Search

Abstract 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.

Abstract 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

Abstract BackgroundEarly identification of impending in-hospital cardiac arrest (IHCA) improves clinical outcomes but remains elusive for practicing clinicians. ObjectiveWe aimed to develop a multimodal machine learning algorithm based on ensemble techniques to predict the occurrence of IHCA. MethodsOur model was developed by the Multiparameter Intelligent Monitoring of Intensive Care (MIMIC)–IV database and validated in the Electronic Intensive Care Unit Collaborative Research Database (eICU-CRD). Baseline features consisting of patient demographics, presenting illness, and comorbidities were collected to train a random forest model. Next, vital signs were extracted to train a long short-term memory model. A support vector machine algorithm then stacked the results to form the final prediction model. ResultsOf 23,909 patients in the MIMIC-IV database and 10,049 patients in the eICU-CRD database, 452 and 85 patients, respectively, had IHCA. At 13 hours in advance of an IHCA event, our algorithm had already demonstrated an area under the receiver operating characteristic curve of 0.85 (95% CI 0.815‐0.885) in the MIMIC-IV database. External validation with the eICU-CRD and National Taiwan University Hospital databases also presented satisfactory results, showing area under the receiver operating characteristic curve values of 0.81 (95% CI 0.763-0.851) and 0.945 (95% CI 0.934-0.956), respectively. ConclusionsUsing only vital signs and information available in the electronic medical record, our model demonstrates it is possible to detect a trajectory of clinical deterioration up to 13 hours in advance. This predictive tool, which has undergone external validation, could forewarn and help clinicians identify patients in need of assessment to improve their overall prognosis.

Summary: 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.

Abstract 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

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.

Biochar derived from pyrolysis or gasification has been gaining significant attention in the recent years due to its potential wide applications for the development of negative emissions technologies. A new concept was developed for biochar and power co-generation system using a combination of biomass pyrolysis (BP) unit, solid oxide fuel cells (SOFCs), and a combined heat and power (CHP) system. A set of detailed experimental data of pyrolysis product yields was established in Aspen Plus to model the BP process. The impacts of various operating parameters including current density (j), fuel utilization factor (Uf), pyrolysis gas reforming temperature (Treformer), and biochar split ratio (Rbiochar) on the SOFC and overall system performances in terms of energy and exergy analyses were evaluated. The simulation results indicated that increasing the Uf, Treformer, and Rbiochar can favorably improve the performances of the BP-SOFC-CHP system. As a whole, the overall electrical, energy and exergy efficiencies of the BP-SOFC-CHP system were in the range of 8–14%, 76–78%, and 71–74%, respectively. From the viewpoint of energy balance, burning the reformed pyrolysis gas can supply enough energy demand for the process to achieve a stand-alone BP-SOFC-CHP plant. In case of a stand-alone system, the overall electrical, energy and exergy efficiencies were 5.4, 63.9 and 57.8%, respectively, with a biochar yield of 31.6%.

In our previous work (Part I), we evaluated the thermodynamic models of the biomass-fed integrated gasification solid oxide fuel cell system with a carbon capture and storage (BIGFC/CCS) unit. In this work (Part II), the techno-economic analysis of the proposed negative emission power plants is carried out. Levelized cost of electricity, net present value (NPV), payback period, internal rate of return (IRR), and levelized cost of negative carbon (LCNC) are the key economic parameters evaluated. The results of a series of sensitivity analysis show the impact of gasification agents and stepwise increase in biochar co-production on the performance of the system. The total overnight cost is estimated to be 6197 $/kW and 5567 $/kW for the air and steam-oxygen gasification BIGFC/CCS systems, respectively. Steam-oxygen gasification is found to be more economically beneficial than air gasification one for all of the cases studied. Economically viable biochar co-production cases are identified to ascertain the influence of capital cost, operating cost, biomass cost, plant capacity factor, and tax. Moreover, the effect of the carbon credit scenario on the economic indicators is also reported. The results show that the most effective economic performance from the steam-oxygen gasification case reported an NPV of 3542 M$, an IRR of 24.2%, and a payback period of 3.3 years, with an LCNC of -322.5$/t of CO2. Compiling the results from Part I and Part II shows that it is easier to achieve negative emission using the steam-oxygen gasification of a BIGFC/CCS system. These results are expected to be helpful for stakeholders in identifying appealing negative emissions power plant projects for near and long-term future investments.

Graphical Abstract

Abstract Image-based teleconsultation using smartphones has become increasingly popular. In parallel, deep learning algorithms have been developed to detect radiological findings in chest X-rays (CXRs). However, the feasibility of using smartphones to automate this process has yet to be evaluated. This study developed a recalibration method to build deep learning models to detect radiological findings on CXR photographs. Two publicly available databases (MIMIC-CXR and CheXpert) were used to build the models, and four derivative datasets containing 6453 CXR photographs were collected to evaluate model performance. After recalibration, the model achieved areas under the receiver operating characteristic curve of 0.80 (95% confidence interval: 0.78–0.82), 0.88 (0.86–0.90), 0.81 (0.79–0.84), 0.79 (0.77–0.81), 0.84 (0.80–0.88), and 0.90 (0.88–0.92), respectively, for detecting cardiomegaly, edema, consolidation, atelectasis, pneumothorax, and pleural effusion. The recalibration strategy, respectively, recovered 84.9%, 83.5%, 53.2%, 57.8%, 69.9%, and 83.0% of performance losses of the uncalibrated model. We conclude that the recalibration method can transfer models from digital CXRs to CXR photographs, which is expected to help physicians’ clinical works.

Abstract 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.

Because of their compact structure, ease of processing and higher heat transfer coefficient, curved-tube heat exchangers are widely applied in various industry applications, such as nuclear power systems, solar-powered engineering, aircraft engine cooling systems and refrigeration and cryogenic systems. Accurate knowledge about the heat transfer characteristics of the supercritical fluids in the tube is critical to the design and optimization of a curved-tube heat exchanger. The available literature indicates that the flow of supercritical fluids flowing in curved tubes affected by the dual effects of the buoyancy force and centrifugal force is more complex compared to straight tubes. Therefore, to obtain insight into their unique characteristics and further research progress, this paper presents a comprehensive review of available experimental and numerical research works on fluids at supercritical pressure flowing in curved tubes. Overall, the secondary flow caused by the curvature enhances the heat transfer and delays the heat transfer deterioration, but it also causes a non-uniform heat transfer distribution along the circumferential direction, and the strengthening performance of the curved tube is damaged. Compared with the more mature theories regarding straight tubes, the flow structure, the coupling mechanism of buoyancy and centrifugal force, and the general heat transfer correlation of supercritical fluids in a curved tube still urgently need to be further studied. Most importantly, studies on the suppression of heat transfer oscillations and heat transfer inhomogeneities specific to curved tubes are scarce. Considering the current status and shortcomings of existing studies, some study topics for supercritical fluids in a curved tube are proposed.

Negative emission technologies have recently received increasing attention due to climate change and global warming. One among them is bioenergy with carbon capture and storage (BECCS), but the capture process is very energy intensive. Here, a novel pathway is introduced, based on second-generation biofuels followed by carbon circulation in an indefinitely closed chain, effectively resulting in a sink. Instead of using an energy-intensive conventional CCS process, the application of an on-board solid oxide fuel cell (SOFC) running on biofuels in an electric vehicle (FCEV) could result in negative emissions by capturing a concentrated stream of CO2, which is readily stored in a second tank. A CO2 recovery system at the fuel station then takes the CO2 from the tank to be transported to storage locations or to be used for local applications such as CO2-based concrete curing and synthesis of e-fuels. Incorporating CO2 utilization technologies into the FCEVs-SOFC system can close the carbon loop, achieving carbon neutrality through feeding the CO2 in a reverse-logistic to a methanol plant. The methanol produced is also used in SOFCs, leading to an infinite repetition of this carbon cycle till a saturation stage is reached. It is determined this pathway will reach typical Cradle-to-Grave negative emissions of 0.515 ton CO2 per vehicle, and total negative CO2 emission of 138 Mt for all passenger cars in the EU is potentially achievable. All steps comprise known technologies with medium to high technology readiness level (TRL) levels, so principally this system can readily be applied in the mid-term.

There is a growing interest in functional magnetic resonance imaging (fMRI) studies on connectivity networks in the brain when subjects are under exposure to natural sensory stimulation. Because of a complicated coupling between spontaneous and evoked brain activity under real-world stimulation, there is no critical mapping between the experimental inputs and corresponding brain responses. The dataset contains auditory fMRI scans and T1-weighted anatomical scans acquired under eyes-closed and eyes-open conditions. Within each scanning condition, the subject was presented 12 different sound clips, including human voices followed by animal vocalizations. The dataset is meant to be used to assess brain dynamics and connectivity networks under natural sound stimulation; it also allows for empirical investigation of changes in fMRI responses between eyes-closed and eyes-open conditions, between animal vocalizations and human voices, as well as between the 12 different sound clips during auditory stimulation. The dataset is a supplement to the research findings in the paper “Brain dynamics and connectivity networks under natural auditory stimulation” published in NeuroImage. Keywords: fMRI, Connectivity networks, Real-world, Auditory

The irregularity and uncertainty of neurophysiologic signals across different time scales can be regarded as neural complexity, which is related to the adaptability of the nervous system and the information processing between neurons. We recently reported general loss of brain complexity, as measured by multiscale sample entropy (MSE), at pain-related regions in females with primary dysmenorrhea (PDM). However, it is unclear whether this loss of brain complexity is associated with inter-subject genetic variations. Brain-derived neurotrophic factor (BDNF) is a widely expressed neurotrophin in the brain and is crucial to neural plasticity. The BDNF Val66Met single-nucleotide polymorphism (SNP) is associated with mood, stress, and pain conditions. Therefore, we aimed to examine the interactions of BDNF Val66Met polymorphism and long-term menstrual pain experience on brain complexity. We genotyped BDNF Val66Met SNP in 80 PDM females (20 Val/Val, 31 Val/Met, 29 Met/Met) and 76 healthy female controls (25 Val/Val, 36 Val/Met, 15 Met/Met). MSE analysis was applied to neural source activity estimated from resting-state magnetoencephalography (MEG) signals during pain-free state. We found that brain complexity alterations were associated with the interactions of BDNF Val66Met polymorphism and menstrual pain experience. In healthy female controls, Met carriers (Val/Met and Met/Met) demonstrated lower brain complexity than Val/Val homozygotes in extensive brain regions, suggesting a possible protective role of Val/Val homozygosity in brain complexity. However, after experiencing long-term menstrual pain, the complexity differences between different genotypes in healthy controls were greatly diminished in PDM females, especially in the limbic system, including the hippocampus and amygdala. Our results suggest that pain experience preponderantly affects the effect of BDNF Val66Met polymorphism on brain complexity. The results of the present study also highlight the potential utilization of resting-state brain complexity for the development of new therapeutic strategies in patients with chronic pain.

The emergence of the digital world has greatly increased the number of accounts and passwords that users must remember. It has also increased the need for secure access to personal information in the cloud. Biometrics is one approach to person recognition, which can be used in identification as well as authentication. Among the various modalities that have been developed, electroencephalography (EEG)-based biometrics features unparalleled universality, distinctiveness and collectability, while minimizing the risk of circumvention. However, commercializing EEG-based person recognition poses a number of challenges. This article reviews the various systems proposed over the past few years with a focus on the shortcomings that have prevented wide-scale implementation, including issues pertaining to temporal stability, psychological and physiological changes, protocol design, equipment and performance evaluation. We also examine several directions for the further development of usable EEG-based recognition systems as well as the niche markets to which they could be applied. It is expected that rapid advancements in EEG instrumentation, on-device processing and machine learning techniques will lead to the emergence of commercialized person recognition systems in the near future.

In this article, the conceptual design of biomass steam gasification (BSG) processes using raw oil palm (ROP) and torrefied oil palm (TOP) are examined in an Aspen Plus simulator. Through thermodynamic analysis, it is verified that the BSG process with torrefied feedstock can effectively enhance the hydrogen yield. When the heat recovery design is added into the BSG process, the system energetic efficiency (SEE) is significantly improved. Finally, an optimization algorithm with respect to SEE and hydrogen yield is solved, and the optimum operating conditions are validated by simulations.

How chronic pain affects brain functions remains unclear. As a potential indicator, brain complexity estimated by entropy-based methods may be helpful for revealing the underlying neurophysiological mechanism of chronic pain. In this study, complexity features with multiple time scales and spectral features were extracted from resting-state magnetoencephalographic signals of 156 female participants with/without primary dysmenorrhea (PDM) during pain-free state. Revealed by multiscale sample entropy (MSE), PDM patients (PDMs) exhibited loss of brain complexity in regions associated with sensory, affective, and evaluative components of pain, including sensorimotor, limbic, and salience networks. Significant correlations between MSE values and psychological states (depression and anxiety) were found in PDMs, which may indicate specific nonlinear disturbances in limbic and default mode network circuits after long-term menstrual pain. These findings suggest that MSE is an important measure of brain complexity and is potentially applicable to future diagnosis of chronic pain.

Spermidine/spermine N(1)-acetyltransferase 1 (Ssat1) is a key enzyme in the polyamine interconversion pathway, which maintains polyamine homeostasis. In addition, mammalian Ssat1 is also involved in many physiological and pathological events such as hypoxia, cell migration, and carcinogenesis. Using cross-genomic bioinformatic analysis in 10 deuterostomes, we found that ssat1 only exists in vertebrates. Comparing with mammalian, zebrafish, an evolutionarily distant vertebrate, contains 3 homologous ssat1 genes, named ssat1a, ssat1b, and ssat1c. All zebrafish homologues could be transcribed and produce active enzymes. Despite the long history since their evolutionary diversification, some features of human SSAT1 are conserved and subfunctionalized in the zebrafish family of Ssat1 proteins. The polyamine-dependent protein synthesis was only found in Ssat1b and Ssat1c, not in Ssat1a. Further study indicated that both 5' and 3' sequences of ssat1b mediate such kind of translational regulation inside the open reading frame (ORF). The polyamine-dependent protein stabilization was only observed in Ssat1b. The last 70 residues of Ssat1b were crucial for its rapid degradation and polyamine-induced stabilization. It is worth noting that only Ssat1b and Ssat1c, but not the polyamine-insensitive Ssat1a, were able to interact with integrin α9 and Hif-1α. Thus, Ssat1b and Ssat1c might not only be a polyamine metabolic enzyme but also simultaneously respond to polyamine levels and engage in cross-talk with other signaling pathways. Our data revealed some correlations between the sequences and functions of the zebrafish family of Ssat1 proteins, which may provide valuable information for studies of their translational regulatory mechanism, protein stability, and physiological functions.