An Arrhythmia classification approach via deep learning using single-lead ECG without QRS wave detection.

Arrhythmia, a frequently encountered and life-threatening cardiac disorder, can manifest as a transient or isolated event. Traditional automatic arrhythmia detection methods have predominantly relied on QRS-wave signal detection. Contemporary research has focused on the utilization of wearable devices for continuous monitoring of heart rates and rhythms through single-lead electrocardiogram (ECG), which holds the potential to promptly detect arrhythmias. However, in this study, we employed a convolutional neural network (CNN) to classify distinct arrhythmias without QRS wave detection step. The ECG data utilized in this study were sourced from the publicly accessible PhysioNet databases. Taking into account the impact of the duration of ECG signal on accuracy, this study trained one-dimensional CNN models with 5-s and 10-s segments, respectively, and compared their results. In the results, the CNN model exhibited the capability to differentiate between Normal Sinus Rhythm (NSR) and various arrhythmias, including Atrial Fibrillation (AFIB), Atrial Flutter (AFL), Wolff-Parkinson-White syndrome (WPW), Ventricular Fibrillation (VF), Ventricular Tachycardia (VT), Ventricular Flutter (VFL), Mobitz II AV Block (MII), and Sinus Bradycardia (SB). Both 10-s and 5-s ECG segments exhibited comparable results, with an average classification accuracy of 97.31%. It reveals the feasibility of utilizing even shorter 5-s recordings for detecting arrhythmias in everyday scenarios. Detecting arrhythmias with a single lead aligns well with the practicality of wearable devices for daily use, and shorter detection times also align with their clinical utility in emergency situations.

Deep convolutional neural network for rib fracture recognition on chest radiographs.

Introduction: Rib fractures are a prevalent injury among trauma patients, and accurate and timely diagnosis is crucial to mitigate associated risks. Unfortunately, missed rib fractures are common, leading to heightened morbidity and mortality rates. While more sensitive imaging modalities exist, their practicality is limited due to cost and radiation exposure. Point of care ultrasound offers an alternative but has drawbacks in terms of procedural time and operator expertise. Therefore, this study aims to explore the potential of deep convolutional neural networks (DCNNs) in identifying rib fractures on chest radiographs. Methods: We assembled a comprehensive retrospective dataset of chest radiographs with formal image reports documenting rib fractures from a single medical center over the last five years. The DCNN models were trained using 2000 region-of-interest (ROI) slices for each category, which included fractured ribs, non-fractured ribs, and background regions. To optimize training of the deep learning models (DLMs), the images were segmented into pixel dimensions of 128 × 128. Results: The trained DCNN models demonstrated remarkable validation accuracies. Specifically, AlexNet achieved 92.6%, GoogLeNet achieved 92.2%, EfficientNetb3 achieved 92.3%, DenseNet201 achieved 92.4%, and MobileNetV2 achieved 91.2%. Discussion: By integrating DCNN models capable of rib fracture recognition into clinical decision support systems, the incidence of missed rib fracture diagnoses can be significantly reduced, resulting in tangible decreases in morbidity and mortality rates among trauma patients. This innovative approach holds the potential to revolutionize the diagnosis and treatment of chest trauma, ultimately leading to improved clinical outcomes for individuals affected by these injuries. The utilization of DCNNs in rib fracture detection on chest radiographs addresses the limitations of other imaging modalities, offering a promising and practical solution to improve patient care and management.

Semantic Visualization in Functional Recovery Prediction of Intravenous Thrombolysis following Acute Ischemic Stroke in Patients by Using Biostatistics: An Exploratory Study.

(1) Background: Intravenous thrombolysis following acute ischemic stroke (AIS) can reduce disability and increase the survival rate. We designed a functional recovery analysis by using semantic visualization to predict the recovery probability in AIS patients receiving intravenous thrombolysis; (2) Methods: We enrolled 131 AIS patients undergoing intravenous thrombolysis from 2011 to 2015 at the Medical Center in northern Taiwan. An additional 54 AIS patients were enrolled from another community hospital. A modified Rankin Score ≤2 after 3 months of follow-up was defined as favorable recovery. We used multivariable logistic regression with forward selection to construct a nomogram; (3) Results: The model included age and the National Institutes of Health Stroke Scale (NIHSS) score as immediate pretreatment parameters. A 5.23% increase in the functional recovery probability occurred for every 1-year reduction in age, and a 13.57% increase in the functional recovery probability occurred for every NIHSS score reduction. The sensitivity, specificity, and accuracy of the model in the validation dataset were 71.79%, 86.67%, and 75.93%, respectively, and the area under the receiver operating characteristic curve (AUC) was 0.867; (4) Conclusions: Semantic visualization-based functional recovery prediction models may help physicians assess the recovery probability before patients undergo emergency intravenous thrombolysis.

Automatic detection and vascular territory classification of hyperacute staged ischemic stroke on diffusion weighted image using convolutional neural networks.

Automated ischemic stroke detection and classification according to its vascular territory is an essential step in stroke image evaluation, especially at hyperacute stage where mechanical thrombectomy may improve patients' outcome. This study aimed to evaluate the performance of various convolutional neural network (CNN) models on hyperacute staged diffusion-weighted images (DWI) for detection of ischemic stroke and classification into anterior circulation infarct (ACI), posterior circulation infarct (PCI) and normal image slices. In this retrospective study, 253 cases of hyperacute staged DWI were identified, downloaded and reviewed. After exclusion, DWI from 127 cases were used and we created a dataset containing total of 2119 image slices, and separates it into three groups, namely ACI (618 slices), PCI (149 slices) and normal (1352 slices). Two transfer learning based CNN models, namely Inception-v3, EfficientNet-b0 and one self-derived modified LeNet model were used. The performance of the models was evaluated and activation maps using gradient-weighted class activation mapping (Grad-Cam) technique were made. Inception-v3 had the best overall accuracy (86.3%), weighted F1 score (86.2%) and kappa score (0.715), followed by the modified LeNet (85.2% accuracy, 84.7% weighted F1 score and 0.693 kappa score). The EfficientNet-b0 had the poorest performance of 83.6% accuracy, 83% weighted F1 score and 0.662 kappa score. The activation map showed that one possible explanation for misclassification is due to susceptibility artifact. A sufficiently high performance can be achieved by using CNN model to detect ischemic stroke on hyperacute staged DWI and classify it according to vascular territory.

Palmitic acid methyl ester induces cardiac hypertrophy through activating the GPR receptor-mediated changes of intracellular calcium concentrations and mitochondrial functions.

Myocardial hypertrophy is associated with a significant increase in intracellular Ca2+ , which can be induced by long-chain fatty acid. Palmitic acid methyl ester (PAME), a fatty acid ester released from adipose tissue, superior cervical ganglion, and retina, has been found to have anti-inflammation, antifibrosis, and peripheral vasodilation effects. However, the effects of PAME on cardiomyocytes are still unclear. The aim of this study was to determine whether PAME could disrupt the intracellular Ca2+ balance, leading to cardiomyocyte hypertrophy. Neonatal rat cardiomyocytes were treated with various concentrations (10-100 µM) of PAME for 1-4 days. Cytosolic Ca2+ and mitochondrial Ca2+ concentrations were examined using Fura-2 AM and Rhod-2, respectively. After treatment with PAME for 4 days, mitochondrial Ca2+ , an indicator of the state of mitochondrial permeability transition pore (MPTP), and cell death were monitored by flow cytometric analysis. ATP levels were detected using the ATP assay kit. Cardiomyocyte hypertrophy was analyzed by measuring the cardiac hypertrophy biomarker and cell area using quantitative real time-polymerase chain reaction, Western Blot analysis and immunofluorescence analysis. Our results show that PAME concentration- and time-dependently increased cytosolic and mitochondria Ca2+ through the mitochondrial calcium uniporter. Moreover, treatment with PAME for 4 days caused MPTP opening, thereby reducing ATP production and enhancing reactive oxygen species (ROS) generation, and finally led to cardiomyocyte hypertrophy. These effects caused by PAME treatment were attenuated by the G-protein coupled receptor 40 (GPR40) inhibitor. In conclusion, PAME impaired mitochondrial function, which in turn led to cardiomyocyte hypertrophy through increasing the mitochondrial Ca2+ levels mediated by activating the GPR40 signaling pathway.

Application of machine learning-based models to boost the predictive power of the SPAN index.

BACKGROUND: This study re-explored the predictive validity of Stroke Prognostication using Age and National Institutes of Health Stroke Scale (SPAN) index in patients who received different treatments for acute ischemic stroke (AIS) and developed machine learning-boosted outcome prediction models. METHODS: We evaluated the prognostic relevance of SPAN index in patients with AIS who received intravenous tissue-type plasminogen activator (IV-tPA), intra-arterial thrombolysis (IAT) or non-thrombolytic treatments (non-tPA), and applied machine learning algorithms to develop SPAN-based outcome prediction models in a cohort of 2145 hospitalized AIS patients. The performance of the models was assessed and compared using the area under the receiver operating characteristic curves (AUCs). RESULTS: SPAN index ≥100 was associated with higher mortality rate and higher modified Rankin Scale at discharge in AIS patients who received the different treatments. Compared to the lower AUCs for the SPAN-alone model across all groups, the AUCs of the logistic regression-boosted model were 0.838, 0.857, 0.766 and 0.875 for the whole cohort, non-tPA, IV-tPA and IAT groups, respectively. Similarly, the AUCs of the generated artificial neural network were 0.846, 0.858, 0.785 and 0.859 for the whole cohort, non-tPA, IV-tPA and IAT groups, respectively, while for gradient boosting decision tree model, we computed 0.850, 0.863, 0.779 and 0.815. CONCLUSIONS: SPAN index has prognostic relevance in patients with AIS who received different treatments. The generated machine learning-based models exhibit good performance for predicting the functional recovery of AIS; thus, their proposed clinical application to aid outcome prediction and decision-making for the patients with AIS.

Effect of three clinical therapies on cytokines modulation in the hip articular cartilage and bone improvement in rat early osteonecrosis of the femoral head.

BACKGROUND: Extracorporeal shockwave therapy (ESWT) and adipose-derived mesenchymal stem cells (ADSCs) have been used clinically for the treatment of osteonecrosis of the femoral head (ONFH). The study elucidated that ESWT, ADSCs, and combination therapy modulated pro-inflammatory cytokines in the articular cartilage and subchondral bone of early rat ONFH. METHODS: ESWT and ADSCs were prepared and isolated for treatment. Micro-CT, pathological analysis, and immunohistochemistry were performed and analysed. RESULTS: After treatments, subchondral bone of ONFH was improved in trabecular bone volume (BV/TV) (p < 0.001), thickness (Tb.Th) (p < 0.01 and 0.001), and separation (Tb.Sp) (p < 0.001) and bone mineral density (BMD) (p < 0.001) using micro-CT analysis. The articular cartilage was protected and decreased apoptosis markers after all the treatments. The expression of IL33 (p < 0.001), IL5 (p < 0.001), IL6 (p < 0.001), and IL17A (p < 0.01) was significantly decreased in the ESWT, ADSCs, and Combination groups as compared with ONFH group. The IL33 receptor ST2 was significantly increased after treatment (p < 0.001) as compared with ONFH group. The Combination group (p < 0.01) decreased the expression of IL6 better than the ESWT and ADSCs groups. CONCLUSION: ESWT, ADSCs and combination therapy significantly protected articular cartilage and subchondral bone of early rat ONFH by modulating the expression of pro-inflammatory cytokines including, IL33 and its receptor ST2, IL5, IL6, and IL17A.

SEMRES - A Triple Security Protected Blockchain Based Medical Record Exchange Structure.

BACKGROUND AND OBJECTIVE: COVID-19, a serious infectious disease outbreak started in the end of 2019, has caused a strong impact on the overall medical system, which reflects the gap in the volume and capacity of medical services and highlights the importance of clinical data ex-change and application. The most important concerns of medical records in the medical field include data privacy, data correctness, and data security. By realizing these three goals, medical records can be made available to different hospital information systems to achieve the most complete medical care services. The privacy and protection of health data require detailed specification and usage requirements, which is particularly important for cross-agency data exchange. METHODS: This research is composed of three main modules. "Combined Encryption and Decryption Architecture", which includes the hybrid double encryption mechanism of AES and RSA, and encrypts medical records to produce "Secured Encrypted Medical Record". "Decentralize EMR Repository", which includes data decryption and an exchange mechanism. After a data transmission is completed, the content verification and data decryption process will be launched to confirm the correctness of the data and obtain the data. A blockchain architecture is used to store the hash value of the encrypted EMR, and completes the correctness verification of the EMR after transmission through the hash value. RESULTS: The results of this study provide an efficient triple encryption mechanism for electronic medical records. SEMRES ensures the correctness of data through the non-repudiation feature of a blockchain open ledger, and complete integrated information security protection and data verification architecture, in order that medical data can be exchanged, verified, and applied in different locations. After the patient receives medical services, the medical record is re-encrypted and verified and stored in the patient's medical record. The blockchain architecture is used to ensure the verification of non-repudiation of medical service, and finally to complete the payment for medical services. CONCLUSIONS: The main aim of this study was to complete a security architecture for medical data, and develop a triple encryption authentication architecture to help data owners easily and securely share personal medical records with medical service personnel.

Predicting the survivals and favorable neurologic outcomes after targeted temperature management by artificial neural networks.

BACKGROUND: To identify the outcome-associated predictors and develop predictive models for patients receiving targeted temperature management (TTM) by artificial neural network (ANN). METHODS: The derived cohort consisted of 580 patients with cardiac arrest and ROSC treated with TTM between January 2014 and August 2019. We evaluated the predictive value of parameters associated with survival and favorable neurologic outcome. ANN were applied for developing outcome prediction models. The generalizability of the models was assessed through 5-fold cross-validation. The performance of the models was assessed according to the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). RESULTS: The parameters associated with survival were age, duration of cardiopulmonary resuscitation, history of diabetes mellitus (DM), heart failure, end-stage renal disease (ESRD), systolic blood pressure (BP), diastolic BP, body temperature, motor response after ROSC, emergent coronary angiography or percutaneous coronary intervention (PCI), and the cooling methods. The parameters associated with the favorable neurologic outcomes were age, sex, DM, chronic obstructive pulmonary disease, ESRD, stroke, pre-arrest cerebral-performance category, BP, body temperature, motor response after ROSC, emergent coronary angiography or PCI, and cooling methods. After adequate training, ANN Model 1 to predict survival achieved an AUC of 0.80. Accuracy, sensitivity, and specificity were 75.9%, 71.6%, and 79.3%, respectively. ANN Model 4 to predict the favorable neurologic outcome achieved an AUC of 0.87, with accuracy, sensitivity, and specificity of 86.7%, 77.7%, and 88.0%, respectively. CONCLUSION: The ANN-based models achieved good performance to predict the survival and favorable neurologic outcomes after TTM. The models proposed have clinical value to assist in decision-making.

Exploring the COVID-19 Pandemic as a Catalyst for Behavior Change Among Patient Health Record App Users in Taiwan: Development and Usability Study.

BACKGROUND: During the COVID-19 pandemic, personal health records (PHRs) have enabled patients to monitor and manage their medical data without visiting hospitals and, consequently, minimize their infection risk. Taiwan's National Health Insurance Administration (NHIA) launched the My Health Bank (MHB) service, a national PHR system through which insured individuals to access their cross-hospital medical data. Furthermore, in 2019, the NHIA released the MHB software development kit (SDK), which enables development of mobile apps with which insured individuals can retrieve their MHB data. However, the NHIA MHB service has its limitations, and the participation rate among insured individuals is low. OBJECTIVE: We aimed to integrate the MHB SDK with our developed blockchain-enabled PHR mobile app, which enables patients to access, store, and manage their cross-hospital PHR data. We also collected and analyzed the app's log data to examine patients' MHB use during the COVID-19 pandemic. METHODS: We integrated our existing blockchain-enabled mobile app with the MHB SDK to enable NHIA MHB data retrieval. The app utilizes blockchain technology to encrypt the downloaded NHIA MHB data. Existing and new indexes can be synchronized between the app and blockchain nodes, and high security can be achieved for PHR management. Finally, we analyzed the app's access logs to compare patients' activities during high and low COVID-19 infection periods. RESULTS: We successfully integrated the MHB SDK into our mobile app, thereby enabling patients to retrieve their cross-hospital medical data, particularly those related to COVID-19 rapid and polymerase chain reaction testing and vaccination information and progress. We retrospectively collected the app's log data for the period of July 2019 to June 2021. From January 2020, the preliminary results revealed a steady increase in the number of people who applied to create a blockchain account for access to their medical data and the number of app subscribers among patients who visited the outpatient department (OPD) and emergency department (ED). Notably, for patients who visited the OPD and ED, the peak proportions with respect to the use of the app for OPD and ED notes and laboratory test results also increased year by year. The highest proportions were 52.40% for ED notes in June 2021, 88.10% for ED laboratory test reports in May 2021, 34.61% for OPD notes in June 2021, and 41.87% for OPD laboratory test reports in June 2021. These peaks coincided with Taiwan's local COVID-19 outbreak lasting from May to June 2021. CONCLUSIONS: This study developed a blockchain-enabled mobile app, which can periodically retrieve and integrate PHRs from the NHIA MHB's cross-hospital data and the investigated hospital's self-pay medical data. Analysis of users' access logs revealed that the COVID-19 pandemic substantially increased individuals' use of PHRs and their health awareness with respect to COVID-19 prevention.

Distinguishing different types of attention deficit hyperactivity disorder in children using artificial neural network with clinical intelligent test.

Background: Attention deficit hyperactivity disorder (ADHD) is a well-studied topic in child and adolescent psychiatry. ADHD diagnosis relies on information from an assessment scale used by teachers and parents and psychological assessment by physicians; however, the assessment results can be inconsistent. Purpose: To construct models that automatically distinguish between children with predominantly inattentive-type ADHD (ADHD-I), with combined-type ADHD (ADHD-C), and without ADHD. Methods: Clinical records with age 6-17 years-old, for January 2011-September 2020 were collected from local general hospitals in northern Taiwan; the data were based on the SNAP-IV scale, the second and third editions of Conners' Continuous Performance Test (CPT), and various intelligence tests. This study used an artificial neural network to construct the models. In addition, k-fold cross-validation was applied to ensure the consistency of the machine learning results. Results: We collected 328 records using CPT-3 and 239 records using CPT-2. With regard to distinguishing between ADHD-I and ADHD-C, a combination of demographic information, SNAP-IV scale results, and CPT-2 results yielded overall accuracies of 88.75 and 85.56% in the training and testing sets, respectively. The replacement of CPT-2 with CPT-3 results in this model yielded an overall accuracy of 90.46% in the training set and 89.44% in the testing set. With regard to distinguishing between ADHD-I, ADHD-C, and the absence of ADHD, a combination of demographic information, SNAP-IV scale results, and CPT-2 results yielded overall accuracies of 86.74 and 77.43% in the training and testing sets, respectively. Conclusion: This proposed model distinguished between the ADHD-I and ADHD-C groups with 85-90% accuracy, and it distinguished between the ADHD-I, ADHD-C, and control groups with 77-86% accuracy. The machine learning model helps clinicians identify patients with ADHD in a timely manner.

Applying artificial neural network for early detection of sepsis with intentionally preserved highly missing real-world data for simulating clinical situation.

PURPOSE: Some predictive systems using machine learning models have been developed to predict sepsis; however, they were mostly built with a low percent of missing values, which does not correspond with the actual clinical situation. In this study, we developed a machine learning model with a high rate of missing and erroneous data to enable prediction under missing, noisy, and erroneous inputs, as in the actual clinical situation. MATERIALS AND METHODS: The proposed artificial neural network model was implemented using the MATLAB ANN toolbox, based on stochastic gradient descent. The dataset was collected over the past decade with approval from the appropriate institutional review boards, and the sepsis status was identified and labeled using Sepsis-3 clinical criteria. The imputation method was built by last observation carried forward and mean value, aimed to simulate clinical situation. RESULTS: The mean area under the receiver operating characteristic (ROC) curve (AUC) of classifying sepsis and nonsepsis patients was 0.82 and 0.786 at 0 h and 40 h prior to onset, respectively. The highest model performance was found for one-hourly data, demonstrating that our ANN model can perform adequately with limited hourly data provided. CONCLUSIONS: Our model has the moderate ability to predict sepsis up to 40 h in advance under simulated clinical situation with real-world data.

Plasma extracellular vesicles tau and ß-amyloid as biomarkers of cognitive dysfunction of Parkinson's disease.

The contribution of circulatory tau and ß-amyloid in Parkinson's disease (PD), especially the cognitive function, remains inconclusive. Extracellular vesicles (EVs) cargo these proteins throughout the bloodstream after they are directly secreted from many cells, including neurons. The present study aims to investigate the role of the plasma EV-borne tau and ß-amyloid as biomarkers for cognitive dysfunction in PD by investigating subjects with mild to moderate stage of PD (n = 116) and non-PD controls (n = 46). Plasma EVs were isolated, and immunomagnetic reduction-based immunoassay was used to assess the levels of α-synuclein, tau, and ß-amyloid 1-42 (Aß1-42) within the EVs. Artificial neural network (ANN) models were then applied to predict cognitive dysfunction. We observed no significant difference in plasma EV tau and Aß1-42 between PD patients and controls. Plasma EV tau was significantly associated with cognitive function. Moreover, plasma EV tau and Aß1-42 were significantly elevated in PD patients with cognitive impairment when compared to PD patients with optimal cognition. The ANN model used the plasma EV α-synuclein, tau, and Aß1-42, as well as the patient's age and gender, as predicting factors. The model achieved an accuracy of 91.3% in identifying cognitive dysfunction in PD patients, and plasma EV tau and Aß1-42 are the most valuable factors. In conclusion, plasma EV tau and Aß1-42 are significant markers of cognitive function in PD patients. Combining with the plasma EV α-synuclein, age, and sex, plasma EV tau and Aß1-42 can identify cognitive dysfunction in PD patients. This study corroborates the prognostic roles of plasma EV tau and Aß1-42 in PD.

Extracorporeal Shockwave Therapy Modulates the Expressions of Proinflammatory Cytokines IL33 and IL17A, and Their Receptors ST2 and IL17RA, within the Articular Cartilage in Early Avascular Necrosis of the Femoral Head in a Rat Model.

Avascular necrosis (AVN) of the femoral head (AVNFH) is a disease caused by injury to the blood supply of the femoral head, resulting in a collapse with osteonecrosis and damage to the articular cartilage. Extracorporeal shockwave therapy (ESWT) has been demonstrated to improve AVNFH owing to its anti-inflammation activity, angiogenesis effect, and tissue regeneration in clinical treatment. However, there are still so many pieces of the jigsaw that need to be fit into place in order to ascertain the mechanism of ESWT for the treatment of AVNFH. The study demonstrated that ESWT significantly protected the trabecular bone volume fraction BV/TV (P < 0.01) and the trabecular thickness (P < 0.001), while in contrast, the trabecular number and trabecular separation were not significantly different after treatment as compared with AVNFH. ESWT protected the articular cartilage in animal model of AVNFH. The levels of IL1-ß and IL33 were significantly induced in the AVNFH group (P < 0.001) as compared with Sham and ESWT groups and reduced in ESWT group (P < 0.001) as compared with AVNFH group. In addition, the expression of the receptor of IL33, ST2, was reduced in AVNFH and induced after ESWT (P < 0.001). The expression of IL17A was induced in the AVNFH group (P < 0.001) and reduced in the ESWT group (P < 0.001). Further, the expression of the receptor of IL17A, IL17RA, was reduced in the AVNFH group (P < 0.001) and improved to a normal level in the ESWT group as compared with Sham group (P < 0.001). Taken together, the results of the study indicated that ESWT modulated the expression of IL1-ß, pro-inflammatory cytokines IL33 and IL17A, and their receptors ST2 and IL17RA, to protect against loss of the extracellular matrix in the articular cartilage of early AVNFH.

Automatic classification of medical image modality and anatomical location using convolutional neural network.

Modern radiologic images comply with DICOM (digital imaging and communications in medicine) standard, which, upon conversion to other image format, would lose its image detail and information such as patient demographics or type of image modality that DICOM format carries. As there is a growing interest in using large amount of image data for research purpose and acquisition of large amount of medical image is now a standard practice in the clinical setting, efficient handling and storage of large amount of image data is important in both the clinical and research setting. In this study, four classes of images were created, namely, CT (computed tomography) of abdomen, CT of brain, MRI (magnetic resonance imaging) of brain and MRI of spine. After converting these images into JPEG (Joint Photographic Experts Group) format, our proposed CNN architecture could automatically classify these 4 groups of medical images by both their image modality and anatomic location. We achieved excellent overall classification accuracy in both validation and test sets (> 99.5%), specificity and F1 score (> 99%) in each category of this dataset which contained both diseased and normal images. Our study has shown that using CNN for medical image classification is a promising methodology and could work on non-DICOM images, which could potentially save image processing time and storage space.

Identifying prognostic factors and developing accurate outcome predictions for in-hospital cardiac arrest by using artificial neural networks.

BACKGROUND: Accurate estimation of neurological outcomes after in-hospital cardiac arrest (IHCA) provides crucial information for clinical management. This study used artificial neural networks (ANNs) to determine the prognostic factors and develop prediction models for IHCA based on immediate preresuscitation parameters. METHODS: The derived cohort comprised 796 patients with IHCA between 2006 and 2014. We applied ANNs to develop prediction models and evaluated the significance of each parameter associated with favorable neurological outcomes. An independent dataset of 108 IHCA patients receiving targeted temperature management was used to validate the identified parameters. The generalizability of the models was assessed through fivefold cross-validation. The performance of the models was assessed using the area under the curve (AUC). RESULTS: ANN model 1, based on 19 baseline parameters, and model 2, based on 11 prearrest parameters, achieved validation AUCs of 0.978 and 0.947, respectively. ANN model 3 based on 30 baseline and prearrest parameters achieved an AUC of 0.997. The key factors associated with favorable outcomes were the duration of cardiopulmonary resuscitation; initial cardiac arrest rhythm; arrest location; and whether the patient had a malignant disease, pneumonia, and respiratory insufficiency. On the basis of these parameters, the validation performance of the ANN models achieved an AUC of 0.906 for IHCA patients who received targeted temperature management. CONCLUSION: The ANN models achieved highly accurate and reliable performance for predicting the neurological outcomes of successfully resuscitated patients with IHCA. These models can be of significant clinical value in assisting with decision-making, especially regarding optimal postresuscitation strategies.

Artificial neural network based prediction of postthrombolysis intracerebral hemorrhage and death.

Despite the salient benefits of the intravenous tissue plasminogen activator (tPA), symptomatic intracerebral hemorrhage (sICH) remains a frequent complication and constitutes a major concern when treating acute ischemic stroke (AIS). This study explored the use of artificial neural network (ANN)-based models to predict sICH and 3-month mortality for patients with AIS receiving tPA. We developed ANN models based on evaluation of the predictive value of pre-treatment parameters associated with sICH and mortality in a cohort of 331 patients between 2009 and 2018. The ANN models were generated using eight clinical inputs and two outputs. The generalizability of the model was validated using fivefold cross-validation. The performance of each model was assessed according to the accuracy, precision, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). After adequate training, the ANN predictive model AUC for sICH was 0.941, with accuracy, sensitivity, and specificity of 91.0%, 85.7%, and 92.5%, respectively. The predictive model AUC for 3-month mortality was 0.976, with accuracy, sensitivity, and specificity of 95.2%, 94.4%, and 95.5%, respectively. The generated ANN-based models exhibited high predictive performance and reliability for predicting sICH and 3-month mortality after thrombolysis; thus, its clinical application to assist decision-making when administering tPA is envisaged.

Increase Risk of Dementia in Patients With Sudden Hearing Loss: A Population-Based Cohort Study With 7-Year Follow-Up in Taiwan.

OBJECTIVE: To investigate the prevalence and risk of subsequent dementia in subjects with sudden hearing loss during a 7-year follow-up period through comparisons with cohorts matched by sex, age group, and year of index date. STUDY DESIGN: A retrospective matched-cohort study. SETTING: The Longitudinal Health Insurance Database 2000 (LHID2000) in Taiwan. PATIENTS: This study included a total of 11,148 subjects, including 1,858 in the study group and 9,290 in the comparison cohort group. INTERVENTION(S): None. MAIN OUTCOME MEASURE(S): We analyzed the differences in sociodemographic characteristics and comorbidities between subjects with sudden hearing loss and the comparison cohort group. Then, we estimated the risk of dementia and also plotted the survival outcomes to evaluate differences in dementia-free survival rates between the two groups. RESULTS: The dementia incidence rates per 1000 person-years were 20.45 and 8.15 for the subjects with sudden hearing loss and comparison cohorts, respectively. When we adjusted for the subjects' characteristics, the hazard ratio for dementia was 1.69 (95% confidence interval [CI] = 1.06-2.68, p < 0.01) for subjects with sudden hearing loss compared with comparison cohorts during the follow-up period, and subjects with sudden hearing loss had lower 7-year dementia-free survival rates compared with comparison cohorts by using a log-rank test. Furthermore, male subjects with sudden hearing loss had a higher risk of dementia (adjusted hazard ratio [HR] = 2.11) than did the male comparison cohorts. CONCLUSIONS: This study revealed a relationship between sudden hearing loss and dementia in an Asian country. The risk of dementia was higher among patients with sudden hearing loss compared with matched cohorts during the 7-year follow-up period.

Predicting major neurologic improvement and long-term outcome after thrombolysis using artificial neural networks.

OBJECTIVE: To develop artificial neural network (ANN)-based functional outcome prediction models for patients with acute ischemic stroke (AIS) receiving intravenous thrombolysis based on immediate pretreatment parameters. METHODS: The derived cohort consisted of 196 patients with AIS treated with intravenous thrombolysis between 2009 and 2017 at Shuang Ho Hospital in Taiwan. We evaluated the predictive value of parameters associated with major neurologic improvement (MNI) at 24 h after thrombolysis as well as the 3-month outcome. ANN models were applied for outcome prediction. The generalizability of the model was assessed through 5-fold cross-validation. The performance of the models was assessed according to the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC), RESULTS: The parameters associated with MNI were blood pressure (BP), heart rate, glucose level, consciousness level, National Institutes of Health Stroke Scale (NIHSS) score, and history of diabetes mellitus (DM). The parameters associated with the 3-month outcome were age, consciousness level, BP, glucose level, hemoglobin A1c, history of DM, stroke subtype, and NIHSS score. After adequate training, ANN Model 1 to predict MNI achieved an AUC of 0.944. Accuracy, sensitivity, and specificity were 94.6%, 89.8%, and 95.9%, respectively. ANN Model 2 to predict the 3-month outcome achieved an AUC of 0.933, with accuracy, sensitivity, and specificity of 88.8%, 94.7%, and 86.5%, respectively. CONCLUSIONS: The ANN-based models achieved reliable performance to predict MNI and 3-month outcomes after thrombolysis for AIS. The models proposed have clinical value to assist in decision-making, especially when invasive adjuvant strategies are considered.

Palmitic Acid Methyl Ester Induces G2/M Arrest in Human Bone Marrow-Derived Mesenchymal Stem Cells via the p53/p21 Pathway.

Bone marrow-derived mesenchymal cells (BM-MSCs) are able to differentiate into adipocytes, which can secrete adipokines to affect BM-MSC proliferation and differentiation. Recent evidences indicated that adipocytes can secrete fatty acid metabolites, such as palmitic acid methyl ester (PAME), which is able to cause vasorelaxation and exerts anti-inflammatory effects. However, effects of PAME on BM-MSC proliferation remain unclear. The aim of this study was to investigate the effect of PAME on human BM-MSC (hBM-MSC) proliferation and its underlying molecular mechanisms. hBM-MSCs were treated with PAME for 48 h and then subjected to various analyses. The results from the present study show that PAME significantly reduced the levels of G2/M phase regulatory proteins, cyclin-dependent kinase 1 (Cdk1), and cyclin B1 and inhibited proliferation in hBM-MSCs. Moreover, the level of Mdm2 protein decreased, while the levels of p21 and p53 protein increased in the PAME-treated hBM-MSCs. However, PAME treatment did not significantly affect apoptosis/necrosis, ROS generation, and the level of Cdc25C protein. PAME also induced intracellular acidosis and increased intracellular Ca2+ levels. Cotreatment with PAME and Na+/H+ exchanger inhibitors together further reduced the intracellular pH but did not affect the PAME-induced decreases of cell proliferation and increases of the cell population at the G2/M phase. Cotreatment with PAME and a calcium chelator together inhibited the PAME-increased intracellular Ca2+ levels but did not affect the PAME-induced cell proliferation inhibition and G2/M cell cycle arrest. Moreover, the half-life of p53 protein was prolonged in the PAME-treated hBM-MSCs. Taken together, these results suggest that PAME induced p53 stabilization, which in turn increased the levels of p53/p21 proteins and decreased the levels of Cdk1/cyclin B1 proteins, thereby preventing the activation of Cdk1, and eventually caused cell cycle arrest at the G2/M phase. The findings from the present study might help get insight into the physiological roles of PAME in regulating hBM-MSC proliferation.