Reliable Prediction of Discharge Disposition Following Cervical Spine Surgery With Ensemble Machine Learning and Validation on a National Cohort.

STUDY DESIGN: A retrospective cohort study. OBJECTIVE: The purpose of this study is to develop a machine learning algorithm to predict nonhome discharge after cervical spine surgery that is validated and usable on a national scale to ensure generalizability and elucidate candidate drivers for prediction. SUMMARY OF BACKGROUND DATA: Excessive length of hospital stay can be attributed to delays in postoperative referrals to intermediate care rehabilitation centers or skilled nursing facilities. Accurate preoperative prediction of patients who may require access to these resources can facilitate a more efficient referral and discharge process, thereby reducing hospital and patient costs in addition to minimizing the risk of hospital-acquired complications. METHODS: Electronic medical records were retrospectively reviewed from a single-center data warehouse (SCDW) to identify patients undergoing cervical spine surgeries between 2008 and 2019 for machine learning algorithm development and internal validation. The National Inpatient Sample (NIS) database was queried to identify cervical spine fusion surgeries between 2009 and 2017 for external validation of algorithm performance. Gradient-boosted trees were constructed to predict nonhome discharge across patient cohorts. The area under the receiver operating characteristic curve (AUROC) was used to measure model performance. SHAP values were used to identify nonlinear risk factors for nonhome discharge and to interpret algorithm predictions. RESULTS: A total of 3523 cases of cervical spine fusion surgeries were included from the SCDW data set, and 311,582 cases were isolated from NIS. The model demonstrated robust prediction of nonhome discharge across all cohorts, achieving an area under the receiver operating characteristic curve of 0.87 (SD=0.01) on both the SCDW and nationwide NIS test sets. Anterior approach only, age, elective admission status, Medicare insurance status, and total Elixhauser Comorbidity Index score were the most important predictors of discharge destination. CONCLUSIONS: Machine learning algorithms reliably predict nonhome discharge across single-center and national cohorts and identify preoperative features of importance following cervical spine fusion surgery.

Weekend Admission Increases Risk of Readmissions Following Elective Cervical Spinal Fusion.

OBJECTIVE: The "weekend effect" occurs when patients cared for during weekends versus weekdays experience worse outcomes. But reasons for this effect are unclear, especially amongst patients undergoing elective cervical spinal fusion (ECSF). Our aim was to analyze whether index weekend admission affects 30- and 90-day readmission rates post-ECSF. METHODS: All ECSF patients > 18 years were retrospectively identified from the 2016-2018 Healthcare Cost and Utilization Project Nationwide Readmissions Database (NRD), using unique patient linkage codes and International Classification of Diseases, Tenth Revision codes. Patient demographics, comorbidities, and outcomes were analyzed. Univariate logistic regression analyzed primary outcomes of 30- and 90-day readmission rates in weekday or weekend groups. Multivariate regression determined the impact of complications on readmission rates. RESULTS: Compared to the weekday group (n = 125,590), the weekend group (n = 1,026) held a higher percentage of Medicare/Medicaid insurance, incurred higher costs, had longer length of stay, and fewer routine home discharge (all p < 0.001). There was no difference in comorbidity burden between weekend versus weekday admissions, as measured by the Elixhauser Comorbidity Index (p = 0.527). Weekend admissions had higher 30-day (4.30% vs. 7.60%, p < 0.001) and 90-day (7.80% vs. 16.10%, p < 0.001) readmission rates, even after adjusting for sex, age, insurance status, and comorbidities. All-cause complication rates were higher for weekend admissions (8.62% vs. 12.7%, p < 0.001), specifically deep vein thrombosis, infection, neurological conditions, and pulmonary embolism. CONCLUSION: Index weekend admission increases 30- and 90-day readmission rates after ECSF. In patients undergoing ECSF on weekends, postoperative care for patients at risk for specific complications will allow for improved outcomes and health care utilization.

Robust prediction of nonhome discharge following elective anterior cervical discectomy and fusion using explainable machine learning.

PURPOSE: Predict nonhome discharge (NHD) following elective anterior cervical discectomy and fusion (ACDF) using an explainable machine learning model. METHODS: 2227 patients undergoing elective ACDF from 2008 to 2019 were identified from a single institutional database. A machine learning model was trained on preoperative variables, including demographics, comorbidity indices, and levels fused. The validation technique was repeated stratified K-Fold cross validation with the area under the receiver operating curve (AUROC) statistic as the performance metric. Shapley Additive Explanation (SHAP) values were calculated to provide further explainability regarding the model's decision making. RESULTS: The preoperative model performed with an AUROC of 0.83 ± 0.05. SHAP scores revealed the most pertinent risk factors to be age, medicare insurance, and American Society of Anesthesiology (ASA) score. Interaction analysis demonstrated that female patients over 65 with greater fusion levels were more likely to undergo NHD. Likewise, ASA demonstrated positive interaction effects with female sex, levels fused and BMI. CONCLUSION: We validated an explainable machine learning model for the prediction of NHD using common preoperative variables. Adding transparency is a key step towards clinical application because it demonstrates that our model's "thinking" aligns with clinical reasoning. Interactive analysis demonstrated that those of age over 65, female sex, higher ASA score, and greater fusion levels were more predisposed to NHD. Age and ASA score were similar in their predictive ability. Machine learning may be used to predict NHD, and can assist surgeons with patient counseling or early discharge planning.

Teledermatology in medical student, postgraduate trainee, and global dermatology education: A systematic review.

Background: In the aftermath of the COVID-19 pandemic, medical students and residents in the U.S. and globally have gained more exposure to teledermatology, both for the purposes of clinical practice and education. Objective: We conducted a systematic review to assess outcomes from teledermatology interventions for dermatology trainees in the U.S. and globally in accordance with Preferred Reporting Items for Systematic Reviews (PRISMA). Methods: We searched MEDLINE, EMBASE, Web of Science, and Cochrane CENTRAL for articles written in English and published database inception to November 20, 2022. Results: In total, 15 studies met the inclusion criteria. Outcomes reported ranged broadly from resident-provider concordance rates, diagnostic accuracy in comparison to control groups, number of patients seen, and self-reported satisfaction and improvement. Generally, studies indicated high satisfaction rates and improvement in educational outcomes among medical students, residents, and other trainees in the global health setting. Limitations: Because of the heterogeneity of study design and outcomes reported, meta-analysis could not be performed. Conclusion: Teledermatology can be successfully deployed for clinical care and education domestically and in the global health setting.

Development of a machine learning algorithm to identify total and reverse shoulder arthroplasty implants from X-ray images.

Introduction: Demand for total shoulder arthroplasty (TSA) has risen significantly and is projected to continue growing. From 2012 to 2017, the incidence of reverse total shoulder arthroplasty (rTSA) rose from 7.3 cases per 100,000 to 19.3 per 100,000. Anatomical TSA saw a growth from 9.5 cases per 100,000 to 12.5 per 100,000. Failure to identify implants in a timely manner can increase operative time, cost and risk of complications. Several machine learning models have been developed to perform medical image analysis. However, they have not been widely applied in shoulder surgery. The authors developed a machine learning model to identify shoulder implant manufacturers and type from anterior-posterior X-ray images. Methods: The model deployed was a convolutional neural network (CNN), which has been widely used in computer vision tasks. 696 radiographs were obtained from a single institution. 70% were used to train the model, while evaluation was done on 30%. Results: On the evaluation set, the model performed with an overall accuracy of 93.9% with positive predictive value, sensitivity and F-1 scores of 94% across 10 different implant types (4 reverse, 6 anatomical). Average identification time was 0.110 s per implant. Conclusion: This proof of concept study demonstrates that machine learning can assist with preoperative planning and improve cost-efficiency in shoulder surgery.

Virtual Reality Hemifield Measurements for Corrective Surgery Eligibility in Ptosis Patients: A Pilot Clinical Trial.

Purpose: We developed an accelerated virtual reality (VR) suprathreshold hemifield perimetry algorithm, the median cut hemifield test (MCHT). This study examines the ability of the MCHT to determine ptosis severity and its reversibility with an artificial improvement by eyelid taping on an HTC Vive Pro Eye VR headset and the Humphrey visual field analyzer (HVFA) to assess the capabilities of emerging technologies in evaluating ptosis. Methods: In a single visit, the MCHT was administered along with the HVFA 30-2 on ptotic untaped and taped eyelids in a randomized order. The primary end points were a superior field visibility comparison with severity of VF loss and VF improvement after taping for MCHT and HVFA. Secondary end points included evaluating patients' Likert-scaled survey responses on the comfort, speed, and overall experience with both testing modalities. Results: VR's MCHT superior field degrees visible correlated well for severe category margin to reflex distance (r = 0.78) compared with HVFA's (r = -0.21). The MCHT also demonstrated noninferiority (83.3% agreement; P = 1) against HVFA for detection of 30% or more superior visual field improvement after taping, warranting a corrective surgical intervention. In comparing hemi-VF in untaped eyes, both tests demonstrated relative obstruction to the field when comparing normal controls to severe ptosis (HVFA P < 0.05; MCHT P < 0.001), which proved sufficient to demonstrate percent improvement with taping. The secondary end point of patient satisfaction favored VR vision testing presentation mode in terms of comfort (P < 0.01), speed (P < 0.001), and overall experience (P < 0.01). Conclusions: This pilot trial supports the use of MCHT for the quantitative measurement of visual field loss owing to ptosis and the reversibility of ptosis that is tested when conducting a presurgical evaluation. We believe the adoption of MCHT testing in oculoplastic clinics could decrease patient burden and accelerate time to corrective treatment. Translational Relevance: In this study, we look at vision field outputs in patients with ptosis to evaluate its severity and improvement with eyelid taping on a low-profile VR-based technology and compare it with HVFA. Our results demonstrate that alternative, portable technologies such as VR can be used to grade the degree of ptosis and determine whether ptosis surgery could provide a significant superior visual field improvement of 30% or more, all while ensuring a more comfortable experience and faster testing time.

Deploying deep learning models on unseen medical imaging using adversarial domain adaptation.

The fundamental challenge in machine learning is ensuring that trained models generalize well to unseen data. We developed a general technique for ameliorating the effect of dataset shift using generative adversarial networks (GANs) on a dataset of 149,298 handwritten digits and dataset of 868,549 chest radiographs obtained from four academic medical centers. Efficacy was assessed by comparing area under the curve (AUC) pre- and post-adaptation. On the digit recognition task, the baseline CNN achieved an average internal test AUC of 99.87% (95% CI, 99.87-99.87%), which decreased to an average external test AUC of 91.85% (95% CI, 91.82-91.88%), with an average salvage of 35% from baseline upon adaptation. On the lung pathology classification task, the baseline CNN achieved an average internal test AUC of 78.07% (95% CI, 77.97-78.17%) and an average external test AUC of 71.43% (95% CI, 71.32-71.60%), with a salvage of 25% from baseline upon adaptation. Adversarial domain adaptation leads to improved model performance on radiographic data derived from multiple out-of-sample healthcare populations. This work can be applied to other medical imaging domains to help shape the deployment toolkit of machine learning in medicine.

Weekend Admission Increases Risk of Readmissions Following Elective Thoracolumbar Spinal Fusion.

STUDY DESIGN: Retrospective database study. OBJECTIVES: The goal of this study was to assess the influence of weekend admission on patients undergoing elective thoracolumbar spinal fusion by investigating hospital readmission outcomes and analyzing differences in demographics, comorbidities, and postoperative factors. METHODS: The 2016-2018 Nationwide Readmission Database was used to identify adult patients who underwent elective thoracolumbar spinal fusion. The sample was divided into weekday and weekend admission patients. Demographics, comorbidities, complications, and discharge status data were compiled. The primary outcomes were 30-day and 90-day readmission. Univariate logistic regression analyzed the relationship between weekday or weekend admission and 30- or 90-day readmission, and multivariate regression determined the impact of covariates. RESULTS: 177,847 patients were identified in total, with 176,842 in the weekday cohort and 1005 in the weekend cohort. Multivariate regression analysis found that 30-day readmissions were significantly greater for the weekend cohort after adjusting for sex, age, Medicare or Medicaid status, and comorbidity status (OR 2.00, 95% CI: 1.60-2.48; P < .001), and 90-day readmissions were also greater for the weekend cohort after adjustment (OR 2.01, 95% CI: 1.68-2.40, P < .001). CONCLUSIONS: Patients undergoing elective thoracolumbar spinal fusion surgery who are initially admitted on weekends are more likely to experience hospital readmission. These patients have increased incidence of deep vein thrombosis, postoperative infection, and non-routine discharge status. These factors are potential areas of focus for reducing the impact of the "weekend effect" and improving outcomes for elective thoracolumbar spinal fusion.

Pragmatic Prediction of Excessive Length of Stay After Cervical Spine Surgery With Machine Learning and Validation on a National Scale.

BACKGROUND: Extended postoperative hospital stays are associated with numerous clinical risks and increased economic cost. Accurate preoperative prediction of extended length of stay (LOS) can facilitate targeted interventions to mitigate clinical harm and resource utilization. OBJECTIVE: To develop a machine learning algorithm aimed at predicting extended LOS after cervical spine surgery on a national level and elucidate drivers of prediction. METHODS: Electronic medical records from a large, urban academic medical center were retrospectively examined to identify patients who underwent cervical spine fusion surgeries between 2008 and 2019 for machine learning algorithm development and in-sample validation. The National Inpatient Sample database was queried to identify cervical spine fusion surgeries between 2009 and 2017 for out-of-sample validation of algorithm performance. Gradient-boosted trees predicted LOS and efficacy was assessed using the area under the receiver operating characteristic curve (AUROC). Shapley values were calculated to characterize preoperative risk factors for extended LOS and explain algorithm predictions. RESULTS: Gradient-boosted trees accurately predicted extended LOS across cohorts, achieving an AUROC of 0.87 (SD = 0.01) on the single-center validation set and an AUROC of 0.84 (SD = 0.00) on the nationwide National Inpatient Sample data set. Anterior approach only, elective admission status, age, and total number of Elixhauser comorbidities were important predictors that affected the likelihood of prolonged LOS. CONCLUSION: Machine learning algorithms accurately predict extended LOS across single-center and national patient cohorts and characterize key preoperative drivers of increased LOS after cervical spine surgery.

Robust Prediction of Non-home Discharge After Thoracolumbar Spine Surgery With Ensemble Machine Learning and Validation on a Nationwide Cohort.

BACKGROUND: Delays in postoperative referrals to rehabilitation or skilled nursing facilities contribute toward extended hospital stays. Facilitating more efficient referrals through accurate preoperative prediction algorithms has the potential to reduce unnecessary economic burden and minimize risk of hospital-acquired complications. We develop a robust machine learning algorithm to predict non-home discharge after thoracolumbar spine surgery that generalizes to unseen populations and identifies markers for prediction. METHODS: Retrospective electronic health records were obtained from our single-center data warehouse (SCDW) to identify patients undergoing thoracolumbar spine surgeries between 2008 and 2019 for algorithm development and internal validation. The National Inpatient Sample (NIS) database was queried to identify thoracolumbar surgeries between 2009 and 2017 for out-of-sample validation. Ensemble decision trees were constructed for prediction and area under the receiver operating characteristic curve (AUROC) was used to assess performance. Shapley additive explanations values were derived to identify drivers of non-home discharge for interpretation of algorithm predictions. RESULTS: A total of 5224 cases of thoracolumbar spine surgeries were isolated from the SCDW and 492,312 cases were identified from NIS. The model achieved an AUROC of 0.81 (standard deviation [SD] = 0.01) on the SCDW test set and 0.77 (SD = 0.01) on the nationwide NIS data set, thereby demonstrating robust prediction of non-home discharge across all diverse patient cohorts. Age, total Elixhauser comorbidities, Medicare insurance, weighted Elixhauser score, and female sex were among the most important predictors of non-home discharge. CONCLUSIONS: Machine learning algorithms reliably predict non-home discharge after thoracolumbar spine surgery across single-center and national cohorts and identify preoperative features of importance that elucidate algorithm decision-making.

Population scale latent space cohort matching for the improved use and exploration of observational trial data.

A significant amount of clinical research is observational by nature and derived from medical records, clinical trials, and large-scale registries. While there is no substitute for randomized, controlled experimentation, such experiments or trials are often costly, time consuming, and even ethically or practically impossible to execute. Combining classical regression and structural equation modeling with matching techniques can leverage the value of observational data. Nevertheless, identifying variables of greatest interest in high-dimensional data is frequently challenging, even with application of classical dimensionality reduction and/or propensity scoring techniques. Here, we demonstrate that projecting high-dimensional medical data onto a lower-dimensional manifold using deep autoencoders and post-hoc generation of treatment/control cohorts based on proximity in the lower-dimensional space results in better matching of confounding variables compared to classical propensity score matching (PSM) in the original high-dimensional space (P<0.0001) and performs similarly to PSM models constructed by experts with prior knowledge of the underlying pathology when evaluated on predicting risk ratios from real-world clinical data. Thus, in cases when the underlying problem is poorly understood and the data is high-dimensional in nature, matching in the autoencoder latent space might be of particular benefit.

Portable hardware & software technologies for addressing ophthalmic health disparities: A systematic review.

Vision impairment continues to be a major global problem, as the WHO estimates 2.2 billion people struggling with vision loss or blindness. One billion of these cases, however, can be prevented by expanding diagnostic capabilities. Direct global healthcare costs associated with these conditions totaled $255 billion in 2010, with a rapid upward projection to $294 billion in 2020. Accordingly, WHO proposed 2030 targets to enhance integration and patient-centered vision care by expanding refractive error and cataract worldwide coverage. Due to the limitations in cost and portability of adapted vision screening models, there is a clear need for new, more accessible vision testing tools in vision care. This comparative, systematic review highlights the need for new ophthalmic equipment and approaches while looking at existing and emerging technologies that could expand the capacity for disease identification and access to diagnostic tools. Specifically, the review focuses on portable hardware- and software-centered strategies that can be deployed in remote locations for detection of ophthalmic conditions and refractive error. Advancements in portable hardware, automated software screening tools, and big data-centric analytics, including machine learning, may provide an avenue for improving ophthalmic healthcare.

Understanding Artificial Intelligence and Predictive Analytics: A Clinically Focused Review of Machine Learning Techniques.

¼: Machine learning and artificial intelligence have seen tremendous growth in recent years and have been applied in numerous studies in the field of orthopaedics. ¼: Machine learning will soon become critical in the day-to-day operations of orthopaedic practice; therefore, it is imperative that providers become accustomed to and familiar with not only the terminology but also the fundamental techniques behind the technology. ¼: A foundation of knowledge regarding machine learning is critical for physicians so they can begin to understand the details in the algorithms that are being developed, which provide improved accuracy compared with clinicians, decreased time required, and a heightened ability to triage patients.

Intraoperative Navigation in Spine Surgery: Effects on Complications and Reoperations.

INTRODUCTION: Intraoperative navigation during spine surgery improves pedicle screw placement accuracy. However, limited studies have correlated the use of navigation with clinical factors, including operative time and safety. In the present study, we compared the complications and reoperations between surgeries with and without navigation. METHODS: The National Surgical Quality Improvement Project database was queried for posterior cervical and lumbar fusions and deformity surgeries from 2011 to 2018 and divided by navigation use. Patients aged >89 years, patients with deformity aged <25 years, and patients undergoing surgery for tumors, fractures, infections, or nonelective indications were excluded. The demographics and perioperative factors were compared via univariate analysis. The outcomes were compared using multivariable logistic regression adjusting for age, sex, body mass index, American Society of Anesthesiologists class, surgical region, and multiple treatment levels. The outcomes were also compared stratifying by revision status. RESULTS: Navigation surgery patients had had higher American Society of Anesthesiologists class (P < 0.0001), more multiple level surgeries (P < 0.0001), and longer operative times (P < 0.0001). The adjusted analysis revealed that navigated lumbar surgery had lower odds of complications (odds ratio [OR], 0.82; 95% confidence interval [CI], 0.77-0.90; P < 0.0001), blood transfusion (OR, 0.79; 95% CI, 0.72-0.87; P < 0.0001), and wound debridement and/or drainage (OR, 0.66; 95% CI, 0.44-0.97; P = 0.04) compared with non-navigated lumbar surgery. Navigated cervical fusions had increased odds of transfusions (OR, 1.53; 95% CI, 1.06-2.23; P = 0.02). Navigated primary fusion had decreased odds of complications (OR, 0.91; 95% CI, 0.85-0.98; P = 0.01). However, no differences were found in revisions (OR, 0.89; 95% CI, 0.69-1.14; P = 0.34). CONCLUSIONS: Navigated surgery patients experienced longer operations owing to a combination of the time required for navigation, more multilevel procedures, and a larger comorbidity burden, without differences in the incidence of infection. Fewer complications and wound washouts were required for navigated lumbar surgery owing to a greater proportion percentage of minimally invasive cases. The combined use of navigation and minimally invasive surgery might benefit patients with the proper indications.

Clinical Trials in Spinal Tumors: A Two-Decade Review.

OBJECTIVE: Clinical trials are essential for assessing the advancements in spine tumor therapeutics. The purpose of the present study was to characterize the trends in clinical trials for primary and metastatic tumor treatment during the past 2 decades. METHODS: The ClinicalTrials.gov database was queried using the search term "spine" for all interventional studies from 1999 to 2020 with the categories of "cancer," "neoplasm," "tumor," and/or "metastasis." The tumor type, phase data, enrollment numbers, and home institution country were recorded. The sponsor was categorized as an academic institution, industry, government, or other and the intervention type as procedure, drug, device, radiation therapy, or other. The frequency of each category and the cumulative frequency during the 20-year period were calculated. RESULTS: A total of 106 registered trials for spine tumors were listed. All, except for 2, that had begun before 2008 had been completed. An enrollment of 51-100 participants (29.8%) was the most common, and most were phase II studies (54.4%). Most of the studies had examined metastatic tumors (58.5%), and the number of new trials annually had increased 3.4-fold from 2009 to 2020. Most of the studies had been conducted in the United States (56.4%). The most common intervention strategy was radiation therapy (32.1%), although from 2010 to 2020, procedural studies had become the most frequent (2.4/year). Most of the studies had been sponsored by academic institutions (63.2%), which during the 20-year period had sponsored 3.2-fold more studies compared with the industry partners. CONCLUSIONS: The number of clinical trials for spine tumor therapies has rapidly increased during the past 15 years, owing to studies at U.S. academic medical institutions investigating radiosurgery for the treatment of metastases. Targeted therapies for tumor subtypes and sequelae have updated international best practices.

Identification of Anterior Cervical Spinal Instrumentation Using a Smartphone Application Powered by Machine Learning.

STUDY DESIGN: Cross-sectional study. OBJECTIVE: The purpose of this study is to develop and validate a machine learning algorithm for the automated identification of anterior cervical discectomy and fusion (ACDF) plates from smartphone images of anterior-posterior (AP) cervical spine radiographs. SUMMARY OF BACKGROUND DATA: Identification of existing instrumentation is a critical step in planning revision surgery for ACDF. Machine learning algorithms that are known to be adept at image classification may be applied to the problem of ACDF plate identification. METHODS: A total of 402 smartphone images containing 15 different types of ACDF plates were gathered. Two hundred seventy-five images (∼70%) were used to train and validate a convolution neural network (CNN) for classification of images from radiographs. One hundred twenty-seven (∼30%) images were held out to test algorithm performance. RESULTS: The algorithm performed with an overall accuracy of 94.4% and 85.8% for top-3 and top-1 accuracy, respectively. Overall positive predictive value, sensitivity, and f1-scores were 0.873, 0.858, and 0.855, respectively. CONCLUSION: This algorithm demonstrates strong performance in the classification of ACDF plates from smartphone images and will be deployed as an accessible smartphone application for further evaluation, improvement, and eventual widespread use.Level of Evidence: 3.

Deep anomaly detection of seizures with paired stereoelectroencephalography and video recordings.

Real-time seizure detection is a resource intensive process as it requires continuous monitoring of patients on stereoelectroencephalography. This study improves real-time seizure detection in drug resistant epilepsy (DRE) patients by developing patient-specific deep learning models that utilize a novel self-supervised dynamic thresholding approach. Deep neural networks were constructed on over 2000 h of high-resolution, multichannel SEEG and video recordings from 14 DRE patients. Consensus labels from a panel of epileptologists were used to evaluate model efficacy. Self-supervised dynamic thresholding exhibited improvements in positive predictive value (PPV; difference: 39.0%; 95% CI 4.5-73.5%; Wilcoxon-Mann-Whitney test; N = 14; p = 0.03) with similar sensitivity (difference: 14.3%; 95% CI - 21.7 to 50.3%; Wilcoxon-Mann-Whitney test; N = 14; p = 0.42) compared to static thresholds. In some models, training on as little as 10 min of SEEG data yielded robust detection. Cross-testing experiments reduced PPV (difference: 56.5%; 95% CI 25.8-87.3%; Wilcoxon-Mann-Whitney test; N = 14; p = 0.002), while multimodal detection significantly improved sensitivity (difference: 25.0%; 95% CI 0.2-49.9%; Wilcoxon-Mann-Whitney test; N = 14; p < 0.05). Self-supervised dynamic thresholding improved the efficacy of real-time seizure predictions. Multimodal models demonstrated potential to improve detection. These findings are promising for future deployment in epilepsy monitoring units to enable real-time seizure detection without annotated data and only minimal training time in individual patients.

Automated Measurement of Lumbar Lordosis on Radiographs Using Machine Learning and Computer Vision.

STUDY DESIGN: Cross sectional database study. OBJECTIVE: To develop a fully automated artificial intelligence and computer vision pipeline for assisted evaluation of lumbar lordosis. METHODS: Lateral lumbar radiographs were used to develop a segmentation neural network (n = 629). After synthetic augmentation, 70% of these radiographs were used for network training, while the remaining 30% were used for hyperparameter optimization. A computer vision algorithm was deployed on the segmented radiographs to calculate lumbar lordosis angles. A test set of radiographs was used to evaluate the validity of the entire pipeline (n = 151). RESULTS: The U-Net segmentation achieved a test dataset dice score of 0.821, an area under the receiver operating curve of 0.914, and an accuracy of 0.862. The computer vision algorithm identified the L1 and S1 vertebrae on 84.1% of the test set with an average speed of 0.14 seconds/radiograph. From the 151 test set radiographs, 50 were randomly chosen for surgeon measurement. When compared with those measurements, our algorithm achieved a mean absolute error of 8.055° and a median absolute error of 6.965° (not statistically significant, P > .05). CONCLUSION: This study is the first to use artificial intelligence and computer vision in a combined pipeline to rapidly measure a sagittal spinopelvic parameter without prior manual surgeon input. The pipeline measures angles with no statistically significant differences from manual measurements by surgeons. This pipeline offers clinical utility in an assistive capacity, and future work should focus on improving segmentation network performance.

Deep Learning and Neurology: A Systematic Review.

Deciphering the massive volume of complex electronic data that has been compiled by hospital systems over the past decades has the potential to revolutionize modern medicine, as well as present significant challenges. Deep learning is uniquely suited to address these challenges, and recent advances in techniques and hardware have poised the field of medical machine learning for transformational growth. The clinical neurosciences are particularly well positioned to benefit from these advances given the subtle presentation of symptoms typical of neurologic disease. Here we review the various domains in which deep learning algorithms have already provided impetus for change-areas such as medical image analysis for the improved diagnosis of Alzheimer's disease and the early detection of acute neurologic events; medical image segmentation for quantitative evaluation of neuroanatomy and vasculature; connectome mapping for the diagnosis of Alzheimer's, autism spectrum disorder, and attention deficit hyperactivity disorder; and mining of microscopic electroencephalogram signals and granular genetic signatures. We additionally note important challenges in the integration of deep learning tools in the clinical setting and discuss the barriers to tackling the challenges that currently exist.

CHK1 Inhibition in Small-Cell Lung Cancer Produces Single-Agent Activity in Biomarker-Defined Disease Subsets and Combination Activity with Cisplatin or Olaparib.

Effective targeted therapies for small-cell lung cancer (SCLC), the most aggressive form of lung cancer, remain urgently needed. Here we report evidence of preclinical efficacy evoked by targeting the overexpressed cell-cycle checkpoint kinase CHK1 in SCLC. Our studies employed RNAi-mediated attenuation or pharmacologic blockade with the novel second-generation CHK1 inhibitor prexasertib (LY2606368), currently in clinical trials. In SCLC models in vitro and in vivo, LY2606368 exhibited strong single-agent efficacy, augmented the effects of cisplatin or the PARP inhibitor olaparib, and improved the response of platinum-resistant models. Proteomic analysis identified CHK1 and MYC as top predictive biomarkers of LY2606368 sensitivity, suggesting that CHK1 inhibition may be especially effective in SCLC with MYC amplification or MYC protein overexpression. Our findings provide a preclinical proof of concept supporting the initiation of a clinical efficacy trial in patients with platinum-sensitive or platinum-resistant relapsed SCLC. Cancer Res; 77(14); 3870-84. ©2017 AACR.