Using an artificial intelligence software improves emergency medicine physician intracranial haemorrhage detection to radiologist levels.

BACKGROUND: Tools to increase the turnaround speed and accuracy of imaging reports could positively influence ED logistics. The Caire ICH is an artificial intelligence (AI) software developed for ED physicians to recognise intracranial haemorrhages (ICHs) on non-contrast enhanced cranial CT scans to manage the clinical care of these patients in a timelier fashion. METHODS: A dataset of 532 non-contrast cranial CT scans was reviewed by five board-certified emergency physicians (EPs) with an average of 14.8 years of practice experience. The scans were labelled in random order for the presence or absence of an ICH. If an ICH was detected, the reader further labelled all subtypes present (ie, epidural, subdural, subarachnoid, intraparenchymal and/or intraventricular haemorrhage). After a washout period, the five EPs reviewed again the scans individually with the assistance of Caire ICH. The mean accuracy of the EP readings with AI assistance was compared with the mean accuracy of three general radiologists reading the films individually. The final diagnosis (ie, ground truth) was adjudicated by a consensus of the radiologists after their individual readings. RESULTS: Mean EP reader accuracy significantly increased by 6.20% (95% CI for the difference 5.10%-7.29%; p=0.0092) when using Caire ICH to detect an ICH. Mean accuracy of the EP cohort in detecting an ICH using Caire ICH was found to be more accurate than the radiologist cohort prior to discussion; this difference, however, was not statistically significant. CONCLUSION: The Caire ICH software significantly improved the accuracy and sensitivity of detecting an ICH by the EP to a level comparable to general radiologists. Further prospective research with larger numbers will be needed to understand the impact of Caire ICH on ED logistics and patient outcomes.

Identification of successful cerebral reperfusions (mTICI ≥2b) using an artificial intelligence strategy.

BACKGROUND: The modified thrombolysis in cerebral infarction (mTICI) scale is a widely used and validated qualitative tool to evaluate angiographic intracerebral inflow following endovascular thrombectomy (EVT). We validated a machine-learning (ML) algorithm to grade digital subtraction angiograms (DSA) using the mTICI scale. MATERIALS AND METHODS: We included angiograms of identified middle cerebral artery (MCA) occlusions who underwent EVT. The complete DSA sequences were preprocessed and normalized. We created three convolutional neural networks to classify DSA into two outcomes, low- (mTICI 0,1,2a) and high-grade (mTICI 2b,2c,3). RESULTS: We included a total of 234 angiograms in this study. The area under the receiver operating characteristic was 0.863 (95% CI 0.816-0.909), 0.914 (95% CI 0.876-0.951), and 0.890 (95% CI 0.848-0.932) for the anteroposterior (AP), lateral (L), and combined models, respectively, when dichotomizing outcomes into low and high grade. The models' area under the precision-recall curve was 0.879 (95% CI 0.829-0.930), 0.906 (95% CI 0.844-0.968), and 0.887 (95% CI 0.834-0.941) for the AP, L, and combined models. CONCLUSION: In complete cerebral DSA, our angiography-based ML strategy was able to predict mTICI scores following EVT rapidly and reliably for MCA occlusions.

A deep learning method to identify and localize large-vessel occlusions from cerebral digital subtraction angiography.

BACKGROUND AND PURPOSE: An essential step during endovascular thrombectomy is identifying the occluded arterial vessel on a cerebral digital subtraction angiogram (DSA). We developed an algorithm that can detect and localize the position of occlusions in cerebral DSA. METHODS: We retrospectively collected cerebral DSAs from a single institution between 2018 and 2020 from 188 patients, 86 of whom suffered occlusions of the M1 and proximal M2 segments. We trained an ensemble of deep-learning models on fewer than 60 large-vessel occlusion (LVO)-positive patients. We evaluated the model on an independent test set and evaluated the truth of its predicted localizations using Intersection over Union and expert review. RESULTS: On an independent test set of 166 cerebral DSA frames with an LVO prevalence of 0.19, the model achieved a specificity of 0.95 (95% confidence interval [CI]: 0.90, 0.99), a precision of 0.7450 (95% CI: 0.64, 0.88), and a sensitivity of 0.76 (95% CI: 0.66, 0.91). The model correctly localized the LVO in at least one frame in 13 of the 14 LVO-positive patients in the test set. The model achieved a precision of 0.67 (95% CI: 0.52, 0.79), recall of 0.69 (95% CI: 0.46, 0.81), and a mean average precision of 0.75 (95% CI: 0.56, 0.91). CONCLUSION: This work demonstrates that a deep learning strategy using a limited dataset can generate effective representations used to identify LVOs. Generating an expanded and more complete dataset of LVOs with obstructed LVOs is likely the best way to improve the model's ability to localize LVOs.

Exploring the evolution of research connectivity and funding in global neurosurgical publications.

BACKGROUND AND OBJECTIVES: There are critical disparities in the neurosurgical care provided around the globe due to challenges in resource allocation, training, and infrastructure. Global neurosurgical collaborations have replaced classical mission trips to address these disparities. However, the development of these collaborations and the impact of research funding on their growth has not yet been systematically studied. In this article, we use a graph theoretical approach to investigate trends in funding and co-authorship between and among authors from high-income countries (HICs) and authors from low- and middle-income countries (LMICs). METHODS: A bibliometric search of the global neurosurgical literature returned 307 articles between 1985 and 2020. A connectivity analysis was conducted to compute the number of co-authorships between HIC-HIC, LMIC-HIC, and LMIC-LMIC authors. The number of connections, summarized as either a global sum of connections or an average number of connections per manuscript, were analyzed in the context of time and funding through parametric statistical tests. RESULTS: An exponential increase in co-authorship collaboration was observed over time, especially after 2015. Notably, LMIC-LMIC collaborations appear to be rising at over twice the rate of other collaboration types. The presence of funding, in general, was associated with increased co-authorship of manuscripts by LMIC and HIC authors together (p = 0.033). A significant majority of the funding associated with LMIC-HIC co-authorships was supplied through charitable organizations and government grants (p = 0.034, p = 0.009, respectively). Most LMIC-LMIC co-authorships had no funding. CONCLUSION: This work shows significant and rapid growth in international neurosurgical partnerships, especially in HIC-LMIC and LMIC-LMIC collaborations. Also, a significant positive relationship exists between research funding and LMIC-HIC co-authorship trends. This work encourages us as a community to continue to expand our translational collaborations with LMIC neurosurgeons and establish funding mechanisms independent of HIC authors.

A multi-institutional meningioma MRI dataset for automated multi-sequence image segmentation.

Meningiomas are the most common primary intracranial tumors and can be associated with significant morbidity and mortality. Radiologists, neurosurgeons, neuro-oncologists, and radiation oncologists rely on brain MRI for diagnosis, treatment planning, and longitudinal treatment monitoring. However, automated, objective, and quantitative tools for non-invasive assessment of meningiomas on multi-sequence MR images are not available. Here we present the BraTS Pre-operative Meningioma Dataset, as the largest multi-institutional expert annotated multilabel meningioma multi-sequence MR image dataset to date. This dataset includes 1,141 multi-sequence MR images from six sites, each with four structural MRI sequences (T2-, T2/FLAIR-, pre-contrast T1-, and post-contrast T1-weighted) accompanied by expert manually refined segmentations of three distinct meningioma sub-compartments: enhancing tumor, non-enhancing tumor, and surrounding non-enhancing T2/FLAIR hyperintensity. Basic demographic data are provided including age at time of initial imaging, sex, and CNS WHO grade. The goal of releasing this dataset is to facilitate the development of automated computational methods for meningioma segmentation and expedite their incorporation into clinical practice, ultimately targeting improvement in the care of meningioma patients.

External Validation of an Artificial Intelligence Device for Intracranial Hemorrhage Detection.

BACKGROUND: Artificial intelligence applications have gained traction in the field of cerebrovascular disease by assisting in the triage, classification, and prognostication of both ischemic and hemorrhagic stroke. The Caire ICH system aims to be the first device to move into the realm of assisted diagnosis for intracranial hemorrhage (ICH) and its subtypes. METHODS: A single-center retrospective dataset of 402 head noncontrast CT scans (NCCT) with an intracranial hemorrhage were retrospectively collected from January 2012 to July 2020; an additional 108 NCCT scans with no intracranial hemorrhage findings were also included. The presence of an ICH and its subtype were determined from the International Classification of Diseases-10 code associated with the scan and validated by an expert panel. We used the Caire ICH vR1 to analyze these scans, and we evaluated its performance in terms of accuracy, sensitivity, and specificity. RESULTS: We found the Caire ICH system to have an accuracy of 98.05% (95% confidence interval [CI]: 96.44%-99.06%), a sensitivity of 97.52% (95% CI: 95.50%-98.81%), and a specificity of 100% (95% CI: 96.67%-100.00%) in the detection of ICH. Experts reviewed the 10 incorrectly classified scans. CONCLUSIONS: The Caire ICH vR1 algorithm was highly accurate, sensitive, and specific in detecting the presence or absence of an ICH and its subtypes in NCCTs. This work suggests that the Caire ICH device has potential to minimize clinical errors in ICH diagnosis that could improve patient outcomes and current workflows as both a point-of-care tool for diagnostics and as a safety net for radiologists.

The ASNR-MICCAI Brain Tumor Segmentation (BraTS) Challenge 2023: Intracranial Meningioma.

Meningiomas are the most common primary intracranial tumor in adults and can be associated with significant morbidity and mortality. Radiologists, neurosurgeons, neuro-oncologists, and radiation oncologists rely on multiparametric MRI (mpMRI) for diagnosis, treatment planning, and longitudinal treatment monitoring; yet automated, objective, and quantitative tools for non-invasive assessment of meningiomas on mpMRI are lacking. The BraTS meningioma 2023 challenge will provide a community standard and benchmark for state-of-the-art automated intracranial meningioma segmentation models based on the largest expert annotated multilabel meningioma mpMRI dataset to date. Challenge competitors will develop automated segmentation models to predict three distinct meningioma sub-regions on MRI including enhancing tumor, non-enhancing tumor core, and surrounding nonenhancing T2/FLAIR hyperintensity. Models will be evaluated on separate validation and held-out test datasets using standardized metrics utilized across the BraTS 2023 series of challenges including the Dice similarity coefficient and Hausdorff distance. The models developed during the course of this challenge will aid in incorporation of automated meningioma MRI segmentation into clinical practice, which will ultimately improve care of patients with meningioma.

Machine Learning for Predicting In-Hospital Mortality After Traumatic Brain Injury in Both High-Income and Low- and Middle-Income Countries.

BACKGROUND: Machine learning (ML) holds promise as a tool to guide clinical decision making by predicting in-hospital mortality for patients with traumatic brain injury (TBI). Previous models such as the international mission for prognosis and clinical trials in TBI (IMPACT) and the corticosteroid randomization after significant head injury (CRASH) prognosis calculators can potentially be improved with expanded clinical features and newer ML approaches. OBJECTIVE: To develop ML models to predict in-hospital mortality for both the high-income country (HIC) and the low- and middle-income country (LMIC) settings. METHODS: We used the Duke University Medical Center National Trauma Data Bank and Mulago National Referral Hospital (MNRH) registry to predict in-hospital mortality for the HIC and LMIC settings, respectively. Six ML models were built on each data set, and the best model was chosen through nested cross-validation. The CRASH and IMPACT models were externally validated on the MNRH database. RESULTS: ML models built on National Trauma Data Bank (n = 5393, 84 predictors) demonstrated an area under the receiver operating curve (AUROC) of 0.91 (95% CI: 0.85-0.97) while models constructed on MNRH (n = 877, 31 predictors) demonstrated an AUROC of 0.89 (95% CI: 0.81-0.97). Direct comparison with CRASH and IMPACT models showed significant improvement of the proposed LMIC models regarding AUROC (P = .038). CONCLUSION: We developed high-performing well-calibrated ML models for predicting in-hospital mortality for both the HIC and LMIC settings that have the potential to influence clinical management and traumatic brain injury patient trajectories.

Deep Learning to Predict Traumatic Brain Injury Outcomes in the Low-Resource Setting.

OBJECTIVE: Traumatic brain injury (TBI) disproportionately affects low- and middle-income countries (LMICs). In these settings, accurate patient prognostication is both difficult and essential for high-quality patient care. With the ultimate goal of enhancing TBI triage in LMICs, we aim to develop the first deep learning model to predict outcomes after TBI and compare its performance with that of less complex algorithms. METHODS: TBI patients' data were prospectively collected in Kampala, Uganda, from 2016 to 2020. To predict good versus poor outcome at hospital discharge, we created deep neural network, shallow neural network, and elastic-net regularized logistic regression models. Predictors included 13 easily acquirable clinical variables. We assessed model performance with 5-fold cross-validation to calculate areas under both the receiver operating characteristic curve and precision-recall curve (AUPRC), in addition to standardized partial AUPRC to focus on comparisons at clinically relevant operating points. RESULTS: We included 2164 patients for model training, of which 12% had poor outcomes. The deep neural network performed best as measured by the area under the receiver operating characteristic curve (0.941) and standardized partial AUPRC in region maximizing recall (0.291), whereas the shallow neural network was best by the area under the precision-recall curve (0.770). In several other comparisons, the elastic-net regularized logistic regression was noninferior to the neural networks. CONCLUSIONS: We present the first use of deep learning for TBI prognostication, with an emphasis on LMICs, where there is great need for decision support to allocate limited resources. Optimal algorithm selection depends on the specific clinical setting; deep learning is not a panacea, though it may have a role in these efforts.

Machine Learning for Predicting Discharge Disposition After Traumatic Brain Injury.

BACKGROUND: Current traumatic brain injury (TBI) prognostic calculators are commonly used to predict the mortality and Glasgow Outcome Scale, but these outcomes are most relevant for severe TBI. Because mild and moderate TBI rarely reaches severe outcomes, there is a need for novel prognostic endpoints. OBJECTIVE: To generate machine learning (ML) models with a strong predictive capacity for trichotomized discharge disposition, an outcome not previously used in TBI prognostic models. The outcome can serve as a proxy for patients' functional status, even in mild and moderate patients with TBI. METHODS: Using a large data set (n = 5292) of patients with TBI from a quaternary care center and 84 predictors, including vitals, demographics, mechanism of injury, initial Glasgow Coma Scale, and comorbidities, we trained 6 different ML algorithms using a nested-stratified-cross-validation protocol. After optimizing hyperparameters and performing model selection, isotonic regression was applied to calibrate models. RESULTS: When maximizing the microaveraged area under the receiver operating characteristic curve during hyperparameter optimization, a random forest model exhibited top performance. A random forest model was also selected when maximizing the microaveraged area under the precision-recall curve. For both models, the weighted average area under the receiver operating characteristic curves was 0.84 (95% CI 0.81-0.87) and the weighted average area under the precision-recall curves was 0.85 (95% CI 0.82-0.88). CONCLUSION: Our group presents high-performing ML models to predict trichotomized discharge disposition. These models can assist in optimization of patient triage and treatment, especially in cases of mild and moderate TBI.

The Scope, Growth, and Inequities of the Global Neurosurgery Literature: A Bibliometric Analysis.

BACKGROUND: Here, we evaluate the evolution and growth of global neurosurgery publications over time, further focusing on the contributions and impact of authors in low- and middle-income countries (LMICs). METHODS: In this systematic bibliometric analysis, we conducted a two-stage blinded screening process of global neurosurgery publications from 5 databases from inception through July 2021. Articles involving multi-national/multi-institutional research collaborations, detailing any area of global neurosurgery collaboration, or influencing global neurosurgery practice were included. Statistical hypothesis testing was conducted to analyze trends and hypotheses of LMIC authorship contributions. RESULTS: The number of global neurosurgery publications has soared in the last decade. Overall, authors from HIC countries were most commonly from the US (41.1%), Canada (4.0%), and the UK (3.9%), while authors from LMIC countries were most commonly from Uganda (4.2%), Tanzania (2.6%), Cameroon (1.8%), and India (1.8%). Over a quarter (28%) of publications had no LMIC authors, while only 11% had 3 or more LMIC authors. The proportion of LMIC authors (LMIC-R) was not correlated with the citation rate of individual articles or with the year of publication, and a positive trend emerged when the LMIC-R of top-publishing LMICs was individually examined and compared to the year of publication. CONCLUSIONS: Despite recent growth, the number of global neurosurgery publications arising from LMICs pales in comparison to those from HICs. Collaborative efforts between certain HICs and LMICs have likely contributed to the observed increase in LMIC author independence over time.

Deep Learning System Boosts Radiologist Detection of Intracranial Hemorrhage.

BACKGROUND: Intracranial hemorrhage (ICH) requires emergent medical treatment for positive outcomes. While previous artificial intelligence (AI) solutions achieved rapid diagnostics, none were shown to improve the performance of radiologists in detecting ICHs. Here, we show that the Caire ICH artificial intelligence system enhances a radiologist's ICH diagnosis performance. METHODS: A dataset of non-contrast-enhanced axial cranial computed tomography (CT) scans (n=532) were labeled for the presence or absence of an ICH. If an ICH was detected, its ICH subtype was identified. After a washout period, the three radiologists reviewed the same dataset with the assistance of the Caire ICH system. Performance was measured with respect to reader agreement, accuracy, sensitivity, and specificity when compared to the ground truth, defined as reader consensus. RESULTS: Caire ICH improved the inter-reader agreement on average by 5.76% in a dataset with an ICH prevalence of 74.3%. Further, radiologists using Caire ICH detected an average of 18 more ICHs and significantly increased their accuracy by 6.15%, their sensitivity by 4.6%, and their specificity by 10.62%. The Caire ICH system also improved the radiologist's ability to accurately identify the ICH subtypes present. CONCLUSION: The Caire ICH device significantly improves the performance of a cohort of radiologists. Such a device has the potential to be a tool that can improve patient outcomes and reduce misdiagnosis of ICH.

Machine Learning to Predict Successful Opioid Dose Reduction or Stabilization After Spinal Cord Stimulation.

BACKGROUND: Spinal cord stimulation (SCS) effectively reduces opioid usage in some patients, but preoperatively, there is no objective measure to predict who will most benefit. OBJECTIVE: To predict successful reduction or stabilization of opioid usage after SCS using machine learning models we developed and to assess if deep learning provides a significant benefit over logistic regression (LR). METHODS: We used the IBM MarketScan national databases to identify patients undergoing SCS from 2010 to 2015. Our models predict surgical success as defined by opioid dose stability or reduction 1 year after SCS. We incorporated 30 predictors, primarily regarding medication patterns and comorbidities. Two machine learning algorithms were applied: LR with recursive feature elimination and deep neural networks (DNNs). To compare model performances, we used nested 5-fold cross-validation to calculate area under the receiver operating characteristic curve (AUROC). RESULTS: The final cohort included 7022 patients, of whom 66.9% had successful surgery. Our 5-variable LR performed comparably with the full 30-variable version (AUROC difference <0.01). The DNN and 5-variable LR models demonstrated similar AUROCs of 0.740 (95% CI, 0.727-0.753) and 0.737 (95% CI, 0.728-0.746) ( P = .25), respectively. The simplified model can be accessed at SurgicalML.com . CONCLUSION: We present the first machine learning-based models for predicting reduction or stabilization of opioid usage after SCS. The DNN and 5-variable LR models demonstrated comparable performances, with the latter revealing significant associations with patients' pre-SCS pharmacologic patterns. This simplified, interpretable LR model may augment patient and surgeon decision making regarding SCS.

Interpretable Artificial Intelligence for COVID-19 Diagnosis from Chest CT Reveals Specificity of Ground-Glass Opacities.

Background The use of CT imaging enhanced by artificial intelligence to effectively diagnose COVID-19, instead of or in addition to reverse transcription-polymerase chain reaction (RT-PCR), can improve widespread COVID-19 detection and resource allocation. Methods 904 axial lung window CT slices from 338 patients in 17 countries were collected and labeled. The data included 606 images from COVID-19 positive patients (confirmed via RT-PCR), 224 images of a variety of other pulmonary diseases including viral pneumonias, and 74 images of normal patients. We developed, trained, validated, and tested an object detection model which detects features in three categories: ground-glass opacities (GGOs) for COVID-19, GGOs for non-COVID-19 diseases, and features that are inconsistent with a COVID-19 diagnosis. These collected features are passed into an interpretable decision tree model to make a suggested diagnosis. Results On an independent test of 219 images from COVID-19 positive, a variety of pneumonia, and healthy patients, the model predicted COVID-19 diagnoses with an accuracy of 96.80 % (95% confidence interval [CI], 96.75 to 96.86) , AUC-ROC of 0.9664 (95% CI, 0.9659 to 0.9671) , sensitivity of 98.33% (95% CI, 98.29 to 98.40) , precision of 95.93% (95% CI, 95.83 to 95.99), and specificity of 94.95% (95% CI, 94.84 to 95.05). On an independent test of 34 images from asymptomatic COVID-19 positive patients, our model achieved an accuracy of 97.06% (95% CI, 96.81 to 97.06) and a sensitivity of 96.97% (95% CI, 96.71 to 96.97). Similarly high performance was also obtained for out-of-sample countries, and no significant performance difference was obtained between genders. Conclusion We present an interpretable artificial intelligence CT analysis tool to diagnose COVID-19 in both symptomatic and asymptomatic patients. Further, our model is able to differentiate COVID-19 GGOs from similar pathologies suggesting that GGOs can be disease-specific.

Fractionated follow-up chemotherapy delays the onset of resistance in bone metastatic prostate cancer.

Prostate cancer to bone metastases are almost always lethal. This results from the ability of metastatic prostate cancer cells to co-opt bone remodeling leading to what is known as the vicious cycle. Understanding how tumor cells can disrupt bone homeostasis through their interactions with the stroma and how metastatic tumors respond to treatment is key to the development of new treatments for what remains an incurable disease. Here we describe an evolutionary game theoretical model of both the homeostatic bone remodeling and its co-option by prostate cancer metastases. This model extends past the evolutionary aspects typically considered in game theoretical models by also including ecological factors such as the physical microenvironment of the bone. Our model recapitulates the current paradigm of the "vicious cycle" driving tumor growth and sheds light on the interactions of heterogeneous tumor cells with the bone microenvironment and treatment response. Our results show that resistant populations naturally become dominant in the metastases under conventional cytotoxic treatment and that novel schedules could be used to better control the tumor and the associated bone disease compared to the current standard of care. Specifically, we introduce fractionated follow up therapy - chemotherapy where dosage is administered initially in one solid block followed by alternating smaller doeses and holidays - and argue that it is better than either a continuous application or a periodic one. Furthermore, we also show that different regimens of chemotherapy can lead to different amounts of pathological bone that are known to correlate with poor quality of life for bone metastatic prostate cancer patients.