Machine Learning and Deep Learning in Spinal Injury: A Narrative Review of Algorithms in Diagnosis and Prognosis

External Validation of Predictors of Mortality in Polytrauma Patients

INTRODUCTION

The Parkland Trauma Index of Mortality (PTIM) is an integrated, machine learning 72-h mortality prediction model that automatically extracts and analyzes demographic, laboratory, and physiological data in polytrauma patients. We hypothesized that this validated model would perform equally as well at another level 1 trauma center.

METHODS

A retrospective cohort study was performed including ∼5000 adult level 1 trauma activation patients from January 2022 to September 2023. Demographics, physiologic and laboratory values were collected. First, a test set of models using PTIM clinical variables (CVs) was used as external validation, named PTIM+. Then, multiple novel mortality prediction models were developed considering all CVs designated as the Cincinnati Trauma Index of Mortality (CTIM). The statistical performance of the models was then compared.

RESULTS

PTIM CVs were found to have similar predictive performance within the PTIM + external validation model. The highest correlating CVs used in CTIM overlapped considerably with those of the PTIM, and performance was comparable between models. Specifically, for prediction of mortality within 48 h (CTIM versus PTIM): positive prediction value was 35.6% versus 32.5%, negative prediction value was 99.6% versus 99.3%, sensitivity was 81.0% versus 82.5%, specificity was 97.3% versus 93.6%, and area under the curve was 0.98 versus 0.94.

CONCLUSIONS

This external cohort study suggests that the variables initially identified via PTIM retain their predictive ability and are accessible in a different level 1 trauma center. This work shows that a trauma center may be able to operationalize an effective predictive model without undertaking a repeated time and resource intensive process of full variable selection.

A Protocol for Comprehensive Analysis of Gait in Individuals with Incomplete Spinal Cord Injury

This is a protocol for comprehensive analysis of gait and affecting factors in individuals with incomplete paraplegia due to spinal cord injury (SCI). A SCI is a devastating event affecting both sensory and motor functions. Due to better care, the SCI population is changing, with a greater proportion retaining impaired ambulatory function. Optimizing ambulatory function after SCI remains challenging. To investigate factors influencing optimal ambulation, a multi-professional research project was grounded with expertise from clinical rehabilitation, neurophysiology, and biomechanical engineering from Karolinska Institutet, the Spinalis Unit at Aleris Rehab Station (Sweden's largest center for specialized neurorehabilitation), and the Promobilia MoveAbility Lab at KTH Royal Institute of Technology. Ambulatory adults with paraplegia will be consecutively invited to participate. Muscle strength, sensitivity, and spasticity will be assessed, and energy expenditure, 3D movements, and muscle function (EMG) during gait and submaximal contractions will be analyzed. Innovative computational modeling and data-driven analyses will be performed, including the identification of clusters of similar movement patterns among the heterogeneous population and analyses that study the link between complex sensorimotor function and movement performance. These results may help optimize ambulatory function for persons with SCI and decrease the risk of secondary conditions during gait with a life-long perspective.

Synergizing Deep Learning-Enabled Preprocessing and Human-AI Integration for Efficient Automatic Ground Truth Generation

The progress of incorporating deep learning in the field of medical image interpretation has been greatly hindered due to the tremendous cost and time associated with generating ground truth for supervised machine learning, alongside concerns about the inconsistent quality of images acquired. Active learning offers a potential solution to these problems of expanding dataset ground truth by algorithmically choosing the most informative samples for ground truth labeling. Still, this effort incurs the costs of human labeling, which needs minimization. Furthermore, automatic labeling approaches employing active learning often exhibit overfitting tendencies while selecting samples closely aligned with the training set distribution and excluding out-of-distribution samples, which could potentially improve the model's effectiveness. We propose that the majority of out-of-distribution instances can be attributed to inconsistent cross images. Since the FDA approved the first whole-slide image system for medical diagnosis in 2017, whole-slide images have provided enriched critical information to advance the field of automated histopathology. Here, we exemplify the benefits of a novel deep learning strategy that utilizes high-resolution whole-slide microscopic images. We quantitatively assess and visually highlight the inconsistencies within the whole-slide image dataset employed in this study. Accordingly, we introduce a deep learning-based preprocessing algorithm designed to normalize unknown samples to the training set distribution, effectively mitigating the overfitting issue. Consequently, our approach significantly increases the amount of automatic region-of-interest ground truth labeling on high-resolution whole-slide images using active deep learning. We accept 92% of the automatic labels generated for our unlabeled data cohort, expanding the labeled dataset by 845%. Additionally, we demonstrate expert time savings of 96% relative to manual expert ground-truth labeling.

The value of machine learning technology and artificial intelligence to enhance patient safety in spine surgery: a review

Machine learning algorithms have the potential to significantly improve patient safety in spine surgeries by providing healthcare professionals with valuable insights and predictive analytics. These algorithms can analyze preoperative data, such as patient demographics, medical history, and imaging studies, to identify potential risk factors and predict postoperative complications. By leveraging machine learning, surgeons can make more informed decisions, personalize treatment plans, and optimize surgical techniques to minimize risks and enhance patient outcomes. Moreover, by harnessing the power of machine learning, healthcare providers can make data-driven decisions, personalize treatment plans, and optimize surgical interventions, ultimately enhancing the quality of care in spine surgery. The findings highlight the potential of integrating artificial intelligence in healthcare settings to mitigate risks and enhance patient safety in surgical practices. The integration of machine learning holds immense potential for enhancing patient safety in spine surgeries. By leveraging advanced algorithms and predictive analytics, healthcare providers can optimize surgical decision-making, mitigate risks, and personalize treatment strategies to improve outcomes and ensure the highest standard of care for patients undergoing spine procedures. As technology continues to evolve, the future of spine surgery lies in harnessing the power of machine learning to transform patient safety and revolutionize surgical practices. The present review article was designed to discuss the available literature in the field of machine learning techniques to enhance patient safety in spine surgery.