoarthritis (OA) rate in our meta-analysis. Success rates showed an association with fracture severity, and were generally low in complex multi-fragmentary fractures. The mean CMS was 34.3 (range: 19–47), indicating a moderate methodological quality of the studies. The present systematic review on clinical outcomes of patients undergoing conservative or surgical treatment for talar fractures reveals a lack of reliable prospective evidence. Talar fractures are associated with relatively poor postoperative outcomes, high rates of AVN, and posttraumatic osteoarthritis. Poor outcomes revealed a positive association with fracture severity. Prospective studies investigating predictors for treatment success and/or failure are urgently needed to improve the overall quality of life and function of patients undergoing surgical treatment due to talar fractures.

Recently, the existence of the tissue renin-angiotensin system (tRAS) has been described for multiple tissues in humans, suggesting its fundamental role in the progression of inflammation and fibrosis. Evidence arises that tRAS might have an impact on the progression of periodontitis and bone loss. However, neither the role of tRAS nor its impact as a therapeutic target have been systematically evaluated for periodontal tissue. The present study sought to characterise tRAS in the periodontal tissue and the effect of its inhibition on periodontal inflammation and bone loss. This systematic review was performed according to the preferred reporting items for systematic reviews and meta analyses (PRISMA) statement. Literature was searched using Web of Science core collection (Web of Science), Medline (Ovid), Cochrane central register of controlled trials (Ovid), Cochrane database of systematic reviews (Ovid), Google Scholar databases and the references of the retrieved studies in March 2020. Information on study design, sample size, population, procedure, type of intervention, observation time, as well as information on sources of bias, was extracted and evaluated. From 455 identified articles, 17 were included in the qualitative synthesis and 11 were included in the quantitative synthesis. Outcomes of studies indicated that the inhibition of tRAS components led to a reduction of periodontal bone loss and inflammation, dependent on the inhibitor used. The findings suggested an important role of tRAS in the periodontal tissue and indicate a potential therapeutic approach for periodontal diseases.