iGWAS: Image-based genome-wide association of self-supervised deep phenotyping of retina fundus images.

Existing imaging genetics studies have been mostly limited in scope by using imaging-derived phenotypes defined by human experts. Here, leveraging new breakthroughs in self-supervised deep representation learning, we propose a new approach, image-based genome-wide association study (iGWAS), for identifying genetic factors associated with phenotypes discovered from medical images using contrastive learning. Using retinal fundus photos, our model extracts a 128-dimensional vector representing features of the retina as phenotypes. After training the model on 40,000 images from the EyePACS dataset, we generated phenotypes from 130,329 images of 65,629 British White participants in the UK Biobank. We conducted GWAS on these phenotypes and identified 14 loci with genome-wide significance (p<5×10-8 and intersection of hits from left and right eyes). We also did GWAS on the retina color, the average color of the center region of the retinal fundus photos. The GWAS of retina colors identified 34 loci, 7 are overlapping with GWAS of raw image phenotype. Our results establish the feasibility of this new framework of genomic study based on self-supervised phenotyping of medical images.

Machine Learning Automated Detection of Large Vessel Occlusion From Mobile Stroke Unit Computed Tomography Angiography.

BACKGROUND: Prehospital automated large vessel occlusion (LVO) detection in Mobile Stroke Units (MSUs) could accelerate identification and treatment of patients with LVO acute ischemic stroke. Here, we evaluate the performance of a machine learning (ML) model on CT angiograms (CTAs) obtained from 2 MSUs to detect LVO. METHODS: Patients evaluated on MSUs in Houston and Los Angeles with out-of-hospital CTAs were identified. Anterior circulation LVO was defined as an occlusion of the intracranial internal carotid artery, middle cerebral artery (M1 or M2), or anterior cerebral artery vessels and determined by an expert human reader. A ML model to detect LVO was trained and tested on independent data sets consisting of in-hospital CTAs and then tested on MSU CTA images. Model performance was determined using area under the receiver-operator curve statistics. RESULTS: Among 68 patients with out-of-hospital MSU CTAs, 40% had an LVO. The most common occlusion location was the middle cerebral artery M1 segment (59%), followed by the internal carotid artery (30%), and middle cerebral artery M2 (11%). Median time from last known well to CTA imaging was 88.0 (interquartile range, 59.5-196.0) minutes. After training on 870 in-hospital CTAs, the ML model performed well in identifying LVO in a separate in-hospital data set of 441 images with area under receiver-operator curve of 0.84 (95% CI, 0.80-0.87). ML algorithm analysis time was under 1 minute. The performance of the ML model on the MSU CTA images was comparable with area under receiver-operator curve 0.80 (95% CI, 0.71-0.89). There was no significant difference in performance between the Houston and Los Angeles MSU CTA cohorts. CONCLUSIONS: In this study of patients evaluated on MSUs in 2 cities, a ML algorithm was able to accurately and rapidly detect LVO using prehospital CTA acquisitions.

Automated prediction of final infarct volume in patients with large-vessel occlusion acute ischemic stroke.

OBJECTIVE: In patients with large-vessel occlusion (LVO) acute ischemic stroke (AIS), determinations of infarct size play a key role in the identification of candidates for endovascular stroke therapy (EVT). An accurate, automated method to quantify infarct at the time of presentation using widely available imaging modalities would improve screening for EVT. Here, the authors aimed to compare the performance of three measures of infarct core at presentation, including an automated method using machine learning. METHODS: Patients with LVO AIS who underwent successful EVT at four comprehensive stroke centers were identified. Patients were included if they underwent concurrent noncontrast head CT (NCHCT), CT angiography (CTA), and CT perfusion (CTP) with Rapid imaging at the time of presentation, and MRI 24 to 48 hours after reperfusion. NCHCT scans were analyzed using the Alberta Stroke Program Early CT Score (ASPECTS) graded by neuroradiology or neurology expert readers. CTA source images were analyzed using a previously described machine learning model named DeepSymNet (DSN). Final infarct volume (FIV) was determined from diffusion-weighted MRI sequences using manual segmentation. The primary outcome was the performance of the three infarct core measurements (NCHCT-ASPECTS, CTA with DSN, and CTP-Rapid) to predict FIV, which was measured using area under the receiver operating characteristic (ROC) curve (AUC) analysis. RESULTS: Among 76 patients with LVO AIS who underwent EVT and met inclusion criteria, the median age was 67 years (IQR 54-76 years), 45% were female, and 37% were White. The median National Institutes of Health Stroke Scale score was 16 (IQR 12-22), and the median NCHCT-ASPECTS on presentation was 8 (IQR 7-8). The median time between when the patient was last known to be well and arrival was 156 minutes (IQR 73-303 minutes), and between NCHCT/CTA/CTP to groin puncture was 73 minutes (IQR 54-81 minutes). The AUC was obtained at three different cutoff points: 10 ml, 30 ml, and 50 ml FIV. At the 50-ml FIV cutoff, the AUC of ASPECTS was 0.74; of CTP core volume, 0.72; and of DSN, 0.82. Differences in AUCs for the three predictors were not significant for the three FIV cutoffs. CONCLUSIONS: In a cohort of patients with LVO AIS in whom reperfusion was achieved, determinations of infarct core at presentation by NCHCT-ASPECTS and a machine learning model analyzing CTA source images were equivalent to CTP in predicting FIV. These findings have suggested that the information to accurately predict infarct core in patients with LVO AIS was present in conventional imaging modalities (NCHCT and CTA) and accessible by machine learning methods.

Novel Autosegmentation Spatial Similarity Metrics Capture the Time Required to Correct Segmentations Better Than Traditional Metrics in a Thoracic Cavity Segmentation Workflow.

Automated segmentation templates can save clinicians time compared to de novo segmentation but may still take substantial time to review and correct. It has not been thoroughly investigated which automated segmentation-corrected segmentation similarity metrics best predict clinician correction time. Bilateral thoracic cavity volumes in 329 CT scans were segmented by a UNet-inspired deep learning segmentation tool and subsequently corrected by a fourth-year medical student. Eight spatial similarity metrics were calculated between the automated and corrected segmentations and associated with correction times using Spearman's rank correlation coefficients. Nine clinical variables were also associated with metrics and correction times using Spearman's rank correlation coefficients or Mann-Whitney U tests. The added path length, false negative path length, and surface Dice similarity coefficient correlated better with correction time than traditional metrics, including the popular volumetric Dice similarity coefficient (respectively ρ = 0.69, ρ = 0.65, ρ = - 0.48 versus ρ = - 0.25; correlation p values < 0.001). Clinical variables poorly represented in the autosegmentation tool's training data were often associated with decreased accuracy but not necessarily with prolonged correction time. Metrics used to develop and evaluate autosegmentation tools should correlate with clinical time saved. To our knowledge, this is only the second investigation of which metrics correlate with time saved. Validation of our findings is indicated in other anatomic sites and clinical workflows. Novel spatial similarity metrics may be preferable to traditional metrics for developing and evaluating autosegmentation tools that are intended to save clinicians time.

Machine Learning-Enabled Automated Determination of Acute Ischemic Core From Computed Tomography Angiography.

Background and Purpose- The availability of and expertise to interpret advanced neuroimaging recommended in the guideline-based endovascular stroke therapy (EST) evaluation are limited. Here, we develop and validate an automated machine learning-based method that evaluates for large vessel occlusion (LVO) and ischemic core volume in patients using a widely available modality, computed tomography angiogram (CTA). Methods- From our prospectively maintained stroke registry and electronic medical record, we identified patients with acute ischemic stroke and stroke mimics with contemporaneous CTA and computed tomography perfusion (CTP) with RAPID (IschemaView) post-processing as a part of the emergent stroke workup. A novel convolutional neural network named DeepSymNet was created and trained to identify LVO as well as infarct core from CTA source images, against CTP-RAPID definitions. Model performance was measured using 10-fold cross validation and receiver-operative curve area under the curve (AUC) statistics. Results- Among the 297 included patients, 224 (75%) had acute ischemic stroke of which 179 (60%) had LVO. Mean CTP-RAPID ischemic core volume was 23±42 mL. LVO locations included internal carotid artery (13%), M1 (44%), and M2 (21%). The DeepSymNet algorithm autonomously learned to identify the intracerebral vasculature on CTA and detected LVO with AUC 0.88. The method was also able to determine infarct core as defined by CTP-RAPID from the CTA source images with AUC 0.88 and 0.90 (ischemic core ≤30 mL and ≤50 mL). These findings were maintained in patients presenting in early (0-6 hours) and late (6-24 hours) time windows (AUCs 0.90 and 0.91, ischemic core ≤50 mL). DeepSymNet probabilities from CTA images corresponded with CTP-RAPID ischemic core volumes as a continuous variable with r=0.7 (Pearson correlation, P<0.001). Conclusions- These results demonstrate that the information needed to perform the neuroimaging evaluation for endovascular therapy with comparable accuracy to advanced imaging modalities may be present in CTA, and the ability of machine learning to automate the analysis.

Remote Monitoring of Treatment Response in Parkinson's Disease: The Habit of Typing on a Computer.

OBJECTIVE: The recent advances in technology are opening a new opportunity to remotely evaluate motor features in people with Parkinson's disease (PD). We hypothesized that typing on an electronic device, a habitual behavior facilitated by the nigrostriatal dopaminergic pathway, could allow for objectively and nonobtrusively monitoring parkinsonian features and response to medication in an at-home setting. METHODS: We enrolled 31 participants recently diagnosed with PD who were due to start dopaminergic treatment and 30 age-matched controls. We remotely monitored their typing pattern during a 6-month (24 weeks) follow-up period before and while dopaminergic medications were being titrated. The typing data were used to develop a novel algorithm based on recursive neural networks and detect participants' responses to medication. The latter were defined by the Unified Parkinson's Disease Rating Scale-III (UPDRS-III) minimal clinically important difference. Furthermore, we tested the accuracy of the algorithm to predict the final response to medication as early as 21 weeks prior to the final 6-month clinical outcome. RESULTS: The score on the novel algorithm based on recursive neural networks had an overall moderate kappa agreement and fair area under the receiver operating characteristic (ROC) curve with the time-coincident UPDRS-III minimal clinically important difference. The participants classified as responders at the final visit (based on the UPDRS-III minimal clinically important difference) had higher scores on the novel algorithm based on recursive neural networks when compared with the participants with stable UPDRS-III, from the third week of the study onward. CONCLUSIONS: This preliminary study suggests that remotely gathered unsupervised typing data allows for the accurate detection and prediction of drug response in PD. © 2019 International Parkinson and Movement Disorder Society.

Detecting Motor Impairment in Early Parkinson's Disease via Natural Typing Interaction With Keyboards: Validation of the neuroQWERTY Approach in an Uncontrolled At-Home Setting.

BACKGROUND: Parkinson's disease (PD) is the second most prevalent neurodegenerative disease and one of the most common forms of movement disorder. Although there is no known cure for PD, existing therapies can provide effective symptomatic relief. However, optimal titration is crucial to avoid adverse effects. Today, decision making for PD management is challenging because it relies on subjective clinical evaluations that require a visit to the clinic. This challenge has motivated recent research initiatives to develop tools that can be used by nonspecialists to assess psychomotor impairment. Among these emerging solutions, we recently reported the neuroQWERTY index, a new digital marker able to detect motor impairment in an early PD cohort through the analysis of the key press and release timing data collected during a controlled in-clinic typing task. OBJECTIVE: The aim of this study was to extend the in-clinic implementation to an at-home implementation by validating the applicability of the neuroQWERTY approach in an uncontrolled at-home setting, using the typing data from subjects' natural interaction with their laptop to enable remote and unobtrusive assessment of PD signs. METHODS: We implemented the data-collection platform and software to enable access and storage of the typing data generated by users while using their computer at home. We recruited a total of 60 participants; of these participants 52 (25 people with Parkinson's and 27 healthy controls) provided enough data to complete the analysis. Finally, to evaluate whether our in-clinic-built algorithm could be used in an uncontrolled at-home setting, we compared its performance on the data collected during the controlled typing task in the clinic and the results of our method using the data passively collected at home. RESULTS: Despite the randomness and sparsity introduced by the uncontrolled setting, our algorithm performed nearly as well in the at-home data (area under the receiver operating characteristic curve [AUC] of 0.76 and sensitivity/specificity of 0.73/0.69) as it did when used to evaluate the in-clinic data (AUC 0.83 and sensitivity/specificity of 0.77/0.72). Moreover, the keystroke metrics presented a strong correlation between the 2 typing settings, which suggests a minimal influence of the in-clinic typing task in users' normal typing. CONCLUSIONS: The finding that an algorithm trained on data from an in-clinic setting has comparable performance with that tested on data collected through naturalistic at-home computer use reinforces the hypothesis that subtle differences in motor function can be detected from typing behavior. This work represents another step toward an objective, user-convenient, and quasi-continuous monitoring tool for PD.

A self-supervised learning approach for registration agnostic imaging models with 3D brain CTA.

Deep learning-based neuroimaging pipelines for acute stroke typically rely on image registration, which not only increases computation but also introduces a point of failure. In this paper, we propose a general-purpose contrastive self-supervised learning method that converts a convolutional deep neural network designed for registered images to work on a different input domain, i.e., with unregistered images. This is accomplished by using a self-supervised strategy that does not rely on labels, where the original model acts as a teacher and a new network as a student. Large vessel occlusion (LVO) detection experiments using computed tomographic angiography (CTA) data from 402 CTA patients show the student model achieving competitive LVO detection performance (area under the receiver operating characteristic curve [AUC] = 0.88 vs. AUC = 0.81) compared to the teacher model, even with unregistered images. The student model trained directly on unregistered images using standard supervised learning achieves an AUC = 0.63, highlighting the proposed method's efficacy in adapting models to different pipelines and domains.

Generalizing Parkinson's disease detection using keystroke dynamics: a self-supervised approach.

OBJECTIVE: Passive monitoring of touchscreen interactions generates keystroke dynamic signals that can be used to detect and track neurological conditions such as Parkinson's disease (PD) and psychomotor impairment with minimal burden on the user. However, this typically requires datasets with clinically confirmed labels collected in standardized environments, which is challenging, especially for a large subject pool. This study validates the efficacy of a self-supervised learning method in reducing the reliance on labels and evaluates its generalizability. MATERIALS AND METHODS: We propose a new type of self-supervised loss combining Barlow Twins loss, which attempts to create similar feature representations with reduced feature redundancy for samples coming from the same subject, and a Dissimilarity loss, which promotes uncorrelated features for samples generated by different subjects. An encoder is first pre-trained using this loss on unlabeled data from an uncontrolled setting, then fine-tuned with clinically validated data. Our experiments test the model generalizability with controls and subjects with PD on 2 independent datasets. RESULTS: Our approach showed better generalization compared to previous methods, including a feature engineering strategy, a deep learning model pre-trained on Parkinsonian signs, and a traditional supervised model. DISCUSSION: The absence of standardized data acquisition protocols and the limited availability of annotated datasets compromise the generalizability of supervised models. In these contexts, self-supervised models offer the advantage of learning more robust patterns from the data, bypassing the need for ground truth labels. CONCLUSION: This approach has the potential to accelerate the clinical validation of touchscreen typing software for neurodegenerative diseases.

Strategies to combine 3D vasculature and brain CTA with deep neural networks: Application to LVO.

Automated tools to detect large vessel occlusion (LVO) in acute ischemic stroke patients using brain computed tomography angiography (CTA) have been shown to reduce the time for treatment, leading to better clinical outcomes. There is a lot of information in a single CTA and deep learning models do not have an obvious way of being conditioned on areas most relevant for LVO detection, i.e., the vasculature structure. In this work, we compare and contrast strategies to make convolutional neural networks focus on the vasculature without discarding context information of the brain parenchyma and propose an attention-inspired strategy to encourage this. We use brain CTAs from which we obtain 3D vasculature images. Then, we compare ways of combining the vasculature and the CTA images using a general-purpose network trained to detect LVO. The results show that the proposed strategies allow to improve LVO detection and could potentially help to learn other cerebrovascular-related tasks.

Unsupervised deep representation learning enables phenotype discovery for genetic association studies of brain imaging.

Understanding the genetic architecture of brain structure is challenging, partly due to difficulties in designing robust, non-biased descriptors of brain morphology. Until recently, brain measures for genome-wide association studies (GWAS) consisted of traditionally expert-defined or software-derived image-derived phenotypes (IDPs) that are often based on theoretical preconceptions or computed from limited amounts of data. Here, we present an approach to derive brain imaging phenotypes using unsupervised deep representation learning. We train a 3-D convolutional autoencoder model with reconstruction loss on 6130 UK Biobank (UKBB) participants' T1 or T2-FLAIR (T2) brain MRIs to create a 128-dimensional representation known as Unsupervised Deep learning derived Imaging Phenotypes (UDIPs). GWAS of these UDIPs in held-out UKBB subjects (n = 22,880 discovery and n = 12,359/11,265 replication cohorts for T1/T2) identified 9457 significant SNPs organized into 97 independent genetic loci of which 60 loci were replicated. Twenty-six loci were not reported in earlier T1 and T2 IDP-based UK Biobank GWAS. We developed a perturbation-based decoder interpretation approach to show that these loci are associated with UDIPs mapped to multiple relevant brain regions. Our results established unsupervised deep learning can derive robust, unbiased, heritable, and interpretable brain imaging phenotypes.

Keystroke-Dynamics for Parkinson's Disease Signs Detection in an At-Home Uncontrolled Population: A New Benchmark and Method.

Parkinson's disease (PD) is the second most prevalent neurodegenerative disease disorder in the world. A prompt diagnosis would enable clinical trials for disease-modifying neuroprotective therapies. Recent research efforts have unveiled imaging and blood markers that have the potential to be used to identify PD patients promptly, however, the idiopathic nature of PD makes these tests very hard to scale to the general population. To this end, we need an easily deployable tool that would enable screening for PD signs in the general population. In this work, we propose a new set of features based on keystroke dynamics, i.e., the time required to press and release keyboard keys during typing, and used to detect PD in an ecologically valid data acquisition setup at the subject's homes, without requiring any pre-defined task. We compare and contrast existing models presented in the literature and present a new model that combines a new type of keystroke dynamics signal representation using hold time and flight time series as a function of key types and asymmetry in the time series using a convolutional neural network. We show how this model achieves an Area Under the Receiving Operating Characteristic curve ranging from 0.80 to 0.83 on a dataset of subjects who actively interacted with their computers for at least 5 months and positively compares against other state-of-the-art approaches previously tested on keystroke dynamics data acquired with mechanical keyboards.

Machine learning and acute stroke imaging.

BACKGROUND: In recent years, machine learning (ML) has had notable success in providing automated analyses of neuroimaging studies, and its role is likely to increase in the future. Thus, it is paramount for clinicians to understand these approaches, gain facility with interpreting ML results, and learn how to assess algorithm performance. OBJECTIVE: To provide an overview of ML, present its role in acute stroke imaging, discuss methods to evaluate algorithms, and then provide an assessment of existing approaches. METHODS: In this review, we give an overview of ML techniques commonly used in medical imaging analysis and methods to evaluate performance. We then review the literature for relevant publications. Searches were run in November 2021 in Ovid Medline and PubMed. Inclusion criteria included studies in English reporting use of artificial intelligence (AI), machine learning, or similar techniques in the setting of, and in applications for, acute ischemic stroke or mechanical thrombectomy. Articles that included image-level data with meaningful results and sound ML approaches were included in this discussion. RESULTS: Many publications on acute stroke imaging, including detection of large vessel occlusion, detection and quantification of intracranial hemorrhage and detection of infarct core, have been published using ML methods. Imaging inputs have included non-contrast head CT, CT angiograph and MRI, with a range of performances. We discuss and review several of the most relevant publications. CONCLUSIONS: ML in acute ischemic stroke imaging has already made tremendous headway. Additional applications and further integration with clinical care is inevitable. Thus, facility with these approaches is critical for the neurointerventional clinician.

Dental CLAIRES: Contrastive LAnguage Image REtrieval Search for Dental Research.

Learning about diagnostic features and related clinical information from dental radiographs is important for dental research. However, the lack of expert-annotated data and convenient search tools poses challenges. Our primary objective is to design a search tool that uses a user's query for oral-related research. The proposed framework, Contrastive LAnguage Image REtrieval Search for dental research, Dental CLAIRES, utilizes periapical radiographs and associated clinical details such as periodontal diagnosis, demographic information to retrieve the best-matched images based on the text query. We applied a contrastive representation learning method to find images described by the user's text by maximizing the similarity score of positive pairs (true pairs) and minimizing the score of negative pairs (random pairs). Our model achieved a hit@3 ratio of 96% and a Mean Reciprocal Rank (MRR) of 0.82. We also designed a graphical user interface that allows researchers to verify the model's performance with interactions.

Segmentation of acute stroke infarct core using image-level labels on CT-angiography.

Acute ischemic stroke is a leading cause of death and disability in the world. Treatment decisions, especially around emergent revascularization procedures, rely heavily on size and location of the infarct core. Currently, accurate assessment of this measure is challenging. While MRI-DWI is considered the gold standard, its availability is limited for most patients suffering from stroke. Another well-studied imaging modality is CT-Perfusion (CTP) which is much more common than MRI-DWI in acute stroke care, but not as precise as MRI-DWI, and it is still unavailable in many stroke hospitals. A method to determine infarct core using CT-Angiography (CTA), a much more available imaging modality albeit with significantly less contrast in stroke core area than CTP or MRI-DWI, would enable significantly better treatment decisions for stroke patients throughout the world. Existing deep-learning-based approaches for stroke core estimation have to face the trade-off between voxel-level segmentation / image-level labels and the difficulty of obtaining large enough samples of high-quality DWI images. The former occurs when algorithms can either output voxel-level labeling which is more informative but requires a significant effort by annotators, or image-level labels that allow for much simpler labeling of the images but results in less informative and interpretable output; the latter is a common issue that forces training either on small training sets using DWI as the target or larger, but noisier, dataset using CT-Perfusion (CTP) as the target. In this work, we present a deep learning approach including a new weighted gradient-based approach to obtain stroke core segmentation with image-level labeling, specifically the size of the acute stroke core volume. Additionally, this strategy allows us to train using labels derived from CTP estimations. We find that the proposed approach outperforms segmentation approaches trained on voxel-level data and the CTP estimation themselves.

Synthetic OCT-A blood vessel maps using fundus images and generative adversarial networks.

Vessel segmentation in fundus images permits understanding retinal diseases and computing image-based biomarkers. However, manual vessel segmentation is a time-consuming process. Optical coherence tomography angiography (OCT-A) allows direct, non-invasive estimation of retinal vessels. Unfortunately, compared to fundus images, OCT-A cameras are more expensive, less portable, and have a reduced field of view. We present an automated strategy relying on generative adversarial networks to create vascular maps from fundus images without training using manual vessel segmentation maps. Further post-processing used for standard en face OCT-A allows obtaining a vessel segmentation map. We compare our approach to state-of-the-art vessel segmentation algorithms trained on manual vessel segmentation maps and vessel segmentations derived from OCT-A. We evaluate them from an automatic vascular segmentation perspective and as vessel density estimators, i.e., the most common imaging biomarker for OCT-A used in studies. Using OCT-A as a training target over manual vessel delineations yields improved vascular maps for the optic disc area and compares to the best-performing vessel segmentation algorithm in the macular region. This technique could reduce the cost and effort incurred when training vessel segmentation algorithms. To incentivize research in this field, we will make the dataset publicly available to the scientific community.

Automated Large Vessel Occlusion Detection Software and Thrombectomy Treatment Times: A Cluster Randomized Clinical Trial.

Importance: The benefit of endovascular stroke therapy (EVT) in large vessel occlusion (LVO) ischemic stroke is highly time dependent. Process improvements to accelerate in-hospital workflows are critical. Objective: To determine whether automated computed tomography (CT) angiogram interpretation coupled with secure group messaging can improve in-hospital EVT workflows. Design, Setting, and Participants: This cluster randomized stepped-wedge clinical trial took place from January 1, 2021, through February 27, 2022, at 4 comprehensive stroke centers (CSCs) in the greater Houston, Texas, area. All 443 participants with LVO stroke who presented through the emergency department were treated with EVT at the 4 CSCs. Exclusion criteria included patients presenting as transfers from an outside hospital (n = 158), in-hospital stroke (n = 39), and patients treated with EVT through randomization in a large core clinical trial (n = 3). Intervention: Artificial intelligence (AI)-enabled automated LVO detection from CT angiogram coupled with secure messaging was activated at the 4 CSCs in a random-stepped fashion. Once activated, clinicians and radiologists received real-time alerts to their mobile phones notifying them of possible LVO within minutes of CT imaging completion. Main Outcomes and Measures: Primary outcome was the effect of AI-enabled LVO detection on door-to-groin (DTG) time and was measured using a mixed-effects linear regression model, which included a random effect for cluster (CSC) and a fixed effect for exposure status (pre-AI vs post-AI). Secondary outcomes included time from hospital arrival to intravenous tissue plasminogen activator (IV tPA) bolus in eligible patients, time from initiation of CT scan to start of EVT, and hospital length of stay. In exploratory analysis, the study team evaluated the impact of AI implementation on 90-day modified Rankin Scale disability outcomes. Results: Among 243 patients who met inclusion criteria, 140 were treated during the unexposed period and 103 during the exposed period. Median age for the complete cohort was 70 (IQR, 58-79) years and 122 were female (50%). Median National Institutes of Health Stroke Scale score at presentation was 17 (IQR, 11-22) and the median DTG preexposure was 100 (IQR, 81-116) minutes. In mixed-effects linear regression, implementation of the AI algorithm was associated with a reduction in DTG time by 11.2 minutes (95% CI, -18.22 to -4.2). Time from CT scan initiation to EVT start fell by 9.8 minutes (95% CI, -16.9 to -2.6). There were no differences in IV tPA treatment times nor hospital length of stay. In multivariable logistic regression adjusted for age, National Institutes of Health Stroke scale score, and the Alberta Stroke Program Early CT Score, there was no difference in likelihood of functional independence (modified Rankin Scale score, 0-2; odds ratio, 1.3; 95% CI, 0.42-4.0). Conclusions and Relevance: Automated LVO detection coupled with secure mobile phone application-based communication improved in-hospital acute ischemic stroke workflows. Software implementation was associated with clinically meaningful reductions in EVT treatment times. Trial Registration: ClinicalTrials.gov Identifier: NCT05838456.

Predicting health-related social needs in Medicaid and Medicare populations using machine learning.

Providers currently rely on universal screening to identify health-related social needs (HRSNs). Predicting HRSNs using EHR and community-level data could be more efficient and less resource intensive. Using machine learning models, we evaluated the predictive performance of HRSN status from EHR and community-level social determinants of health (SDOH) data for Medicare and Medicaid beneficiaries participating in the Accountable Health Communities Model. We hypothesized that Medicaid insurance coverage would predict HRSN status. All models significantly outperformed the baseline Medicaid hypothesis. AUCs ranged from 0.59 to 0.68. The top performance (AUC = 0.68 CI 0.66-0.70) was achieved by the "any HRSNs" outcome, which is the most useful for screening prioritization. Community-level SDOH features had lower predictive performance than EHR features. Machine learning models can be used to prioritize patients for screening. However, screening only patients identified by our current model(s) would miss many patients. Future studies are warranted to optimize prediction of HRSNs.

Issues in Melanoma Detection: Semisupervised Deep Learning Algorithm Development via a Combination of Human and Artificial Intelligence.

BACKGROUND: Automatic skin lesion recognition has shown to be effective in increasing access to reliable dermatology evaluation; however, most existing algorithms rely solely on images. Many diagnostic rules, including the 3-point checklist, are not considered by artificial intelligence algorithms, which comprise human knowledge and reflect the diagnosis process of human experts. OBJECTIVE: In this paper, we aimed to develop a semisupervised model that can not only integrate the dermoscopic features and scoring rule from the 3-point checklist but also automate the feature-annotation process. METHODS: We first trained the semisupervised model on a small, annotated data set with disease and dermoscopic feature labels and tried to improve the classification accuracy by integrating the 3-point checklist using ranking loss function. We then used a large, unlabeled data set with only disease label to learn from the trained algorithm to automatically classify skin lesions and features. RESULTS: After adding the 3-point checklist to our model, its performance for melanoma classification improved from a mean of 0.8867 (SD 0.0191) to 0.8943 (SD 0.0115) under 5-fold cross-validation. The trained semisupervised model can automatically detect 3 dermoscopic features from the 3-point checklist, with best performances of 0.80 (area under the curve [AUC] 0.8380), 0.89 (AUC 0.9036), and 0.76 (AUC 0.8444), in some cases outperforming human annotators. CONCLUSIONS: Our proposed semisupervised learning framework can help with the automatic diagnosis of skin disease based on its ability to detect dermoscopic features and automate the label-annotation process. The framework can also help combine semantic knowledge with a computer algorithm to arrive at a more accurate and more interpretable diagnostic result, which can be applied to broader use cases.

A novel framework to estimate cognitive impairment via finger interaction with digital devices.

Measuring cognitive function is essential for characterizing brain health and tracking cognitive decline in Alzheimer's Disease and other neurodegenerative conditions. Current tools to accurately evaluate cognitive impairment typically rely on a battery of questionnaires administered during clinical visits which is essential for the acquisition of repeated measurements in longitudinal studies. Previous studies have shown that the remote data collection of passively monitored daily interaction with personal digital devices can measure motor signs in the early stages of synucleinopathies, as well as facilitate longitudinal patient assessment in the real-world scenario with high patient compliance. This was achieved by the automatic discovery of patterns in the time series of keystroke dynamics, i.e. the time required to press and release keys, by machine learning algorithms. In this work, our hypothesis is that the typing patterns generated from user-device interaction may reflect relevant features of the effects of cognitive impairment caused by neurodegeneration. We use machine learning algorithms to estimate cognitive performance through the analysis of keystroke dynamic patterns that were extracted from mechanical and touchscreen keyboard use in a dataset of cognitively normal (n = 39, 51% male) and cognitively impaired subjects (n = 38, 60% male). These algorithms are trained and evaluated using a novel framework that integrates items from multiple neuropsychological and clinical scales into cognitive subdomains to generate a more holistic representation of multifaceted clinical signs. In our results, we see that these models based on typing input achieve moderate correlations with verbal memory, non-verbal memory and executive function subdomains [Spearman's ρ between 0.54 (P < 0.001) and 0.42 (P < 0.001)] and a weak correlation with language/verbal skills [Spearman's ρ 0.30 (P < 0.05)]. In addition, we observe a moderate correlation between our typing-based approach and the Total Montreal Cognitive Assessment score [Spearman's ρ 0.48 (P < 0.001)]. Finally, we show that these machine learning models can perform better by using our subdomain framework that integrates the information from multiple neuropsychological scales as opposed to using the individual items that make up these scales. Our results support our hypothesis that typing patterns are able to reflect the effects of neurodegeneration in mild cognitive impairment and Alzheimer's disease and that this new subdomain framework both helps the development of machine learning models and improves their interpretability.