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: Articular cartilage defects often result in pain, loss of function and finally osteoarthritis. Developing cell-based therapies for cartilage repair is a major goal of orthopaedic research. Autologous chondrocyte implantation is currently the gold standard cell-based surgical procedure for the treatment of large, isolated, full thickness cartilage defects. Several disadvantages such as the need for two surgical procedures or hypertrophic regenerative cartilage, underline the need for alternative cell sources. Objective: Mesenchymal stem cells, particularly synovium-derived mesenchymal stem cells, represent a promising cell source. Synovium-derived mesenchymal stem cells have attracted considerable attention since they display great chondrogenic potential and less hypertrophic differentiation than mesenchymal stem cells derived from bone marrow. The aim of this review was to summarize the current knowledge on the chondrogenic potential for synovial stem cells in regard to cartilage repair purposes. Results: A literature search was carried out identifying 260 articles in the databases up to January 2017. Several in vitro and initial animal in vivo studies of cartilage repair using synovia stem cell application showed encouraging results. Since synvoium-derived stem cells are located in the direct vicinity of cartilage and cartilage lesions these cells might even contribute to natural cartilage regeneration. The only one published human in vivo study with 10 patients revealed good results concerning postoperative outcome, MRI, and histologic features after a two-stage implantation of synovial stem cells into an isolated cartilage defect of the femoral condyle. Conclusion: Synovium-derived stem cells possess great chondrogenic potential and showed encouraging results for cartilage repair purposes. Furthermore, synovial stem cells play an important role in joint homeostasis and possibly in natural cartilage repair. Further studies are needed to elucidate the interplay of synovial stem cells and chondrocytes, and the promising role of synovium-derived stem cells in cartilage tissue engineering.

BACKGROUND: Minimally invasive transforaminal lumbar interbody fusion (MIS-TLIF) is an increasingly popular procedure with several potential advantages over traditional open TLIF.OBJECTIVE: The current study aimed to compare fusion rates of different graft materials used in MIS-TLIF, via meta-analysis of the published literature.METHODS: A Medline search was performed and a database was created including patient's type of graft, clinical outcome, fusion rate, fusion assessment modality, and duration of follow-up. Meta-analysis of the fusion rate was performed using StatsDirect software (StatsDirect Ltd, Cheshire, United Kingdom).RESULTS: A total of 1533 patients from 40 series were included. Fusion rates were high, ranging from 91.8% to 99%. The imaging modalities used to assess fusion were computed tomography scans (30%) and X-rays (70%). Comparison of all recombinant human bone morphogenetic protein (rhBMP) series with all non-rhBMP series showed fusion rates of 96.6% and 92.5%, respectively. The lowest fusion rate was seen with isolated use of autologous local bone (91.8%). The highest fusion rate was observed with combination of autologous local bone with bone extender and rhBMP (99.1%). The highest fusion rate without the use of BMP was seen with autologous local bone + bone extender (93.1%). The reported complication rate ranged from 0% to 35.71%. Clinical improvement was observed in all studies.CONCLUSION: Fusion rates are generally high with MIS-TLIF regardless of the graft material used. Given the potential complications of iliac bone harvesting and rhBMP, use of other bone graft options for MIS-TLIF is reasonable. The highest fusion rate without the use of rhBMP was seen with autologous local bone plus bone extender (93.1%).