Passive Data Use for Ethical Digital Public Health Surveillance in a Postpandemic World.

There is a fundamental need to establish the most ethical and effective way of tracking disease in the postpandemic era. The ubiquity of mobile phones is generating large amounts of passive data (collected without active user participation) that can be used as a tool for tracking disease. Although discussions of pragmatism or economic issues tend to guide public health decisions, ethical issues are the foremost public concern. Thus, officials must look to history and current moral frameworks to avoid past mistakes and ethical pitfalls. Past pandemics demonstrate that the aftermath is the most effective time to make health policy decisions. However, an ethical discussion of passive data use for digital public health surveillance has yet to be attempted, and little has been done to determine the best method to do so. Therefore, we aim to highlight four potential areas of ethical opportunity and challenge: (1) informed consent, (2) privacy, (3) equity, and (4) ownership.

Deep Learning for Adjacent Segment Disease at Preoperative MRI for Cervical Radiculopathy.

Background Patients who undergo surgery for cervical radiculopathy are at risk for developing adjacent segment disease (ASD). Identifying patients who will develop ASD remains challenging for clinicians. Purpose To develop and validate a deep learning algorithm capable of predicting ASD by using only preoperative cervical MRI in patients undergoing single-level anterior cervical diskectomy and fusion (ACDF). Materials and Methods In this Health Insurance Portability and Accountability Act-compliant study, retrospective chart review was performed for 1244 patients undergoing single-level ACDF in two tertiary care centers. After application of inclusion and exclusion criteria, 344 patients were included, of whom 60% (n = 208) were used for training and 40% for validation (n = 43) and testing (n = 93). A deep learning-based prediction model with 48 convolutional layers was designed and trained by using preoperative T2-sagittal cervical MRI. To validate model performance, a neuroradiologist and neurosurgeon independently provided ASD predictions for the test set. Validation metrics included accuracy, areas under the curve, and F1 scores. The difference in proportion of wrongful predictions between the model and clinician was statistically tested by using the McNemar test. Results A total of 344 patients (median age, 48 years; interquartile range, 41-58 years; 182 women) were evaluated. The model predicted ASD on the 93 test images with an accuracy of 88 of 93 (95%; 95% CI: 90, 99), sensitivity of 12 of 15 (80%; 95% CI: 60, 100), and specificity of 76 of 78 (97%; 95% CI: 94, 100). The neuroradiologist and neurosurgeon provided predictions with lower accuracy (54 of 93; 58%; 95% CI: 48, 68), sensitivity (nine of 15; 60%; 95% CI: 35, 85), and specificity (45 of 78; 58%; 95% CI: 56, 77) compared with the algorithm. The McNemar test on the contingency table demonstrated that the proportion of wrongful predictions was significantly lower by the model (test statistic, 2.000; P < .001). Conclusion A deep learning algorithm that used only preoperative cervical T2-weighted MRI outperformed clinical experts at predicting adjacent segment disease in patients undergoing surgery for cervical radiculopathy. © RSNA, 2021 An earlier incorrect version appeared online. This article was corrected on September 22, 2021.

Daily Pain Prediction Using Smartphone Speech Recordings of Patients With Spine Disease.

BACKGROUND: Pain evaluation remains largely subjective in neurosurgical practice, but machine learning provides the potential for objective pain assessment tools. OBJECTIVE: To predict daily pain levels using speech recordings from personal smartphones of a cohort of patients with diagnosed neurological spine disease. METHODS: Patients with spine disease were enrolled through a general neurosurgical clinic with approval from the institutional ethics committee. At-home pain surveys and speech recordings were administered at regular intervals through the Beiwe smartphone application. Praat audio features were extracted from the speech recordings to be used as input to a K-nearest neighbors (KNN) machine learning model. The pain scores were transformed from a 0 to 10 scale to low and high pain for better discriminative capacity. RESULTS: A total of 60 patients were enrolled, and 384 observations were used to train and test the prediction model. Using the KNN prediction model, an accuracy of 71% with a positive predictive value of 0.71 was achieved in classifying pain intensity into high and low. The model showed 0.71 precision for high pain and 0.70 precision for low pain. Recall of high pain was 0.74, and recall of low pain was 0.67. The overall F1 score was 0.73. CONCLUSION: Our study uses a KNN to model the relationship between speech features and pain levels collected from personal smartphones of patients with spine disease. The proposed model is a stepping stone for the development of objective pain assessment in neurosurgery clinical practice.

FDA-approved machine learning algorithms in neuroradiology: A systematic review of the current evidence for approval.

Over the past decade, machine learning (ML) and artificial intelligence (AI) have become increasingly prevalent in the medical field. In the United States, the Food and Drug Administration (FDA) is responsible for regulating AI algorithms as "medical devices" to ensure patient safety. However, recent work has shown that the FDA approval process may be deficient. In this study, we evaluate the evidence supporting FDA-approved neuroalgorithms, the subset of machine learning algorithms with applications in the central nervous system (CNS), through a systematic review of the primary literature. Articles covering the 53 FDA-approved algorithms with applications in the CNS published in PubMed, EMBASE, Google Scholar and Scopus between database inception and January 25, 2022 were queried. Initial searches identified 1505 studies, of which 92 articles met the criteria for extraction and inclusion. Studies were identified for 26 of the 53 neuroalgorithms, of which 10 algorithms had only a single peer-reviewed publication. Performance metrics were available for 15 algorithms, external validation studies were available for 24 algorithms, and studies exploring the use of algorithms in clinical practice were available for 7 algorithms. Papers studying the clinical utility of these algorithms focused on three domains: workflow efficiency, cost savings, and clinical outcomes. Our analysis suggests that there is a meaningful gap between the FDA approval of machine learning algorithms and their clinical utilization. There appears to be room for process improvement by implementation of the following recommendations: the provision of compelling evidence that algorithms perform as intended, mandating minimum sample sizes, reporting of a predefined set of performance metrics for all algorithms and clinical application of algorithms prior to widespread use. This work will serve as a baseline for future research into the ideal regulatory framework for AI applications worldwide.

Traditional Machine Learning Methods versus Deep Learning for Meningioma Classification, Grading, Outcome Prediction, and Segmentation: A Systematic Review and Meta-Analysis.

BACKGROUND: Meningiomas are common intracranial tumors. Machine learning (ML) algorithms are emerging to improve accuracy in 4 primary domains: classification, grading, outcome prediction, and segmentation. Such algorithms include both traditional approaches that rely on hand-crafted features and deep learning (DL) techniques that utilize automatic feature extraction. The aim of this study was to evaluate the performance of published traditional ML versus DL algorithms in classification, grading, outcome prediction, and segmentation of meningiomas. METHODS: A systematic review and meta-analysis were conducted. Major databases were searched through September 2021 for publications evaluating traditional ML versus DL models on meningioma management. Performance measures including pooled sensitivity, specificity, F1-score, area under the receiver-operating characteristic curve, positive and negative likelihood ratios (LR+, LR-) along with their respective 95% confidence intervals (95% CIs) were derived using random-effects models. RESULTS: Five hundred thirty-four records were screened, and 43 articles were included, regarding classification (3 articles), grading (29), outcome prediction (7), and segmentation (6) of meningiomas. Of the 29 studies that reported on grading, 10 could be meta-analyzed with 2 DL models (sensitivity 0.89, 95% CI: 0.74-0.96; specificity 0.91, 95% CI: 0.45-0.99; LR+ 10.1, 95% CI: 1.33-137; LR- 0.12, 95% CI: 0.04-0.59) and 8 traditional ML (sensitivity 0.74, 95% CI: 0.62-0.83; specificity 0.93, 95% CI: 0.79-0.98; LR+ 10.5, 95% CI: 2.91-39.5; and LR- 0.28, 95% CI: 0.17-0.49). The insufficient performance metrics reported precluded further statistical analysis of other performance metrics. CONCLUSIONS: ML on meningiomas is mostly carried out with traditional methods. For meningioma grading, traditional ML methods generally had a higher LR+, while DL models a lower LR-.

Prevalence of pre-operative anxiety and associated risk factors among patients awaiting elective surgery in a tertiary care hospital.

Background: Patients undergoing surgery have a fear of anesthesia and surgical procedures that results in anxiety. The global incidence of pre-operative anxiety is estimated at 60-92%. Age, gender, education, marital status, type of family, type of anesthesia and surgery, and history of surgery are the contributing factors. High levels of anxiety during the pre-operative period has negative impacts on surgical outcomes. The main objective of this study was to find out the prevalence of pre-operative anxiety and associated risk factors in a hospital setting of a developing country. Methods: This was a single center, analytical, cross-sectional study conducted among the admitted patients scheduled for elective surgeries in a tertiary care hospital. Non-probability convenience sampling was adopted and a total of 205 cases were included. The researchers themselves collected the data on the day before surgery using questionnaires comprised of two parts: semi-structured questionnaires prepared via literature review and Amsterdam Pre-operative Anxiety and Information Scale (APAIS). Data were analyzed in SPSS version 23. Bivariate and multivariate analyses were performed appropriately. Results: The prevalence of pre-operative anxiety was 25.85%. The median anaesthesia related, surgery related, and total anxiety scores were 4.00, 5.00 and 9.00 respectively. Likewise, the median score of information desired component scale was 5.00. Different anxiety scores were positively correlated with the information desire component score. The patients living in a nuclear family (adjusted OR, 2.480; 95% CI, 1.272-4.837, p = 0.008) and those without past history of surgery (adjusted OR, 2.451; 95% CI, 1.107-5.424, p = 0.027) had approximately 2.5 times higher risk of having pre-operative anxiety compared to those from a joint family and those having past history of surgery respectively. Those receiving spinal anesthesia had approximately two times lower risk of anxiety (adjusted OR, 0.511; 95% CI, 0.265-0.985, p = 0.045). Conclusions: One fourth of the patients had pre-operative anxiety. Type of family, type of anesthesia and past history of surgery were found to be the independent predictors of anxiety.

A systematic review of federated learning applications for biomedical data.

OBJECTIVES: Federated learning (FL) allows multiple institutions to collaboratively develop a machine learning algorithm without sharing their data. Organizations instead share model parameters only, allowing them to benefit from a model built with a larger dataset while maintaining the privacy of their own data. We conducted a systematic review to evaluate the current state of FL in healthcare and discuss the limitations and promise of this technology. METHODS: We conducted a literature search using PRISMA guidelines. At least two reviewers assessed each study for eligibility and extracted a predetermined set of data. The quality of each study was determined using the TRIPOD guideline and PROBAST tool. RESULTS: 13 studies were included in the full systematic review. Most were in the field of oncology (6 of 13; 46.1%), followed by radiology (5 of 13; 38.5%). The majority evaluated imaging results, performed a binary classification prediction task via offline learning (n = 12; 92.3%), and used a centralized topology, aggregation server workflow (n = 10; 76.9%). Most studies were compliant with the major reporting requirements of the TRIPOD guidelines. In all, 6 of 13 (46.2%) of studies were judged at high risk of bias using the PROBAST tool and only 5 studies used publicly available data. CONCLUSION: Federated learning is a growing field in machine learning with many promising uses in healthcare. Few studies have been published to date. Our evaluation found that investigators can do more to address the risk of bias and increase transparency by adding steps for data homogeneity or sharing required metadata and code.

Deep neural networks allow expert-level brain meningioma segmentation and present potential for improvement of clinical practice.

Accurate brain meningioma segmentation and volumetric assessment are critical for serial patient follow-up, surgical planning and monitoring response to treatment. Current gold standard of manual labeling is a time-consuming process, subject to inter-user variability. Fully-automated algorithms for meningioma segmentation have the potential to bring volumetric analysis into clinical and research workflows by increasing accuracy and efficiency, reducing inter-user variability and saving time. Previous research has focused solely on segmentation tasks without assessment of impact and usability of deep learning solutions in clinical practice. Herein, we demonstrate a three-dimensional convolutional neural network (3D-CNN) that performs expert-level, automated meningioma segmentation and volume estimation on MRI scans. A 3D-CNN was initially trained by segmenting entire brain volumes using a dataset of 10,099 healthy brain MRIs. Using transfer learning, the network was then specifically trained on meningioma segmentation using 806 expert-labeled MRIs. The final model achieved a median performance of 88.2% reaching the spectrum of current inter-expert variability (82.6-91.6%). We demonstrate in a simulated clinical scenario that a deep learning approach to meningioma segmentation is feasible, highly accurate and has the potential to improve current clinical practice.

Deep Tone Mapping Operator for High Dynamic Range Images.

A computationally fast tone mapping operator (TMO) that can quickly adapt to a wide spectrum of high dynamic range (HDR) content is quintessential for visualization on varied low dynamic range (LDR) output devices such as movie screens or standard displays. Existing TMOs can successfully tone-map only a limited number of HDR content and require an extensive parameter tuning to yield the best subjective-quality tone-mapped output. In this paper, we address this problem by proposing a fast, parameter-free and scene-adaptable deep tone mapping operator (DeepTMO) that yields a high-resolution and high-subjective quality tone mapped output. Based on conditional generative adversarial network (cGAN), DeepTMO not only learns to adapt to vast scenic-content (e.g., outdoor, indoor, human, structures, etc.) but also tackles the HDR related scene-specific challenges such as contrast and brightness, while preserving the fine-grained details. We explore 4 possible combinations of Generator-Discriminator architectural designs to specifically address some prominent issues in HDR related deep-learning frameworks like blurring, tiling patterns and saturation artifacts. By exploring different influences of scales, loss-functions and normalization layers under a cGAN setting, we conclude with adopting a multi-scale model for our task. To further leverage on the large-scale availability of unlabeled HDR data, we train our network by generating targets using an objective HDR quality metric, namely Tone Mapping Image Quality Index (TMQI). We demonstrate results both quantitatively and qualitatively, and showcase that our DeepTMO generates high-resolution, high-quality output images over a large spectrum of real-world scenes. Finally, we evaluate the perceived quality of our results by conducting a pair-wise subjective study which confirms the versatility of our method.