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.

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.

Concomitant Traumatic Brain Injury Delays Surgery in Patients With Traumatic Spinal Cord Injury.

BACKGROUND AND OBJECTIVES: Growing evidence supports prompt surgical decompression for patients with traumatic spinal cord injury (tSCI). Rates of concomitant tSCI and traumatic brain injury (TBI) range from 10% to 30%. Concomitant TBI may delay tSCI diagnosis and surgical intervention. Little is known about real-world management of this common injury constellation that carries significant clinical consequences. This study aimed to quantify the impact of concomitant TBI on surgical timing in a national cohort of patients with tSCI. METHODS: Patient data were obtained from the National Trauma Data Bank (2007-2016). Patients admitted for tSCI and who received surgical intervention were included. Delayed surgical intervention was defined as surgery after 24 hours of admission. Multivariable hierarchical regression models were constructed to measure the risk-adjusted association between concomitant TBI and delayed surgical intervention. Secondary outcome included favorable discharge status. RESULTS: We identified 14 964 patients with surgically managed tSCI across 377 North American trauma centers, of whom 2444 (16.3%) had concomitant TBI and 4610 (30.8%) had central cord syndrome (CCS). The median time to surgery was 20.0 hours for patients without concomitant TBI and 24.8 hours for patients with concomitant TBI. Hierarchical regression modeling revealed that concomitant TBI was independently associated with delayed surgery in patients with tSCI (odds ratio [OR], 1.3; 95% CI, 1.1-1.6). Although CCS was associated with delayed surgery (OR, 1.5; 95% CI, 1.4-1.7), we did not observe a significant interaction between concomitant TBI and CCS. In the subset of patients with concomitant tSCI and TBI, patients with severe TBI were significantly more likely to experience a surgical delay than patients with mild TBI (OR, 1.4; 95% CI, 1.0-1.9). CONCLUSION: Concomitant TBI delays surgical management for patients with tSCI. This effect is largest for patients with tSCI with severe TBI. These findings should serve to increase awareness of concomitant TBI and tSCI and the likelihood that this may delay time-sensitive surgery.

Augmented reality in spine surgery - past, present, and future.

BACKGROUND CONTEXT: Augmented reality (AR) is increasingly recognized as a valuable tool in spine surgery. Here we provides an overview of the key developments and technological milestones that have laid the foundation for AR applications in this field. We also assess the quality of existing studies on AR systems in spine surgery and explore potential future applications. PURPOSE: The purpose of this narrative review is to examine the role of AR in spine surgery. It aims to highlight the evolution of AR technology in this context, evaluate the existing body of research, and outline potential future directions for integrating AR into spine surgery. STUDY DESIGN: Narrative review. METHODS: We conducted a thorough literature search to identify studies and developments related to AR in spine surgery. Relevant articles, reports, and technological advancements were analyzed to establish the historical context and current state of AR in this field. RESULTS: The review identifies significant milestones in the development of AR technology for spine surgery. It discusses the growing body of research and highlights the strengths and weaknesses of existing investigations. Additionally, it presents insights into the potential for AR to enhance spine surgical education and speculates on future applications. CONCLUSIONS: Augmented reality has emerged as a promising adjunct in spine surgery, with notable advancements and research efforts. The integration of AR into the spine surgery operating room holds promise, as does its potential to revolutionize surgical education. Future applications of AR in spine surgery may include real-time navigation, enhanced visualization, and improved patient outcomes. Continued development and evaluation of AR technology are essential for its successful implementation in this specialized surgical field.

Machine learning predictive models in neurosurgery: an appraisal based on the TRIPOD guidelines. Systematic review.

OBJECTIVE: In recent years, machine learning models for clinical prediction have become increasingly prevalent in the neurosurgical literature. However, little is known about the quality of these models, and their translation to clinical care has been limited. The aim of this systematic review was to empirically determine the adherence of machine learning models in neurosurgery with standard reporting guidelines specific to clinical prediction models. METHODS: Studies describing the development or validation of machine learning predictive models published between January 1, 2020, and January 10, 2023, across five neurosurgery journals (Journal of Neurosurgery, Journal of Neurosurgery: Spine, Journal of Neurosurgery: Pediatrics, Neurosurgery, and World Neurosurgery) were included. Studies where the TRIPOD (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis) guidelines were not applicable, radiomic studies, and natural language processing studies were excluded. RESULTS: Forty-seven studies featuring a machine learning-based predictive model in neurosurgery were included. The majority (53%) of studies were single-center studies, and only 15% of studies externally validated the model in an independent cohort of patients. The median compliance across all 47 studies was 82.1% (IQR 75.9%-85.7%). Giving details of treatment (n = 17 [36%]), including the number of patients with missing data (n = 11 [23%]), and explaining the use of the prediction model (n = 23 [49%]) were identified as the TRIPOD criteria with the lowest rates of compliance. CONCLUSIONS: Improved adherence to TRIPOD guidelines will increase transparency in neurosurgical machine learning predictive models and streamline their translation into clinical care.

Phosphorylation barcodes direct biased chemokine signaling at CXCR3.

G protein-coupled receptor (GPCR)-biased agonism, selective activation of certain signaling pathways relative to others, is thought to be directed by differential GPCR phosphorylation "barcodes." At chemokine receptors, endogenous chemokines can act as "biased agonists", which may contribute to the limited success when pharmacologically targeting these receptors. Here, mass spectrometry-based global phosphoproteomics revealed that CXCR3 chemokines generate different phosphorylation barcodes associated with differential transducer activation. Chemokine stimulation resulted in distinct changes throughout the kinome in global phosphoproteomics studies. Mutation of CXCR3 phosphosites altered ß-arrestin 2 conformation in cellular assays and was consistent with conformational changes observed in molecular dynamics simulations. T cells expressing phosphorylation-deficient CXCR3 mutants resulted in agonist- and receptor-specific chemotactic profiles. Our results demonstrate that CXCR3 chemokines are non-redundant and act as biased agonists through differential encoding of phosphorylation barcodes, leading to distinct physiological processes.

Phosphorylation barcodes direct biased chemokine signaling at CXCR3.

G protein-coupled receptor (GPCR) biased agonism, the activation of some signaling pathways over others, is thought to largely be due to differential receptor phosphorylation, or "phosphorylation barcodes." At chemokine receptors, ligands act as "biased agonists" with complex signaling profiles, which contributes to the limited success in pharmacologically targeting these receptors. Here, mass spectrometry-based global phosphoproteomics revealed that CXCR3 chemokines generate different phosphorylation barcodes associated with differential transducer activation. Chemokine stimulation resulted in distinct changes throughout the kinome in global phosphoproteomic studies. Mutation of CXCR3 phosphosites altered ß-arrestin conformation in cellular assays and was confirmed by molecular dynamics simulations. T cells expressing phosphorylation-deficient CXCR3 mutants resulted in agonist- and receptor-specific chemotactic profiles. Our results demonstrate that CXCR3 chemokines are non-redundant and act as biased agonists through differential encoding of phosphorylation barcodes and lead to distinct physiological processes.

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.

Single-Cell Analysis Reveals Distinct Immune and Smooth Muscle Cell Populations that Contribute to Chronic Thromboembolic Pulmonary Hypertension.

Rationale: Chronic thromboembolic pulmonary hypertension (CTEPH) is a sequela of acute pulmonary embolism (PE) in which the PE remodels into a chronic scar in the pulmonary arteries. This results in vascular obstruction, pulmonary microvasculopathy, and pulmonary hypertension. Objectives: Our current understanding of CTEPH pathobiology is primarily derived from cell-based studies limited by the use of specific cell markers or phenotypic modulation in cell culture. Therefore, our main objective was to identify the multiple cell types that constitute CTEPH thrombusy and to study their dysfunction. Methods: Here we used single-cell RNA sequencing of tissue removed at the time of pulmonary endarterectomy surgery from five patients to identify the multiple cell types. Using in vitro assays, we analyzed differences in phenotype between CTEPH thrombus and healthy pulmonary vascular cells. We studied potential therapeutic targets in cells isolated from CTEPH thrombus. Measurements and Main Results: Single-cell RNA sequencing identified multiple cell types, including macrophages, T cells, and smooth muscle cells (SMCs), that constitute CTEPH thrombus. Notably, multiple macrophage subclusters were identified but broadly split into two categories, with the larger group characterized by an upregulation of inflammatory signaling predicted to promote pulmonary vascular remodeling. CD4+ and CD8+ T cells were identified and likely contribute to chronic inflammation in CTEPH. SMCs were a heterogeneous population, with a cluster of myofibroblasts that express markers of fibrosis and are predicted to arise from other SMC clusters based on pseudotime analysis. Additionally, cultured endothelial, smooth muscle, and myofibroblast cells isolated from CTEPH fibrothrombotic material have distinct phenotypes from control cells with regard to angiogenic potential and rates of proliferation and apoptosis. Last, our analysis identified PAR1 (protease-activated receptor 1) as a potential therapeutic target that links thrombosis to chronic PE in CTEPH, with PAR1 inhibition decreasing SMC and myofibroblast proliferation and migration. Conclusions: These findings suggest a model for CTEPH similar to atherosclerosis, with chronic inflammation promoted by macrophages and T cells driving vascular remodeling through SMC modulation, and suggest new approaches for pharmacologically targeting this disease.

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.

Location bias contributes to functionally selective responses of biased CXCR3 agonists.

Some G protein-coupled receptor (GPCR) ligands act as "biased agonists" that preferentially activate specific signaling transducers over others. Although GPCRs are primarily found at the plasma membrane, GPCRs can traffic to and signal from many subcellular compartments. Here, we determine that differential subcellular signaling contributes to the biased signaling generated by three endogenous ligands of the GPCR CXC chemokine receptor 3 (CXCR3). The signaling profile of CXCR3 changes as it traffics from the plasma membrane to endosomes in a ligand-specific manner. Endosomal signaling is critical for biased activation of G proteins, ß-arrestins, and extracellular-signal-regulated kinase (ERK). In CD8 + T cells, the chemokines promote unique transcriptional responses predicted to regulate inflammatory pathways. In a mouse model of contact hypersensitivity, ß-arrestin-biased CXCR3-mediated inflammation is dependent on receptor internalization. Our work demonstrates that differential subcellular signaling is critical to the overall biased response observed at CXCR3, which has important implications for drugs targeting chemokine receptors and other GPCRs.

Biased agonists of the chemokine receptor CXCR3 differentially signal through Gαi:ß-arrestin complexes.

G protein-coupled receptors (GPCRs) are the largest family of cell surface receptors and signal through the proximal effectors, G proteins and ß-arrestins, to influence nearly every biological process. The G protein and ß-arrestin signaling pathways have largely been considered separable; however, direct interactions between Gα proteins and ß-arrestins have been described that appear to be part of a distinct GPCR signaling pathway. Within these complexes, Gαi/o, but not other Gα protein subtypes, directly interacts with ß-arrestin, regardless of the canonical Gα protein that is coupled to the GPCR. Here, we report that the endogenous biased chemokine agonists of CXCR3 (CXCL9, CXCL10, and CXCL11), together with two small-molecule biased agonists, differentially formed Gαi:ß-arrestin complexes. Formation of the Gαi:ß-arrestin complexes did not correlate well with either G protein activation or ß-arrestin recruitment. ß-arrestin biosensors demonstrated that ligands that promoted Gαi:ß-arrestin complex formation generated similar ß-arrestin conformations. We also found that Gαi:ß-arrestin complexes did not couple to the mitogen-activated protein kinase ERK, as is observed with other receptors such as the V2 vasopressin receptor, but did couple with the clathrin adaptor protein AP-2, which suggests context-dependent signaling by these complexes. These findings reinforce the notion that Gαi:ß-arrestin complex formation is a distinct GPCR signaling pathway and enhance our understanding of the spectrum of biased agonism.

Noncanonical scaffolding of Gαi and ß-arrestin by G protein-coupled receptors.

Heterotrimeric guanine nucleotide-binding protein (G protein)-coupled receptors (GPCRs) are common drug targets and canonically couple to specific Gα protein subtypes and ß-arrestin adaptor proteins. G protein-mediated signaling and ß-arrestin-mediated signaling have been considered separable. We show here that GPCRs promote a direct interaction between Gαi protein subtype family members and ß-arrestins regardless of their canonical Gα protein subtype coupling. Gαi:ß-arrestin complexes bound extracellular signal-regulated kinase (ERK), and their disruption impaired both ERK activation and cell migration, which is consistent with ß-arrestins requiring a functional interaction with Gαi for certain signaling events. These results introduce a GPCR signaling mechanism distinct from canonical G protein activation in which GPCRs cause the formation of Gαi:ß-arrestin signaling complexes.

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.