Early prediction of mortality at sepsis diagnosis time in critically ill patients by using interpretable machine learning.

This study applied machine learning for the early prediction of 30-day mortality at sepsis diagnosis time in critically ill patients. Retrospective study using data collected from the Medical Information Mart for Intensive Care IV database. The data of the patient cohort was divided on the basis of the year of hospitalization, into training (2008-2013), validation (2014-2016), and testing (2017-2019) datasets. 24,377 patients with the sepsis diagnosis time < 24 h after intensive care unit (ICU) admission were included. A gradient boosting tree-based algorithm (XGBoost) was used for training the machine learning model to predict 30-day mortality at sepsis diagnosis time in critically ill patients. Model performance was measured in both discrimination and calibration aspects. The model was interpreted using the SHapley Additive exPlanations (SHAP) module. The 30-day mortality rate of the testing dataset was 17.9%, and 39 features were selected for the machine learning model. Model performance on the testing dataset achieved an area under the receiver operating characteristic curve (AUROC) of 0.853 (95% CI 0.837-0.868) and an area under the precision-recall curves of 0.581 (95% CI 0.541-0.619). The calibration plot for the model revealed a slope of 1.03 (95% CI 0.94-1.12) and intercept of 0.14 (95% CI 0.04-0.25). The SHAP revealed the top three most significant features, namely age, increased red blood cell distribution width, and respiratory rate. Our study demonstrated the feasibility of using the interpretable machine learning model to predict mortality at sepsis diagnosis time.

Automatic segmentation and radiomic texture analysis for osteoporosis screening using chest low-dose computed tomography.

OBJECTIVE: This study developed a diagnostic tool combining machine learning (ML) segmentation and radiomic texture analysis (RTA) for bone density screening using chest low-dose computed tomography (LDCT). METHODS: A total of 197 patients who underwent LDCT followed by dual-energy X-ray absorptiometry were analyzed. First, an autosegmentation model was trained using LDCT to delineate the thoracic vertebral body (VB). Second, a two-level classifier was developed using radiomic features extracted from VBs for the hierarchical pairwise classification of each patient's bone status. All the patients were initially classified as either normal or abnormal, and all patients with abnormal bone density were then subdivided into an osteopenia group and an osteoporosis group. The performance of the classifier was evaluated through fivefold cross-validation. RESULTS: The model for automated VB segmentation achieved a Sorenson-Dice coefficient of 0.87 ± 0.01. Furthermore, the area under the receiver operating characteristic curve scores for the two-level classifier were 0.96 ± 0.01 for detecting abnormal bone density (accuracy = 0.91 ± 0.02; sensitivity = 0.93 ± 0.03; specificity = 0.89 ± 0.03) and 0.98 ± 0.01 for distinguishing osteoporosis (accuracy = 0.94 ± 0.02; sensitivity = 0.95 ± 0.03; specificity = 0.93 ± 0.03). The testing prediction accuracy levels for the first- and second-level classifiers were 0.92 ± 0.04 and 0.94 ± 0.05, respectively. The overall testing prediction accuracy of our method was 0.90 ± 0.05. CONCLUSION: The combination of ML segmentation and RTA for automated bone density prediction based on LDCT scans is a feasible approach that could be valuable for osteoporosis screening during lung cancer screening. KEY POINTS: • This study developed an automatic diagnostic tool combining machine learning-based segmentation and radiomic texture analysis for bone density screening using chest low-dose computed tomography. • The developed method enables opportunistic screening without quantitative computed tomography or a dedicated phantom. • The developed method could be integrated into the current clinical workflow and used as an adjunct for opportunistic screening or for patients who are ineligible for screening with dual-energy X-ray absorptiometry.

Brain Reactions to Opening and Closing the Eyes: Salivary Cortisol and Functional Connectivity.

This study empirically assessed the strength and duration of short-term effects induced by brain reactions to closing/opening the eyes on a few well-known resting-state networks. We also examined the association between these reactions and subjects' cortisol levels. A total of 55 young adults underwent 8-min resting-state fMRI (rs-fMRI) scans under 4-min eyes-closed and 4-min eyes-open conditions. Saliva samples were collected from 25 of the 55 subjects before and after the fMRI sessions and assayed for cortisol levels. Our empirical results indicate that when the subjects were relaxed with their eyes closed, the effect of opening the eyes on conventional resting-state networks (e.g., default-mode, frontal-parietal, and saliency networks) lasted for roughly 60-s, during which we observed a short-term increase in activity in rs-fMRI time courses. Moreover, brain reactions to opening the eyes had a pronounced effect on time courses in the temporo-parietal lobes and limbic structures, both of which presented a prolonged decrease in activity. After controlling for demographic factors, we observed a significantly positive correlation between pre-scan cortisol levels and connectivity in the limbic structures under both conditions. Under the eyes-closed condition, the temporo-parietal lobes presented significant connectivity to limbic structures and a significantly positive correlation with pre-scan cortisol levels. Future research on rs-fMRI could consider the eyes-closed condition when probing resting-state connectivity and its neuroendocrine correlates, such as cortisol levels. It also appears that abrupt instructions to open the eyes while the subject is resting quietly with eyes closed could be used to probe brain reactivity to aversive stimuli in the ventral hippocampus and other limbic structures.

Developing and Validating Multi-Modal Models for Mortality Prediction in COVID-19 Patients: a Multi-center Retrospective Study.

The unprecedented global crisis brought about by the COVID-19 pandemic has sparked numerous efforts to create predictive models for the detection and prognostication of SARS-CoV-2 infections with the goal of helping health systems allocate resources. Machine learning models, in particular, hold promise for their ability to leverage patient clinical information and medical images for prediction. However, most of the published COVID-19 prediction models thus far have little clinical utility due to methodological flaws and lack of appropriate validation. In this paper, we describe our methodology to develop and validate multi-modal models for COVID-19 mortality prediction using multi-center patient data. The models for COVID-19 mortality prediction were developed using retrospective data from Madrid, Spain (N = 2547) and were externally validated in patient cohorts from a community hospital in New Jersey, USA (N = 242) and an academic center in Seoul, Republic of Korea (N = 336). The models we developed performed differently across various clinical settings, underscoring the need for a guided strategy when employing machine learning for clinical decision-making. We demonstrated that using features from both the structured electronic health records and chest X-ray imaging data resulted in better 30-day mortality prediction performance across all three datasets (areas under the receiver operating characteristic curves: 0.85 (95% confidence interval: 0.83-0.87), 0.76 (0.70-0.82), and 0.95 (0.92-0.98)). We discuss the rationale for the decisions made at every step in developing the models and have made our code available to the research community. We employed the best machine learning practices for clinical model development. Our goal is to create a toolkit that would assist investigators and organizations in building multi-modal models for prediction, classification, and/or optimization.

The crystal structure of protein-transporting chaperone BCP1 from Saccharomyces cerevisiae.

BCP1 is a protein enriched in the nucleus that is required for Mss4 nuclear export and identified as the chaperone of ribosomal protein Rpl23 in Saccharomyces cerevisiae. According to sequence homology, BCP1 is related to the mammalian BRCA2-interacting protein BCCIP and belongs to the BCIP protein family (PF13862) in the Pfam database. However, the BCIP family has no discernible similarity to proteins with known structure. Here, we report the crystal structure of BCP1, presenting an α/ß fold in which the central antiparallel ß-sheet is flanked by helices. Protein structural classification revealed that BCP1 has similarity to the GNAT superfamily but no conserved substrate-binding residues. Further modeling and protein-protein docking work provide a plausible model to explain the interaction between BCP1 and Rpl23. Our structural analysis presents the first structure of BCIP family and provides a foundation for understanding the molecular basis of BCP1 as a chaperone of Rpl23 for ribosome biosynthesis.

Machine learning-based segmentation of ischemic penumbra by using diffusion tensor metrics in a rat model.

BACKGROUND: Recent trials have shown promise in intra-arterial thrombectomy after the first 6-24 h of stroke onset. Quick and precise identification of the salvageable tissue is essential for successful stroke management. In this study, we examined the feasibility of machine learning (ML) approaches for differentiating the ischemic penumbra (IP) from the infarct core (IC) by using diffusion tensor imaging (DTI)-derived metrics. METHODS: Fourteen male rats subjected to permanent middle cerebral artery occlusion (pMCAO) were included in this study. Using a 7 T magnetic resonance imaging, DTI metrics such as fractional anisotropy, pure anisotropy, diffusion magnitude, mean diffusivity (MD), axial diffusivity, and radial diffusivity were derived. The MD and relative cerebral blood flow maps were coregistered to define the IP and IC at 0.5 h after pMCAO. A 2-level classifier was proposed based on DTI-derived metrics to classify stroke hemispheres into the IP, IC, and normal tissue (NT). The classification performance was evaluated using leave-one-out cross validation. RESULTS: The IC and non-IC can be accurately segmented by the proposed 2-level classifier with an area under the receiver operating characteristic curve (AUC) between 0.99 and 1.00, and with accuracies between 96.3 and 96.7%. For the training dataset, the non-IC can be further classified into the IP and NT with an AUC between 0.96 and 0.98, and with accuracies between 95.0 and 95.9%. For the testing dataset, the classification accuracy for IC and non-IC was 96.0 ± 2.3% whereas for IP and NT, it was 80.1 ± 8.0%. Overall, we achieved the accuracy of 88.1 ± 6.7% for classifying three tissue subtypes (IP, IC, and NT) in the stroke hemisphere and the estimated lesion volumes were not significantly different from those of the ground truth (p = .56, .94, and .78, respectively). CONCLUSIONS: Our method achieved comparable results to the conventional approach using perfusion-diffusion mismatch. We suggest that a single DTI sequence along with ML algorithms is capable of dichotomizing ischemic tissue into the IC and IP.

Brain dynamics and connectivity networks under natural auditory stimulation.

The analysis of functional magnetic resonance imaging (fMRI) data is challenging when subjects are under exposure to natural sensory stimulation. In this study, a two-stage approach was developed to enable the identification of connectivity networks involved in the processing of information in the brain under natural sensory stimulation. In the first stage, the degree of concordance between the results of inter-subject and intra-subject correlation analyses is assessed statistically. The microstructurally (i.e., cytoarchitectonically) defined brain areas are designated either as concordant in which the results of both correlation analyses are in agreement, or as discordant in which one analysis method shows a higher proportion of supra-threshold voxels than does the other. In the second stage, connectivity networks are identified using the time courses of supra-threshold voxels in brain areas contingent upon the classifications derived in the first stage. In an empirical study, fMRI data were collected from 40 young adults (19 males, average age 22.76 ±â€¯3.25), who underwent auditory stimulation involving sound clips of human voices and animal vocalizations under two operational conditions (i.e., eyes-closed and eyes-open). The operational conditions were designed to assess confounding effects due to auditory instructions or visual perception. The proposed two-stage analysis demonstrated that stress modulation (affective) and language networks in the limbic and cortical structures were respectively engaged during sound stimulation, and presented considerable variability among subjects. The network involved in regulating visuomotor control was sensitive to the eyes-open instruction, and presented only small variations among subjects. A high degree of concordance was observed between the two analyses in the primary auditory cortex which was highly sensitive to the pitch of sound clips. Our results have indicated that brain areas can be identified as concordant or discordant based on the two correlation analyses. This may further facilitate the search for connectivity networks involved in the processing of information under natural sensory stimulation.

Manifold decoding for neural representations of face viewpoint and gaze direction using magnetoencephalographic data.

The main challenge in decoding neural representations lies in linking neural activity to representational content or abstract concepts. The transformation from a neural-based to a low-dimensional representation may hold the key to encoding perceptual processes in the human brain. In this study, we developed a novel model by which to represent two changeable features of faces: face viewpoint and gaze direction. These features are embedded in spatiotemporal brain activity derived from magnetoencephalographic data. Our decoding results demonstrate that face viewpoint and gaze direction can be represented by manifold structures constructed from brain responses in the bilateral occipital face area and right superior temporal sulcus, respectively. Our results also show that the superposition of brain activity in the manifold space reveals the viewpoints of faces as well as directions of gazes as perceived by the subject. The proposed manifold representation model provides a novel opportunity to gain further insight into the processing of information in the human brain.

Decoding the perception of endogenous pain from resting-state MEG.

Decoding the neural representations of pain is essential to obtaining an objective assessment as well as an understanding of its underlying mechanisms. The complexities involved in the subjective experience of pain make it difficult to obtain a quantitative assessment from the induced spatiotemporal patterns of brain activity of high dimensionality. Most previous studies have investigated the perception of pain by analyzing the amplitude or spatial patterns in the response of the brain to external stimulation. This study investigated the decoding of endogenous pain perceptions according to resting-state magnetoencephalographic (MEG) recordings. In our experiments, we applied a beamforming method to calculate the brain activity for every brain region and examined temporal and spectral features of brain activity for predicting the intensity of perceived pain in patients with primary dysmenorrhea undergoing menstrual pain. Our results show that the asymmetric index of sample entropy in the precuneus and the sample entropy in the left posterior cingulate gyrus were the most informative characteristics associated with the perception of menstrual pain. The correlation coefficient (ρ=0.64, p<0.001) between the predicted and self-reported pain scores demonstrated the high prediction accuracy. In addition to the estimated brain activity, we were able to predict accurate pain scores directly from MEG channel signals (ρ=0.65, p<0.001). These findings suggest the possibility of using the proposed model based on resting-state MEG to predict the perceived intensity of endogenous pain.

Decoding and encoding of visual patterns using magnetoencephalographic data represented in manifolds.

Visual decoding and encoding are crucial aspects in investigating the representation of visual information in the human brain. This paper proposes a bidirectional model for decoding and encoding of visual stimulus based on manifold representation of the temporal and spatial information extracted from magnetoencephalographic data. In the proposed decoding process, principal component analysis is applied to extract temporal principal components (TPCs) from the visual cortical activity estimated by a beamforming method. The spatial distribution of each TPC is in a high-dimensional space and can be mapped to the corresponding spatiotemporal component (STC) on a low-dimensional manifold. Once the linear mapping between the STC and the wavelet coefficients of the stimulus image is determined, the decoding process can synthesize an image resembling the stimulus image. The encoding process is performed by reversing the mapping or transformation in the decoding model and can predict the spatiotemporal brain activity from a stimulus image. In our experiments using visual stimuli containing eleven combinations of checkerboard patches, the information of spatial layout in the stimulus image was revealed in the embedded manifold. The correlation between the reconstructed and original images was 0.71 and the correlation map between the predicted and original brain activity was highly correlated to the map between the original brain activity for different stimuli (r=0.89). These results suggest that the temporal component is important in visual processing and manifolds can well represent the information related to visual perception.

Drop the shortcuts: image augmentation improves fairness and decreases AI detection of race and other demographics from medical images.

BACKGROUND: It has been shown that AI models can learn race on medical images, leading to algorithmic bias. Our aim in this study was to enhance the fairness of medical image models by eliminating bias related to race, age, and sex. We hypothesise models may be learning demographics via shortcut learning and combat this using image augmentation. METHODS: This study included 44,953 patients who identified as Asian, Black, or White (mean age, 60.68 years ±18.21; 23,499 women) for a total of 194,359 chest X-rays (CXRs) from MIMIC-CXR database. The included CheXpert images comprised 45,095 patients (mean age 63.10 years ±18.14; 20,437 women) for a total of 134,300 CXRs were used for external validation. We also collected 1195 3D brain magnetic resonance imaging (MRI) data from the ADNI database, which included 273 participants with an average age of 76.97 years ±14.22, and 142 females. DL models were trained on either non-augmented or augmented images and assessed using disparity metrics. The features learned by the models were analysed using task transfer experiments and model visualisation techniques. FINDINGS: In the detection of radiological findings, training a model using augmented CXR images was shown to reduce disparities in error rate among racial groups (-5.45%), age groups (-13.94%), and sex (-22.22%). For AD detection, the model trained with augmented MRI images was shown 53.11% and 31.01% reduction of disparities in error rate among age and sex groups, respectively. Image augmentation led to a reduction in the model's ability to identify demographic attributes and resulted in the model trained for clinical purposes incorporating fewer demographic features. INTERPRETATION: The model trained using the augmented images was less likely to be influenced by demographic information in detecting image labels. These results demonstrate that the proposed augmentation scheme could enhance the fairness of interpretations by DL models when dealing with data from patients with different demographic backgrounds. FUNDING: National Science and Technology Council (Taiwan), National Institutes of Health.

Estimating the volume of penumbra in rodents using DTI and stack-based ensemble machine learning framework.

BACKGROUND: This study investigates the potential of diffusion tensor imaging (DTI) in identifying penumbral volume (PV) compared to the standard gadolinium-required perfusion-diffusion mismatch (PDM), utilizing a stack-based ensemble machine learning (ML) approach with enhanced explainability. METHODS: Sixteen male rats were subjected to middle cerebral artery occlusion. The penumbra was identified using PDM at 30 and 90 min after occlusion. We used 11 DTI-derived metrics and 14 distance-based features to train five voxel-wise ML models. The model predictions were integrated using stack-based ensemble techniques. ML-estimated and PDM-defined PVs were compared to evaluate model performance through volume similarity assessment, the Pearson correlation analysis, and Bland-Altman analysis. Feature importance was determined for explainability. RESULTS: In the test rats, the ML-estimated median PV was 106.4 mL (interquartile range 44.6-157.3 mL), whereas the PDM-defined median PV was 102.0 mL (52.1-144.9 mL). These PVs had a volume similarity of 0.88 (0.79-0.96), a Pearson correlation coefficient of 0.93 (p < 0.001), and a Bland-Altman bias of 2.5 mL (2.4% of the mean PDM-defined PV), with 95% limits of agreement ranging from -44.9 to 49.9 mL. Among the features used for PV prediction, the mean diffusivity was the most important feature. CONCLUSIONS: Our study confirmed that PV can be estimated using DTI metrics with a stack-based ensemble ML approach, yielding results comparable to the volume defined by the standard PDM. The model explainability enhanced its clinical relevance. Human studies are warranted to validate our findings. RELEVANCE STATEMENT: The proposed DTI-based ML model can estimate PV without the need for contrast agent administration, offering a valuable option for patients with kidney dysfunction. It also can serve as an alternative if perfusion map interpretation fails in the clinical setting. KEY POINTS: • Penumbral volume can be estimated by DTI combined with stack-based ensemble ML. • Mean diffusivity was the most important feature used for predicting penumbral volume. • The proposed approach can be beneficial for patients with kidney dysfunction.

A multimodal framework for extraction and fusion of satellite images and public health data.

In low- and middle-income countries, the substantial costs associated with traditional data collection pose an obstacle to facilitating decision-making in the field of public health. Satellite imagery offers a potential solution, but the image extraction and analysis can be costly and requires specialized expertise. We introduce SatelliteBench, a scalable framework for satellite image extraction and vector embeddings generation. We also propose a novel multimodal fusion pipeline that utilizes a series of satellite imagery and metadata. The framework was evaluated generating a dataset with a collection of 12,636 images and embeddings accompanied by comprehensive metadata, from 81 municipalities in Colombia between 2016 and 2018. The dataset was then evaluated in 3 tasks: including dengue case prediction, poverty assessment, and access to education. The performance showcases the versatility and practicality of SatelliteBench, offering a reproducible, accessible and open tool to enhance decision-making in public health.

Efficient conversion of waste-to-SNG via hybrid renewable energy systems for circular economy: Process design, energy, and environmental analysis.

Developing an efficient and environment-friendly route for waste valorization is extremely significant in accelerating the transition toward a circular economy. A novel waste-to-synthetic natural gas (SNG) conversion process comprising hybrid renewable energy systems is proposed for this purpose. This includes thermochemical waste conversion and power-to-gas technologies for simultaneous waste utilization and renewable energy storage applications. The energy and environmental performances of the proposed waste-to-SNG plant are assessed and optimized. Results indicated that the implementation of a thermal pretreatment unit prior to the plasma gasification (two-step) is beneficial to improve the yield of hydrogen in the syngas, thereby leading to less renewable energy requirement for green hydrogen production used in the methanation process. This also enhances SNG yield by a factor of 30% as compared to the case without thermal pretreatment (one-step). The overall energy efficiency (OE) of the proposed waste-to-SNG plant is in the range of 61.36-77.73%, while the energy return on investment (EROI) ranges between 2.66 and 6.11. Most environmental impacts are mainly contributed by the indirect carbon emissions as a consequence of the power requirement for thermal pretreatment, plasma gasifier, and auxiliary equipment. The value of specific electricity consumption for SNG production of the treated RDF exhibits 1.70-9.25 % less than that of raw RDF when the pretreatment temperature is less than 300 °C. The OE of the system declines by 4.52% when 50 wt% of biomass is mixed in the fuel, whereas an enhancement of 18.33% in EROI and a reduction of 16.19% in specific CO2 emissions are obtained.

Clinically Interpretable Machine Learning Models for Early Prediction of Mortality in Older Patients with Multiple Organ Dysfunction Syndrome: An International Multicenter Retrospective Study.

BACKGROUND: Multiple organ dysfunction syndrome (MODS) is associated with a high risk of mortality among older patients. Current severity scores are limited in their ability to assist clinicians with triage and management decisions. We aim to develop mortality prediction models for older patients with MODS admitted to the ICU. METHODS: The study analyzed older patients from 197 hospitals in the United States and 1 hospital in the Netherlands. The cohort was divided into the young-old (65-80 years) and old-old (≥80 years), which were separately used to develop and evaluate models including internal, external, and temporal validation. Demographic characteristics, comorbidities, vital signs, laboratory measurements, and treatments were used as predictors. We used the XGBoost algorithm to train models, and the SHapley Additive exPlanations (SHAP) method to interpret predictions. RESULTS: Thirty-four thousand four hundred and ninety-seven young-old (11.3% mortality) and 21 330 old-old (15.7% mortality) patients were analyzed. Discrimination AUROC of internal validation models in 9 046 U.S. patients was as follows: 0.87 and 0.82, respectively; discrimination of external validation models in 1 905 EUR patients was as follows: 0.86 and 0.85, respectively; and discrimination of temporal validation models in 8 690 U.S. patients: 0.85 and 0.78, respectively. These models outperformed standard clinical scores like Sequential Organ Failure Assessment and Acute Physiology Score III. The Glasgow Coma Scale, Charlson Comorbidity Index, and Code Status emerged as top predictors of mortality. CONCLUSIONS: Our models integrate data spanning physiologic and geriatric-relevant variables that outperform existing scores used in older adults with MODS, which represents a proof of concept of how machine learning can streamline data analysis for busy ICU clinicians to potentially optimize prognostication and decision making.

Deep learning with test-time augmentation for radial endobronchial ultrasound image differentiation: a multicentre verification study.

PURPOSE: Despite the importance of radial endobronchial ultrasound (rEBUS) in transbronchial biopsy, researchers have yet to apply artificial intelligence to the analysis of rEBUS images. MATERIALS AND METHODS: This study developed a convolutional neural network (CNN) to differentiate between malignant and benign tumours in rEBUS images. This study retrospectively collected rEBUS images from medical centres in Taiwan, including 769 from National Taiwan University Hospital Hsin-Chu Branch, Hsinchu Hospital for model training (615 images) and internal validation (154 images) as well as 300 from National Taiwan University Hospital (NTUH-TPE) and 92 images were obtained from National Taiwan University Hospital Hsin-Chu Branch, Biomedical Park Hospital (NTUH-BIO) for external validation. Further assessments of the model were performed using image augmentation in the training phase and test-time augmentation (TTA). RESULTS: Using the internal validation dataset, the results were as follows: area under the curve (AUC) (0.88 (95% CI 0.83 to 0.92)), sensitivity (0.80 (95% CI 0.73 to 0.88)), specificity (0.75 (95% CI 0.66 to 0.83)). Using the NTUH-TPE external validation dataset, the results were as follows: AUC (0.76 (95% CI 0.71 to 0.80)), sensitivity (0.58 (95% CI 0.50 to 0.65)), specificity (0.92 (95% CI 0.88 to 0.97)). Using the NTUH-BIO external validation dataset, the results were as follows: AUC (0.72 (95% CI 0.64 to 0.82)), sensitivity (0.71 (95% CI 0.55 to 0.86)), specificity (0.76 (95% CI 0.64 to 0.87)). After fine-tuning, the AUC values for the external validation cohorts were as follows: NTUH-TPE (0.78) and NTUH-BIO (0.82). Our findings also demonstrated the feasibility of the model in differentiating between lung cancer subtypes, as indicated by the following AUC values: adenocarcinoma (0.70; 95% CI 0.64 to 0.76), squamous cell carcinoma (0.64; 95% CI 0.54 to 0.74) and small cell lung cancer (0.52; 95% CI 0.32 to 0.72). CONCLUSIONS: Our results demonstrate the feasibility of the proposed CNN-based algorithm in differentiating between malignant and benign lesions in rEBUS images.

Enabling chronic obstructive pulmonary disease diagnosis through chest X-rays: A multi-site and multi-modality study.

PURPOSE: Chronic obstructive pulmonary disease (COPD) is one of the most common chronic illnesses in the world. Unfortunately, COPD is often difficult to diagnose early when interventions can alter the disease course, and it is underdiagnosed or only diagnosed too late for effective treatment. Currently, spirometry is the gold standard for diagnosing COPD but it can be challenging to obtain, especially in resource-poor countries. Chest X-rays (CXRs), however, are readily available and may have the potential as a screening tool to identify patients with COPD who should undergo further testing or intervention. In this study, we used three CXR datasets alongside their respective electronic health records (EHR) to develop and externally validate our models. METHOD: To leverage the performance of convolutional neural network models, we proposed two fusion schemes: (1) model-level fusion, using Bootstrap aggregating to aggregate predictions from two models, (2) data-level fusion, using CXR image data from different institutions or multi-modal data, CXR image data, and EHR data for model training. Fairness analysis was then performed to evaluate the models across different demographic groups. RESULTS: Our results demonstrate that DL models can detect COPD using CXRs with an area under the curve of over 0.75, which could facilitate patient screening for COPD, especially in low-resource regions where CXRs are more accessible than spirometry. CONCLUSIONS: By using a ubiquitous test, future research could build on this work to detect COPD in patients early who would not otherwise have been diagnosed or treated, altering the course of this highly morbid disease.

A deep learning model using chest X-ray for identifying TB and NTM-LD patients: a cross-sectional study.

BACKGROUND: Timely differentiating between pulmonary tuberculosis (TB) and nontuberculous mycobacterial lung disease (NTM-LD), which are radiographically similar, is important because infectiousness and treatment differ. This study aimed to evaluate whether artificial intelligence could distinguish between TB or NTM-LD patients by chest X-rays (CXRs) from suspects of mycobacterial lung disease. METHODS: A total of 1500 CXRs, including 500 each from patients with pulmonary TB, NTM-LD, and patients with clinical suspicion but negative mycobacterial culture (Imitator) from two hospitals, were retrospectively collected and evaluated in this study. We developed a deep neural network (DNN) and evaluated model performance using the area under the receiver operating characteristic curves (AUC) in both internal and external test sets. Furthermore, we conducted a reader study and tested our model under three scenarios of different mycobacteria prevalence. RESULTS: Among the internal and external test sets, the AUCs of our DNN model were 0.83 ± 0.005 and 0.76 ± 0.006 for pulmonary TB, 0.86 ± 0.006 and 0.64 ± 0.017 for NTM-LD, and 0.77 ± 0.007 and 0.74 ± 0.005 for Imitator. The DNN model showed higher performance on the internal test set in classification accuracy (66.5 ± 2.5%) than senior (50.8 ± 3.0%, p < 0.001) and junior pulmonologists (47.5 ± 2.8%, p < 0.001). Among different prevalence scenarios, the DNN model has stable performance in terms of AUC to detect TB and mycobacterial lung disease. CONCLUSION: DNN model had satisfactory performance and a higher accuracy than pulmonologists on classifying patients with presumptive mycobacterial lung diseases. DNN model could be a complementary first-line screening tool.

Digital phenotyping: An equal opportunity approach to reducing disparities in Alzheimer's disease and related dementia research.

A rapidly aging world population is fueling a concomitant increase in Alzheimer's disease (AD) and related dementias (ADRD). Scientific inquiry, however, has largely focused on White populations in Australia, the European Union, and North America. As such, there is an incomplete understanding of AD in other populations. In this perspective, we describe research efforts and challenges of cohort studies from three regions of the world: Central America, East Africa, and East Asia. These cohorts are engaging with the Davos Alzheimer's Collaborative (DAC), a global partnership that brings together cohorts from around the world to advance understanding of AD. Each cohort is poised to leverage the widespread use of mobile devices to integrate digital phenotyping into current methodologies and mitigate the lack of representativeness in AD research of racial and ethnic minorities across the globe. In addition to methods that these three cohorts are already using, DAC has developed a digital phenotyping protocol that can collect ADRD-related data remotely via smartphone and/or in clinic via a tablet to generate a common data elements digital dataset that can be harmonized with additional clinical and molecular data being collected at each cohort site and when combined across cohorts and made accessible can provide a global data resource that is more racially/ethnically represented of the world population.

Decision thresholding on fMRI activation maps using the Hilbert-Huang transform.

Objective. Functional magnetic resonance imaging (fMRI) requires thresholds by which to identify brain regions with significant activation, particularly for experiments involving real-life paradigms. One conventional non-parametric approach to generating surrogate data involves decomposition of the original fMRI time series using the Fourier transform, after which the phase is randomized without altering the magnitude of individual frequency components. However, it has been reported that spontaneous brain signals could be non-stationary, which, if true, could lead to false-positive results.Approach. This paper introduces a randomization procedure based on the Hilbert-Huang transform by which to account for non-stationarity in fMRI time series derived from two fMRI datasets (stationary or non-stationary). The significance of individual voxels was determined by comparing the distribution of empirical data versus a surrogate distribution.Main results. In a comparison with conventional phase-randomization and wavelet-based permutation methods, the proposed method proved highly effective in generating activation maps indicating essential brain regions, while filtering out noise in the white matter.Significance. This work demonstrated the importance of considering the non-stationary nature of fMRI time series when selecting resampling methods by which to probe brain activity or identify functional networks in real-life fMRI experiments. We propose a statistical testing method to deal with the non-stationarity of continuous brain signals.