Deep learning to refine the identification of high-quality clinical research articles from the biomedical literature: Performance evaluation.

BACKGROUND: Identifying practice-ready evidence-based journal articles in medicine is a challenge due to the sheer volume of biomedical research publications. Newer approaches to support evidence discovery apply deep learning techniques to improve the efficiency and accuracy of classifying sound evidence. OBJECTIVE: To determine how well deep learning models using variants of Bidirectional Encoder Representations from Transformers (BERT) identify high-quality evidence with high clinical relevance from the biomedical literature for consideration in clinical practice. METHODS: We fine-tuned variations of BERT models (BERTBASE, BioBERT, BlueBERT, and PubMedBERT) and compared their performance in classifying articles based on methodological quality criteria. The dataset used for fine-tuning models included titles and abstracts of >160,000 PubMed records from 2012 to 2020 that were of interest to human health which had been manually labeled based on meeting established critical appraisal criteria for methodological rigor. The data was randomly divided into 80:10:10 sets for training, validating, and testing. In addition to using the full unbalanced set, the training data was randomly undersampled into four balanced datasets to assess performance and select the best performing model. For each of the four sets, one model that maintained sensitivity (recall) at ≥99% was selected and were ensembled. The best performing model was evaluated in a prospective, blinded test and applied to an established reference standard, the Clinical Hedges dataset. RESULTS: In training, three of the four selected best performing models were trained using BioBERTBASE. The ensembled model did not boost performance compared with the best individual model. Hence a solo BioBERT-based model (named DL-PLUS) was selected for further testing as it was computationally more efficient. The model had high recall (>99%) and 60% to 77% specificity in a prospective evaluation conducted with blinded research associates and saved >60% of the work required to identify high quality articles. CONCLUSIONS: Deep learning using pretrained language models and a large dataset of classified articles produced models with improved specificity while maintaining >99% recall. The resulting DL-PLUS model identifies high-quality, clinically relevant articles from PubMed at the time of publication. The model improves the efficiency of a literature surveillance program, which allows for faster dissemination of appraised research.

Tracking auditory mismatch negativity responses during full conscious state and coma.

The mismatch negativity (MMN) is considered the electrophysiological change-detection response of the brain, and therefore a valuable clinical tool for monitoring functional changes associated with return to consciousness after severe brain injury. Using an auditory multi-deviant oddball paradigm, we tracked auditory MMN responses in seventeen healthy controls over a 12-h period, and in three comatose patients assessed over 24 h at two time points. We investigated whether the MMN responses show fluctuations in detectability over time in full conscious awareness, or whether such fluctuations are rather a feature of coma. Three methods of analysis were utilized to determine whether the MMN and subsequent event-related potential (ERP) components could be identified: traditional visual analysis, permutation t-test, and Bayesian analysis. The results showed that the MMN responses elicited to the duration deviant-stimuli are elicited and reliably detected over the course of several hours in healthy controls, at both group and single-subject levels. Preliminary findings in three comatose patients provide further evidence that the MMN is often present in coma, varying within a single patient from easily detectable to undetectable at different times. This highlights the fact that regular and repeated assessments are extremely important when using MMN as a neurophysiological predictor of coma emergence.

Multi-Center Validation Study of Automated Classification of Pathological Slowing in Adult Scalp Electroencephalograms Via Frequency Features.

Pathological slowing in the electroencephalogram (EEG) is widely investigated for the diagnosis of neurological disorders. Currently, the gold standard for slowing detection is the visual inspection of the EEG by experts, which is time-consuming and subjective. To address those issues, we propose three automated approaches to detect slowing in EEG: Threshold-based Detection System (TDS), Shallow Learning-based Detection System (SLDS), and Deep Learning-based Detection System (DLDS). These systems are evaluated on channel-, segment-, and EEG-level. The three systems perform prediction via detecting slowing at individual channels, and those detections are arranged in histograms for detection of slowing at the segment- and EEG-level. We evaluate the systems through Leave-One-Subject-Out (LOSO) cross-validation (CV) and Leave-One-Institution-Out (LOIO) CV on four datasets from the US, Singapore, and India. The DLDS achieved the best overall results: LOIO CV mean balanced accuracy (BAC) of 71.9%, 75.5%, and 82.0% at channel-, segment- and EEG-level, and LOSO CV mean BAC of 73.6%, 77.2%, and 81.8% at channel-, segment-, and EEG-level. The channel- and segment-level performance is comparable to the intra-rater agreement (IRA) of an expert of 72.4% and 82%. The DLDS can process a 30 min EEG in 4 s and can be deployed to assist clinicians in interpreting EEGs.

Automated Detection of Interictal Epileptiform Discharges from Scalp Electroencephalograms by Convolutional Neural Networks.

Visual evaluation of electroencephalogram (EEG) for Interictal Epileptiform Discharges (IEDs) as distinctive biomarkers of epilepsy has various limitations, including time-consuming reviews, steep learning curves, interobserver variability, and the need for specialized experts. The development of an automated IED detector is necessary to provide a faster and reliable diagnosis of epilepsy. In this paper, we propose an automated IED detector based on Convolutional Neural Networks (CNNs). We have evaluated the proposed IED detector on a sizable database of 554 scalp EEG recordings (84 epileptic patients and 461 nonepileptic subjects) recorded at Massachusetts General Hospital (MGH), Boston. The proposed CNN IED detector has achieved superior performance in comparison with conventional methods with a mean cross-validation area under the precision-recall curve (AUPRC) of 0.838[Formula: see text]±[Formula: see text]0.040 and false detection rate of 0.2[Formula: see text]±[Formula: see text]0.11 per minute for a sensitivity of 80%. We demonstrated the proposed system to be noninferior to 30 neurologists on a dataset from the Medical University of South Carolina (MUSC). Further, we clinically validated the system at National University Hospital (NUH), Singapore, with an agreement accuracy of 81.41% with a clinical expert. Moreover, the proposed system can be applied to EEG recordings with any arbitrary number of channels.

A fast machine learning approach to facilitate the detection of interictal epileptiform discharges in the scalp electroencephalogram.

BACKGROUND: Finding interictal epileptiform discharges (IEDs) in the EEG is a part of diagnosing epilepsy. Automated software for annotating EEGs of patients with suspected epilepsy can therefore help with reaching a diagnosis. A large amount of data is required for training and evaluating an effective IED detection system. IEDs occur infrequently in the most patients' EEG, therefore, interictal EEG recordings contain mostly background waveforms. NEW METHOD: As the first step to detect IEDs, we propose a machine learning technique eliminating most EEG background data using an ensemble of simple fast classifiers based on several EEG features. This could save computation time for an IED detection method, allowing the remaining waveforms to be classified by more computationally intensive methods. We consider several efficient features and reject background by applying thresholds on them in consecutive steps. RESULTS: We applied the proposed algorithm on a dataset of 156 EEGs (93 and 63 with and without IEDs, respectively). We were able to eliminate 78% of background waveforms while retaining 97% of IEDs on our cross-validated dataset. COMPARISON WITH EXISTING METHODS: We applied support vector machine, k-nearest neighbours, and random forest classifiers to detect IEDs with and without initial background rejection. Results show that rejecting background by our proposed method speeds up the overall classification by a factor ranging from 1.8 to 4.7 for the considered classifiers. CONCLUSIONS: The proposed method successfully reduces computation time of an IED detection system. Therefore, it is beneficial in speeding up IED detection especially when utilizing large EEG datasets.

The apoptotic effects of Brucea javanica fruit extract against HT29 cells associated with p53 upregulation and inhibition of NF-κB translocation.

BACKGROUND: Brucea javanica (L.) Merr. is a plant from the genus Brucea, which is used in local traditional medicine to treat various diseases. Recent studies revealed an impressive anticancer efficiency of B. javanica extract in different types of cancer cells. PURPOSE: In this study, we have investigated the cytotoxic effects of the B. javanica hexane, ethanolic extracts against colon cancer cells. HT29 colon cells were selected as an in vitro cancer model to evaluate the anticancer activity of B. javanica ethanolic extract (BJEE) and the possible mechanisms of action that induced apoptosis. METHODS: 3-(4,5-dimethylthiazol-2-yl)-2, 5,-diphenyltetrazolium bromide (MTT), lactate dehydrogenase, acridine orange/propidium iodide, and annexin-V-fluorescein isothiocyanate assays were performed to determine the antiproliferative and apoptosis validation of BJEE on cancer cells. Measurement of reactive oxygen species (ROS) production, caspase activities, nucleus factor-κB activity, and gene expression experiments was done to investigate the potential mechanisms of action in the apoptotic process. RESULTS: The results obtained from this study illustrated the significant antiproliferative effect of BJEE on colorectal cancer cells, with a concentration value that inhibits 50% of the cell growth of 25±3.1 µg/mL after 72 h of treatment. MTT assay demonstrated that the BJEE is selectively toxic to cancer cells, and BJEE induced cell apoptosis via activation of caspase-8 along with modulation of apoptosis-related proteins such as Fas, CD40, tumor necrosis factor-related apoptosis-inducing ligands, and tumor necrosis factor receptors, which confirmed the contribution of extrinsic pathway. Meanwhile, increased ROS production in treated cells subsequently activated caspase-9 production, which triggered the intrinsic pathways. In addition, overexpression of cytochrome-c, Bax, and Bad proteins along with suppression of Bcl-2 illustrated that mitochondrial-dependent pathway also contributed to BJEE-induced cell death. Consistent with the findings from this study, BJEE-induced cancer cell death proceeds via extrinsic and intrinsic mitochondrial-dependent and -independent events. CONCLUSION: From the evidence obtained from this study, it is concluded that the BJEE is a promising natural extract to combat colorectal cancer cells (HT29 cells) via induction of apoptosis through activation of extrinsic and intrinsic pathways.

Synthesis of Novel Derivatives of Quinazoline Schiff base Compound Promotes Epithelial Wound Healing.

Quinazoline is an aromatic bicyclic compound exhibiting several pharmaceutical and biological activities. This study was conducted to investigate the potential wound healing properties of Synthetic Quinazoline Compound (SQC) on experimental rats. The toxicity of SQC was determined by MTT cell proliferation assay. The healing effect of SQC was assessed by in vitro wound healing scratch assay on the skin fibroblast cells (BJ-5ta) and in vivo wound healing experiment of low and high dose of SQC on adult Sprague-Dawley rats compared with negative (gum acacia) and positive control (Intrasite-gel). Hematoxylin and Eosin (H&E), Masson's Trichrome (MT) staining and immunohistochemistry analysis were performed to evaluate the histopathological alterations and proteins expression of Bax and Hsp70 on the wound tissue after 10 days. In addition, levels of antioxidant enzymes (catalase, glutathione peroxidase and superoxide dismutase), and malondialdehyde (MDA) were measured in wound tissue homogenates. The SQC significantly enhanced BJ-5ta cell proliferation and accelerated the percentage of wound closure, with less scarring, increased fibroblast and collagen fibers and less inflammatory cells compared with the negative control. The compound also increases endogenous enzymes and decline lipid peroxidation in wound homogenate.

CLASSIFIER CASCADE TO AID IN DETECTION OF EPILEPTIFORM TRANSIENTS IN INTERICTAL EEG.

The presence of Epileptiform Transients (ET) in the electroencephalogram (EEG) is a key finding in the medical workup of a patient with suspected epilepsy. Automated ET detection can increase the uniformity and speed of ET detection. Current ET detection methods suffer from insufficient precision and high false positive rates. Since ETs occur infrequently in the EEG of most patients, the majority of recordings comprise background EEG waveforms. In this work we establish a method to exclude as much background data as possible from EEG recordings by applying a classifier cascade. The remaining data can then be classified using other ET detection methods. We compare a single Support Vector Machine (SVM) to a cascade of SVMs for detecting ETs. Our results show that the precision and false positive rate improve significantly by incorporating a classifier cascade before ET detection. Our method can help improve the precision and false positive rate of an ET detection system. At a fixed sensitivity, we were able to improve precision by 6.78%; and at a fixed false positive rate, the sensitivity improved by 2.83%.

Interictal epileptiform discharge characteristics underlying expert interrater agreement.

OBJECTIVE: The presence of interictal epileptiform discharges (IED) in the electroencephalogram (EEG) is a key finding in the medical workup of a patient with suspected epilepsy. However, inter-rater agreement (IRA) regarding the presence of IED is imperfect, leading to incorrect and delayed diagnoses. An improved understanding of which IED attributes mediate expert IRA might help in developing automatic methods for IED detection able to emulate the abilities of experts. Therefore, using a set of IED scored by a large number of experts, we set out to determine which attributes of IED predict expert agreement regarding the presence of IED. METHODS: IED were annotated on a 5-point scale by 18 clinical neurophysiologists within 200 30-s EEG segments from recordings of 200 patients. 5538 signal analysis features were extracted from the waveforms, including wavelet coefficients, morphological features, signal energy, nonlinear energy operator response, electrode location, and spectrogram features. Feature selection was performed by applying elastic net regression and support vector regression (SVR) was applied to predict expert opinion, with and without the feature selection procedure and with and without several types of signal normalization. RESULTS: Multiple types of features were useful for predicting expert annotations, but particular types of wavelet features performed best. Local EEG normalization also enhanced best model performance. As the size of the group of EEGers used to train the models was increased, the performance of the models leveled off at a group size of around 11. CONCLUSIONS: The features that best predict inter-rater agreement among experts regarding the presence of IED are wavelet features, using locally standardized EEG. Our models for predicting expert opinion based on EEGer's scores perform best with a large group of EEGers (more than 10). SIGNIFICANCE: By examining a large group of EEG signal analysis features we found that wavelet features with certain wavelet basis functions performed best to identify IEDs. Local normalization also improves predictability, suggesting the importance of IED morphology over amplitude-based features. Although most IED detection studies in the past have used opinion from three or fewer experts, our study suggests a "wisdom of the crowd" effect, such that pooling over a larger number of expert opinions produces a better correlation between expert opinion and objectively quantifiable features of the EEG.

The antiulcer effect of Cibotium barometz leaves in rats with experimentally induced acute gastric ulcer.

Cibotium barometz is a pharmaceutical plant customarily used in traditional medicine in Malaysia for the treatment of different diseases, such as gastric ulcer. The gastroprotective effect of C. barometz leaves against ethanol-induced gastric hemorrhagic abrasions in Sprague Dawley rats has been evaluated in terms of medicinal properties. Seven groups of rats (normal control and ulcerated control groups, omeprazole 20 mg/kg, 62.5, 125, 250, and 500 mg/kg of C. barometz correspondingly) were used in antiulcer experiment and pretreated with 10% Tween 20. After 1 hour, the normal group was orally administered 10% Tween 20, whereas absolute alcohol was fed orally to ulcerated control, omeprazole, and experimental groups. Gastric's homogenate were assessed for endogenous enzymes activities. Stomachs were examined macroscopically and histologically. Grossly, the data demonstrated a significant decrease in the ulcer area of rats pretreated with plant extract in a dose-dependent manner with respect to the ulcerated group. Homogenates of the gastric tissue exhibited significantly increased endogenous enzymes activities in rats pretreated with C. barometz extract associated with the ulcerated control group. Histology of rats pretreated with C. barometz extract group using hematoxylin and eosin staining exhibited a moderate-to-mild disruption of the surface epithelium with reduction in submucosal edema and leucocyte infiltration in a dose-dependent manner. In addition, it showed heat shock protein70 protein up-expression and BCL2-associated X protein downexpression. These outcomes might be attributed to the gastroprotective and antioxidative effects of the plant.

Synthesis and Characterization of a New Benzoindole Derivative with Apoptotic Activity Against Colon Cancer Cells.

BACKGROUND: Colorectal cancer is the third most common form of cancer in both men and women around the world. The chemistry and biological study of heterocyclic compounds have been an interesting area for a long time in pharmaceutical and medicinal chemistry. METHODS: A new synthetic compound, 2-(1,1-dimethyl-1H-benzo[e]indol-2-yl)-3-((2-hydroxyphenyl)amino) acrylaldehyde, abbreviated as DBID, was prepared through the reaction of 2-(diformylmethylidene)-1,1- dimethylbenzo[e]indole with 2-aminophenol. The chemical structure of the synthesized compound was characterized by 1H NMR, 13C NMR and APT-NMR spectroscopy and confirmed by elemental analysis (CHN). The compound was screened for the antiproliferation effect against colorectal cancer cell line, HCT 116 and its possible mechanism of action was elucidated. To determine the IC50 value, the MTT assay was used and its apoptosisinducing effect was investigated. RESULTS: DBID inhibited the proliferation of HCT 116 cells with an IC50 of 9.32 µg/ml and significantly increased the levels of caspase -8, -9 and -3/7 in the treated cells compared to untreated cells. Apoptosis features in HCT 116 cell was detected in treated cells by using the AO/PI staining that confirmed that the cells had undergone remarkable morphological changes in apoptotic bodies. Furthermore, this changes in expression of caspase -8, -9 and -3 were confirmed by gene and protein quantification using RT-PCR and western blot analysis, respectively. CONCLUSION: The current study showed that the DBID compound has demonstrated chemotherapeutic activity which was evidenced by significant increases in the expression and activation of caspase and exploit the apoptotic signaling pathways to trigger cancer cell death.

FAST AND EFFICIENT REJECTION OF BACKGROUND WAVEFORMS IN INTERICTAL EEG.

Automated annotation of electroencephalograms (EEG) of epileptic patients is important in diagnosis and management of epilepsy. Epilepsy is often associated with the presence of epileptiform transients (ET) in the EEG. To develop an efficient ET detector, a vast amount of data is required to train and evaluate the performance of the detector. Interictal EEG data contains mostly background waveforms, since ETs only occur occasionally in most patients. In order to detect ETs in an automated fashion, it is meaningful to first try to eliminate most background waveforms by means of simple, fast classifiers. The remaining waveforms can in a following step be processed by more sophisticated and computationally demanding classification algorithms, such as deep learning systems. In this study, we design a cascade of simple thresholding steps to reject most background waveforms in interictal EEG, while maintaining most ETs. Several simple and quick-to-compute EEG features are chosen. By thresholding these features in consecutive steps, background waveforms are rejected sequentially. In our numerical experiments, a cascade of 10 steps is able to reject 98.65% of all background segments in the dataset, while preserving 90.6% of the ETs.