Reporting of equity in observational epidemiology: A methodological review.

Background: Observational studies can inform how we understand and address persisting health inequities through the collection, reporting and analysis of health equity factors. However, the extent to which the analysis and reporting of equity-relevant aspects in observational research are generally unknown. Thus, we aimed to systematically evaluate how equity-relevant observational studies reported equity considerations in the study design and analyses. Methods: We searched MEDLINE for health equity-relevant observational studies from January 2020 to March 2022, resulting in 16 828 articles. We randomly selected 320 studies, ensuring a balance in focus on populations experiencing inequities, country income settings, and coronavirus disease 2019 (COVID-19) topic. We extracted information on study design and analysis methods. Results: The bulk of the studies were conducted in North America (n = 95, 30%), followed by Europe and Central Asia (n = 55, 17%). Half of the studies (n = 171, 53%) addressed general health and well-being, while 49 (15%) focused on mental health conditions. Two-thirds of the studies (n = 220, 69%) were cross-sectional. Eight (3%) engaged with populations experiencing inequities, while 22 (29%) adapted recruitment methods to reach these populations. Further, 67 studies (21%) examined interaction effects primarily related to race or ethnicity (48%). Two-thirds of the studies (72%) adjusted for characteristics associated with inequities, and 18 studies (6%) used flow diagrams to depict how populations experiencing inequities progressed throughout the studies. Conclusions: Despite over 80% of the equity-focused observational studies providing a rationale for a focus on health equity, reporting of study design features relevant to health equity ranged from 0-95%, with over half of the items reported by less than one-quarter of studies. This methodological study is a baseline assessment to inform the development of an equity-focussed reporting guideline for observational studies as an extension of the well-known Strengthening Reporting of Observational Studies in Epidemiology (STROBE) guideline.

A comprehensive evaluation of large Language models on benchmark biomedical text processing tasks.

Recently, Large Language Models (LLMs) have demonstrated impressive capability to solve a wide range of tasks. However, despite their success across various tasks, no prior work has investigated their capability in the biomedical domain yet. To this end, this paper aims to evaluate the performance of LLMs on benchmark biomedical tasks. For this purpose, a comprehensive evaluation of 4 popular LLMs in 6 diverse biomedical tasks across 26 datasets has been conducted. To the best of our knowledge, this is the first work that conducts an extensive evaluation and comparison of various LLMs in the biomedical domain. Interestingly, we find based on our evaluation that in biomedical datasets that have smaller training sets, zero-shot LLMs even outperform the current state-of-the-art models when they were fine-tuned only on the training set of these datasets. This suggests that pre-training on large text corpora makes LLMs quite specialized even in the biomedical domain. We also find that not a single LLM can outperform other LLMs in all tasks, with the performance of different LLMs may vary depending on the task. While their performance is still quite poor in comparison to the biomedical models that were fine-tuned on large training sets, our findings demonstrate that LLMs have the potential to be a valuable tool for various biomedical tasks that lack large annotated data.

Motivations for investigating health inequities in observational epidemiology: a content analysis of 320 studies.

OBJECTIVES: To enhance equity in clinical and epidemiological research, it is crucial to understand researcher motivations for conducting equity-relevant studies. Therefore, we evaluated author motivations in a randomly selected sample of equity-relevant observational studies published during the COVID-19 pandemic. STUDY DESIGN AND SETTING: We searched MEDLINE for studies from 2020 to 2022, resulting in 16,828 references. We randomly selected 320 studies purposefully sampled across income setting (high vs low-middle-income), COVID-19 topic (vs non-COVID-19), and focus on populations experiencing inequities. Of those, 206 explicitly mentioned motivations which we analyzed thematically. We used discourse analysis to investigate the reasons behind emerging motivations. RESULTS: We identified the following motivations: (1) examining health disparities, (2) tackling social determinants to improve access, and (3) addressing knowledge gaps in health equity. Discourse analysis showed motivations stem from commitments to social justice and recognizing the importance of highlighting it in research. Other discourses included aspiring to improve health-care efficiency, wanting to understand cause-effect relationships, and seeking to contribute to an equitable evidence base. CONCLUSION: Understanding researchers' motivations for assessing health equity can aid in developing guidance that tailors to their needs. We will consider these motivations in developing and sharing equity guidance to better meet researchers' needs.

Digital interventions to reduce social isolation and loneliness in older adults: An evidence and gap map.

Background: Social isolation and loneliness are more common in older adults and are associated with a serious impact on their well-being, mental health, physical health, and longevity. They are a public health concern highlighted by the COVID-19 pandemic restrictions, hence the need for digital technology tools to enable remotely delivered interventions to alleviate the impact of social isolation and loneliness during the COVID-19 restrictions. Objectives: To map available evidence on the effects of digital interventions to mitigate social isolation and/or loneliness in older adults in all settings except hospital settings. Search Methods: We searched the following databases from inception to May 16, 2021, with no language restrictions. Ovid MEDLINE, Embase, APA PsycInfo via Ovid, CINAHL via EBSCO, Web of Science via Clarivate, ProQuest (all databases), International Bibliography of the Social Sciences (IBSS) via ProQuest, EBSCO (all databases except CINAHL), Global Index Medicus, and Epistemonikos. Selection Criteria: Titles and abstracts and full text of potentially eligible articles were independently screened in duplicate following the eligibility criteria. Data Collection and Analysis: We developed and pilot tested a data extraction code set in Eppi-Reviewer and data were individually extracted and coded based on an intervention-outcome framework which was also used to define the dimensions of the evidence and gap map. Main Results: We included 200 articles (103 primary studies and 97 systematic reviews) that assessed the effects of digital interventions to reduce social isolation and/or loneliness in older adults. Most of the systematic reviews (72%) were classified as critically low quality, only 2% as high quality and 25% were published since the COVID-19 pandemic. The evidence is unevenly distributed with clusters predominantly in high-income countries and none in low-income countries. The most common interventions identified are digital interventions to enhance social interactions with family and friends and the community via videoconferencing and telephone calls. Digital interventions to enhance social support, particularly socially assistive robots, and virtual pets were also common. Most interventions focused on reducing loneliness and depression and improving quality of life of older adults. Major gaps were identified in community level outcomes and process indicators. No included studies or reviews assessed affordability or digital divide although the value of accessibility and barriers caused by digital divide were discussed in three primary studies and three reviews. Adverse effects were reported in only two studies and six reviews. No study or review included participants from the LGBTQIA2S+ community and only one study restricted participants to 80 years and older. Very few described how at-risk populations were recruited or conducted any equity analysis to assess differences in effects for populations experiencing inequities across PROGRESS-Plus categories. Authors' Conclusions: The restrictions placed on people during the pandemic have shone a spotlight onto social isolation and loneliness, particularly for older adults. This evidence and gap map shows available evidence on the effectiveness of digital interventions for reducing social isolation or loneliness in older adults. Although the evidence is relatively large and recent, it is unevenly distributed and there is need for more high-quality research. This map can guide researchers and funders to consider areas of major gaps as priorities for further research.

A scoping review establishes need for consensus guidance on reporting health equity in observational studies.

OBJECTIVES: To evaluate the support from the available guidance on reporting of health equity in research for our candidate items and to identify additional items for the Strengthening Reporting of Observational studies in Epidemiology-Equity extension. STUDY DESIGN AND SETTING: We conducted a scoping review by searching Embase, MEDLINE, CINAHL, Cochrane Methodology Register, LILACS, and Caribbean Center on Health Sciences Information up to January 2022. We also searched reference lists and gray literature for additional resources. We included guidance and assessments (hereafter termed "resources") related to conduct and/or reporting for any type of health research with or about people experiencing health inequity. RESULTS: We included 34 resources, which supported one or more candidate items or contributed to new items about health equity reporting in observational research. Each candidate item was supported by a median of six (range: 1-15) resources. In addition, 12 resources suggested 13 new items, such as "report the background of investigators". CONCLUSION: Existing resources for reporting health equity in observational studies aligned with our interim checklist of candidate items. We also identified additional items that will be considered in the development of a consensus-based and evidence-based guideline for reporting health equity in observational studies.

Term dependency extraction using rule-based Bayesian Network for medical image retrieval.

Text-Based Medical Image Retrieval (TBMIR) has been known to be successful in retrieving medical images with textual descriptions. Usually, these descriptions are very brief and cannot express the whole visual content of the image in words, hence negatively affect the retrieval performance. One of the solutions offered in the literature is to form a Bayesian Network thesaurus taking advantage of some medical terms extracted from the image datasets. Despite the interestingness of this solution, it is not efficient as it is highly related to the co-occurrence measure, the layer arrangement and the arc directions. A significant drawback of the co-occurrence measure is the generation of a lot of uninteresting co-occurring terms. Several studies applied the association rules mining and its measures to discover the correlation between the terms. In this paper, we propose a new efficient association Rule Based Bayesian Network (R2BN) model for TBMIR using updated medically-dependent features (MDF) based on Unified Medical Language System (UMLS). The MDF are a set of medical terms that refers to the imaging modalities, the image color, the searched object dimension, etc. The proposed model presents the association rules mined from MDF in the form of Bayesian Network model. Then, it exploits the association rule measures (support, confidence, and lift) to prune the Bayesian Network model for efficient computation. The proposed R2BN model is combined with a literature probabilistic model to predict the relevance of an image to a given query. Experiments are carried out with ImageCLEF medical retrieval task collections from 2009 to 2013. Results show that our proposed model enhances significantly the image retrieval accuracy compared to the state-of-the-art retrieval models.

Image Translation by Ad CycleGAN for COVID-19 X-Ray Images: A New Approach for Controllable GAN.

We propose a new generative model named adaptive cycle-consistent generative adversarial network, or Ad CycleGAN to perform image translation between normal and COVID-19 positive chest X-ray images. An independent pre-trained criterion is added to the conventional Cycle GAN architecture to exert adaptive control on image translation. The performance of Ad CycleGAN is compared with the Cycle GAN without the external criterion. The quality of the synthetic images is evaluated by quantitative metrics including Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Peak Signal-to-Noise Ratio (PSNR), Universal Image Quality Index (UIQI), visual information fidelity (VIF), Frechet Inception Distance (FID), and translation accuracy. The experimental results indicate that the synthetic images generated either by the Cycle GAN or by the Ad CycleGAN have lower MSE and RMSE, and higher scores in PSNR, UIQI, and VIF in homogenous image translation (i.e., Y → Y) compared to the heterogenous image translation process (i.e., X → Y). The synthetic images by Ad CycleGAN through the heterogeneous image translation have significantly higher FID score compared to Cycle GAN (p < 0.01). The image translation accuracy of Ad CycleGAN is higher than that of Cycle GAN when normal images are converted to COVID-19 positive images (p < 0.01). Therefore, we conclude that the Ad CycleGAN with the independent criterion can improve the accuracy of GAN image translation. The new architecture has more control on image synthesis and can help address the common class imbalance issue in machine learning methods and artificial intelligence applications with medical images.

Incidence of Venous Thromboembolism in Hospitalized COVID-19 Patients Receiving Thromboprophylaxis.

Background: The purpose of this study was to investigate the association between anticoagulant dosing intensity in coronavirus disease 2019 (COVID-19) infected patients and its outcomes on venous thromboembolism (VTE) and all-cause mortality. Methods: This is a retrospective observational study that examined different anticoagulation regimens among COVID-19 patients for prophylaxis of VTE. Primary outcomes of the study were VTE incidence and all-cause mortality for patients receiving prophylaxis-intensity (PPX) and therapeutic-intensity (TX) anticoagulation. Secondary outcomes were incidence of hemorrhagic events and hospital length of stay. Patients were matched (1:1) based on age and Charlson comorbidity score. Sub-group analyses evaluated outcomes within critically ill patients, between specific anticoagulant agents and comorbid conditions. Results: The primary outcome of VTE occurred in six patients within the prophylactic dose group and eight patients in the therapeutic-intensity dose group (risk ratio (RR): 2.02 (95% confidence interval (CI): 0.7 - 5.2); P = 0.2). Bleeding occurred in 15 (11%) patients in the prophylactic group and 27 (19%) patients in the therapeutic group (RR: 0.5 (95% CI: 0.3 - 1.0); P < 0.049). Hospital length of stay was shorter by 4 days in those treated with prophylactic-intensity anticoagulation (P = 0.003). Intensive care unit admission and ventilation were negatively correlated with mortality in a multivariate analysis. Conclusions: Among hospitalized COVID-19 patients, the use of therapeutic-intensity anticoagulation did not show any benefits in reducing the occurrence of VTE. An increase in mortality and in the incidence of hemorrhagic events was statistically significant in the therapeutic-intensity group. Future prospective studies are warranted to evaluate anticoagulation therapy in COVID-19 infected patients.

CycleGAN with Dynamic Criterion for Malaria Blood Cell Image Synthetization.

We present a cycle-consistent adversarial network (Cycle GAN) with dynamic criterion to synthesize blood cells parasitized by malaria plasmodia. The result shows 100% of the synthetic images are correctly classified by the pretrained classifier compared to 99.61% of the real images, 76.6% generated by the Cycle GAN without the dynamic criterion. The average score of Frechet Inception Distance (FID) of the generated images by the enhanced Cycle GAN is 0.0043 (Std=0.0005), which is significantly lower than the FID score of the variational autoencoder (VAE) model (0.0085 (Std=0.0007)). We conclude that the new Cycle GAN model with dynamic criterion can generate high quality malaria infected blood cell images with good diversity. The new method provides new augmentation technique to enhance the image diversity where the acquisition of well-annotated images is highly restricted, and to improve the robustness of medical image automatic processing by deep neural networks.

GFCNet: Utilizing graph feature collection networks for coronavirus knowledge graph embeddings.

In response to fighting COVID-19 pandemic, researchers in machine learning and artificial intelligence have constructed some medical knowledge graphs (KG) based on existing COVID-19 datasets, however, these KGs contain a considerable amount of semantic relations which are incomplete or missing. In this paper, we focus on the task of knowledge graph embedding (KGE), which serves an important solution to infer the missing relations. In the past, there have been a collection of knowledge graph embedding models with different scoring functions to learn entity and relation embeddings published. However, these models share the same problems of rarely taking important features of KG like attribute features, other than relation triples, into account, while dealing with the heterogeneous, complex and incomplete COVID-19 medical data. To address the above issue, we propose a graph feature collection network (GFCNet) for COVID-19 KGE task, which considers both neighbor and attribute features in KGs. The extensive experiments conducted on the COVID-19 drug KG dataset show promising results and prove the effectiveness and efficiency of our proposed model. In addition, we also explain the future directions of deepening the study on COVID-19 KGE task.

A Machine Learning Approach to Predict the Outcome of Urinary Calculi Treatment Using Shock Wave Lithotripsy: Model Development and Validation Study.

BACKGROUND: Shock wave lithotripsy (SWL), ureteroscopy, and percutaneous nephrolithotomy are established treatments for renal stones. Historically, SWL has been a predominant and commonly used procedure for treating upper tract renal stones smaller than 20 mm in diameter due to its noninvasive nature. However, the reported failure rate of SWL after one treatment session ranges from 30% to 89%. The failure rate can be reduced by identifying candidates likely to benefit from SWL and manage patients who are likely to fail SWL with other treatment modalities. This would enhance and optimize treatment results for SWL candidates. OBJECTIVE: We proposed to develop a machine learning model that can predict SWL outcomes to assist practitioners in the decision-making process when considering patients for stone treatment. METHODS: A data set including 58,349 SWL procedures performed during 31,569 patient visits for SWL to a single hospital between 1990 and 2016 was used to construct and validate the predictive model. The AdaBoost algorithm was applied to a data set with 17 predictive attributes related to patient demographics and stone characteristics, with success or failure as an outcome. The AdaBoost algorithm was also applied to a training data set. The generated model's performance was compared to that of 5 other machine learning algorithms, namely C4.5 decision tree, naïve Bayes, Bayesian network, K-nearest neighbors, and multilayer perceptron. RESULTS: The developed model was validated with a testing data set and performed significantly better than the models generated by the other 5 predictive algorithms. The sensitivity and specificity of the model were 0.875 and 0.653, respectively, while its positive predictive value was 0.7159 and negative predictive value was 0.839. The C-statistics of the receiver operating characteristic (ROC) analysis was 0.843, which reflects an excellent test. CONCLUSIONS:  We have developed a rigorous machine learning model to assist physicians and decision-makers to choose patients with renal stones who are most likely to have successful SWL treatment based on their demographics and stone characteristics. The proposed machine learning model can assist physicians and decision-makers in planning for SWL treatment and allow for more effective use of limited health care resources and improve patient prognoses.

MR angiographic findings of aberrant right subclavian artery with agenesis of the left common carotid artery and anomalous origin of the vertebral arteries.

INTRODUCTION: Congenital aortic arch anomalies and variants have been extensively characterized in the medical literature. Proper identification of these anomalies is important when surgical or percutaneous interventions are indicated. CASE PRESENTATION: We present a case of a 48-year old male who presented to the emergency department with altered mental status. Magnetic resonance angiography (MRA) findings revealed an aberrant right subclavian artery (ARSA), early bifurcation of the right common carotid artery (CCA) with anomalous origin of the right vertebral artery (VA) from the right common carotid artery bifurcation, anomalous left vertebral artery originating from the aortic arch, and absent left common carotid artery with independent origins of the left external carotid artery (ECA) and internal carotid artery (ICA). No other abnormalities were identified, and the patient demonstrated no symptoms attributable to his vascular anomalies. CONCLUSION: To our knowledge, this unique combination of anomalies has never been reported in the literature. With an understanding of embryological pathways, even exceedingly rare anomalies like this one can be explained.

Basel III FRTB: data pooling innovation to lower capital charges.

BACKGROUND: Anticipated to overhaul the structure of market risk teams, IT teams, and trading desks within banks by 2023, Basel III's Fundamental Review of the Trading Book requirements will also increase capital charges banks will incur globally. The case study focuses on describing what is needed with regards to the risk factor eligibility test (RFET) as well as for implementing a data pool to lower capital charges. By establishing a consortium of banks per region to implement a data pooling solution, participants can prove a wider breadth of modellable risk factors per asset class and use the Internal Models Approach (IMA) of valuing risk to lower capital charge requirements significantly. CASE DESCRIPTION: First, a description on the historical context surrounding the Fundamental Review of the Trading Book rules and the business requirements needed to comply with the risk factor eligibility test is made. Then an examination is conducted on the innovative data pooling initiative implemented by CanDeal, TickSmith Corp., and the 6 largest Canadian banks to lower capital charge requirements under the Fundamental Review of the Trading Book. DISCUSSION AND EVALUATION: A description is made on what types of data, expertise, and technology is needed to calculate for risk factor modellability. It is up to each firm to decide if the benefits to using the Internal Models Approach to lower capital charges outweighs implementation and running costs of the underlying data platform. Implementing a data pool for each region comes with challenges that include anti-competition law that may block the initiative, varied benefits to each competitive participant, and data security concerns. CONCLUSION: It is evident that the data pool innovation provides benefits to lowering capital charges as the Canadian banks have seen an increase of modellability by several factors using the sample bond asset class. While each firm must still determine internally if the benefits outweighs the technological costs they will incur, it is clear that regulators are pushing for increased data retention and scrutiny.

Interprofessional Education on Medication Adherence: Peer-to-Peer Teaching of Osteopathic Medical Students.

CONTEXT: Medication nonadherence is an important barrier to achieving optimal clinical outcomes. Currently, there are limited data on methods used to train medical students about medication adherence. OBJECTIVE: To evaluate the knowledge, confidence, and attitudes of first-year osteopathic medical students before and after a 30-minute peer-to-peer medication adherence education program led by a third-year pharmacy student. METHODS: All first-year medical students from Touro University California College of Osteopathic Medicine were invited to participate in 1 of 3 medication adherence educational sessions held in May 2019. A third-year pharmacy student who received training from Touro University California College of Pharmacy faculty served as the peer educator. Each session took approximately 1 hour to complete. The session included a preprogram survey, a 30-minute program, and a postprogram survey. Survey items included demographics; medication adherence knowledge, confidence, and attitudes; and attitudes toward the peer-to-peer educational format. Statistical comparisons of preprogram and postprogram knowledge, confidence, and attitudes were made using a paired t test, the McNemar test, and the Wilcoxon signed-rank test. P<.05 was considered statistically significant. A sample size calculation was performed using mean knowledge scores to determine whether the study achieved 80% power. RESULTS: Twenty-three students participated in the study. Medication adherence knowledge scores improved after the program (17.4 [77.4%] vs 9.98 [92.2%]; P<.001). Confidence scores also improved for all 7 survey items (P<.001). Medical students had more positive attitudes toward medication adherence after the program, with 8 of 10 survey items in this domain showing improvement. Most students had a positive attitude toward the peer-to-peer educational format. All participants reported that they would implement the medication adherence skills learned at the program with future patients. CONCLUSION: A 30-minute peer-to-peer program led by a pharmacy student improved first-year medical students' knowledge, confidence, and attitudes with regard to medication adherence and provided an effective format to enhance interprofessional learning and collaboration.

Deep generative learning for automated EHR diagnosis of traditional Chinese medicine.

BACKGROUND: Computer-aided medical decision-making (CAMDM) is the method to utilize massive EMR data as both empirical and evidence support for the decision procedure of healthcare activities. Well-developed information infrastructure, such as hospital information systems and disease surveillance systems, provides abundant data for CAMDM. However, the complexity of EMR data with abstract medical knowledge makes the conventional model incompetent for the analysis. Thus a deep belief networks (DBN) based model is proposed to simulate the information analysis and decision-making procedure in medical practice. The purpose of this paper is to evaluate a deep learning architecture as an effective solution for CAMDM. METHODS: A two-step model is applied in our study. At the first step, an optimized seven-layer deep belief network (DBN) is applied as an unsupervised learning algorithm to perform model training to acquire feature representation. Then a support vector machine model is adopted to DBN at the second step of the supervised learning. There are two data sets used in the experiments. One is a plain text data set indexed by medical experts. The other is a structured dataset on primary hypertension. The data are randomly divided to generate the training set for the unsupervised learning and the testing set for the supervised learning. The model performance is evaluated by the statistics of mean and variance, the average precision and coverage on the data sets. Two conventional shallow models (support vector machine / SVM and decision tree / DT) are applied as the comparisons to show the superiority of our proposed approach. RESULTS: The deep learning (DBN + SVM) model outperforms simple SVM and DT on two data sets in terms of all the evaluation measures, which confirms our motivation that the deep model is good at capturing the key features with less dependence when the index is built up by manpower. CONCLUSIONS: Our study shows the two-step deep learning model achieves high performance for medical information retrieval over the conventional shallow models. It is able to capture the features of both plain text and the highly-structured database of EMR data. The performance of the deep model is superior to the conventional shallow learning models such as SVM and DT. It is an appropriate knowledge-learning model for information retrieval of EMR system. Therefore, deep learning provides a good solution to improve the performance of CAMDM systems.

Detection of subthreshold atrophy in crossed cerebellar degeneration via two-compartment mathematical modeling of cell density in DWI: A proof of concept study.

Crossed cerebellar diaschisis (CCD) refers to transneuronal degeneration of the corticopontocerebellar pathway, resulting in atrophy of cerebellum contralateral to supratentorial pathology. CCD is traditionally diagnosed on nuclear medicine studies. Our aim is to apply a biexponential diffusion model, composed of intracellular and extracellular compartments, to the detection of subthreshold CCD on DWI, with the calculated fraction of the intracellular compartment as a proposed measure of cell density. At a voxel-by-voxel basis, we solve for intracellular and extracellular coefficients in each side of the cerebellum and compare the distribution of coefficients between each hemisphere. We demonstrate, in all six CCD cases, a significantly lower contribution of the intracellular compartment to the cerebellar hemisphere contralateral to supratentorial pathology (p < 0.01). In a separate, proof-of-concept case of pontine stroke, we also demonstrate reduced intracellular coefficients in bilateral cerebellar hemispheres, excluding middle cerebellar peduncles (p < 0.01). Our findings are consistent with a decreased intracellular fraction, presumably a surrogate for reduced cellular density in corticopontocerebellar degeneration, despite normal-appearing scans. Our approach allows detection of subthreshold structural changes and offers the additional advantage of applicability to most clinical cases, where only three DWI beta values are available.

Fast Screening Technology for Drug Emergency Management: Predicting Suspicious SNPs for ADR with Information Theory-based Models.

OBJECTIVE: The genetic polymorphism of Cytochrome P450 (CYP 450) is considered as one of the main causes for adverse drug reactions (ADRs). In order to explore the latent correlations between ADRs and potentially corresponding single-nucleotide polymorphism (SNPs) in CYP450, three algorithms based on information theory are used as the main method to predict the possible relation. METHODS: The study uses a retrospective case-control study to explore the potential relation of ADRs to specific genomic locations and single-nucleotide polymorphism (SNP). The genomic data collected from 53 healthy volunteers are applied for the analysis, another group of genomic data collected from 30 healthy volunteers excluded from the study are used as the control group. The SNPs respective on five loci of CYP2D6*2,*10,*14 and CYP1A2*1C, *1F are detected by the Applied Biosystem 3130xl. The raw data is processed by ChromasPro to detect the specific alleles on the above loci from each sample. The secondary data are reorganized and processed by R combined with the reports of ADRs from clinical reports. Three information theory based algorithms are implemented for the screening task: JMI, CMIM, and mRMR. If a SNP is selected by more than two algorithms, we are confident to conclude that it is related to the corresponding ADR. The selection results are compared with the control decision tree + LASSO regression model. RESULTS: In the study group where ADRs occur, 10 SNPs are considered relevant to the occurrence of a specific ADR by the combined information theory model. In comparison, only 5 SNPs are considered relevant to a specific ADR by the decision tree + LASSO regression model. In addition, the new method detects more relevant pairs of SNP and ADR which are affected by both SNP and dosage. This implies that the new information theory based model is effective to discover correlations of ADRs and CYP 450 SNPs and is helpful in predicting the potential vulnerable genotype for some ADRs. CONCLUSION: The newly proposed information theory based model has superiority performance in detecting the relation between SNP and ADR compared to the decision tree + LASSO regression model. The new model is more sensitive to detect ADRs compared to the old method, while the old method is more reliable. Therefore, the selection criteria for selecting algorithms should depend on the pragmatic needs.

DL-ADR: a novel deep learning model for classifying genomic variants into adverse drug reactions.

BACKGROUND: Genomic variations are associated with the metabolism and the occurrence of adverse reactions of many therapeutic agents. The polymorphisms on over 2000 locations of cytochrome P450 enzymes (CYP) due to many factors such as ethnicity, mutations, and inheritance attribute to the diversity of response and side effects of various drugs. The associations of the single nucleotide polymorphisms (SNPs), the internal pharmacokinetic patterns and the vulnerability of specific adverse reactions become one of the research interests of pharmacogenomics. The conventional genomewide association studies (GWAS) mainly focuses on the relation of single or multiple SNPs to a specific risk factors which are a one-to-many relation. However, there are no robust methods to establish a many-to-many network which can combine the direct and indirect associations between multiple SNPs and a serial of events (e.g. adverse reactions, metabolic patterns, prognostic factors etc.). In this paper, we present a novel deep learning model based on generative stochastic networks and hidden Markov chain to classify the observed samples with SNPs on five loci of two genes (CYP2D6 and CYP1A2) respectively to the vulnerable population of 14 types of adverse reactions. METHODS: A supervised deep learning model is proposed in this study. The revised generative stochastic networks (GSN) model with transited by the hidden Markov chain is used. The data of the training set are collected from clinical observation. The training set is composed of 83 observations of blood samples with the genotypes respectively on CYP2D6*2, *10, *14 and CYP1A2*1C, *1 F. The samples are genotyped by the polymerase chain reaction (PCR) method. A hidden Markov chain is used as the transition operator to simulate the probabilistic distribution. The model can perform learning at lower cost compared to the conventional maximal likelihood method because the transition distribution is conditional on the previous state of the hidden Markov chain. A least square loss (LASSO) algorithm and a k-Nearest Neighbors (kNN) algorithm are used as the baselines for comparison and to evaluate the performance of our proposed deep learning model. RESULTS: There are 53 adverse reactions reported during the observation. They are assigned to 14 categories. In the comparison of classification accuracy, the deep learning model shows superiority over the LASSO and kNN model with a rate over 80 %. In the comparison of reliability, the deep learning model shows the best stability among the three models. CONCLUSIONS: Machine learning provides a new method to explore the complex associations among genomic variations and multiple events in pharmacogenomics studies. The new deep learning algorithm is capable of classifying various SNPs to the corresponding adverse reactions. We expect that as more genomic variations are added as features and more observations are made, the deep learning model can improve its performance and can act as a black-box but reliable verifier for other GWAS studies.

Automatic Classification of Ultrasound Screening Examinations of the Abdominal Aorta.

Our work facilitates the identification of veterans who may be at risk for abdominal aortic aneurysms (AAA) based on the 2007 mandate to screen all veteran patients that meet the screening criteria. The main research objective is to automatically index three clinical conditions: pertinent negative AAA, pertinent positive AAA, and visually unacceptable image exams. We developed and evaluated a ConText-based algorithm with the GATE (General Architecture for Text Engineering) development system to automatically classify 1402 ultrasound radiology reports for AAA screening. Using the results from JAPE (Java Annotation Pattern Engine) transducer rules, we developed a feature vector to classify the radiology reports with a decision table classifier. We found that ConText performed optimally on precision and recall for pertinent negative (0.99 (0.98-0.99), 0.99 (0.99-1.00)) and pertinent positive AAA detection (0.98 (0.95-1.00), 0.97 (0.92-1.00)), and respectably for determination of non-diagnostic image studies (0.85 (0.77-0.91), 0.96 (0.91-0.99)). In addition, our algorithm can determine the AAA size measurements for further characterization of abnormality. We developed and evaluated a regular expression based algorithm using GATE for determining the three contextual conditions: pertinent negative, pertinent positive, and non-diagnostic from radiology reports obtained for evaluating the presence or absence of abdominal aortic aneurysm. ConText performed very well at identifying the contextual features. Our study also discovered contextual trigger terms to detect sub-standard ultrasound image quality. Limitations of performance included unknown dictionary terms, complex sentences, and vague findings that were difficult to classify and properly code.

White matter changes in chronic alcoholic liver disease: Hypothesized association and putative biochemical mechanisms.

Advanced liver disease has long been associated with cerebral abnormalities. These abnormalities, termed acquired hepatocerebral degeneration, are typically visualized as T1 weighted hyperintensity on MRI in the deep gray matter of the basal ganglia. Recent reports, however, have demonstrated that a subset of patients with chronic alcoholic liver disease may also develop white matter abnormalities. Thus far, the morphology of these changes is not well characterized. Previous studies have described these changes as patchy, sporadic white matter abnormalities but have not posited localization of these changes to any particular white matter tracts. This paper hypothesizes that the white matter findings associated with advanced alcoholic liver disease localize to the corticocerebellar tracts. As an initial investigation of this hypothesis, 78 patients with a diagnosis of liver cirrhosis and an MRI showing clearly abnormal T1 weighted hyperintensity in the bilateral globus pallidus, characteristic of chronic liver disease, were examined for white matter signal abnormalities in the corticocerebellar tracts using FLAIR and T2 weighted images. The corticocerebellar tracts were subdivided into two regions: periventricular white matter (consisting of the sum of the centrum-semiovale and corona radiata), and lower white matter (consisting of the corona radiata, internal capsules, middle cerebral peduncles, middle cerebellar peduncles and cerebellum). As compared to matched controls, significantly greater signal abnormalities in both the periventricular white matter and lower white matter regions of the corticocerebellar tracts were observed in patients with known liver cirrhosis and abnormal T1 W hyperintensity in the globi pallidi. This difference was most pronounced in the lower white matter region of the corticocerebellar tract, with statistical significance of p<0.0005. Furthermore, the pathophysiologic mechanism underlying these changes remains unknown. This paper hypothesizes that the etiology of white matter changes associated with advanced liver disease may resemble that of white matter findings in subacute combined degeneration secondary to vitamin B12 deficiency. Specifically, significant evidence suggests that dysfunctional methionine metabolism as well as dysregulated cytokine production secondary to B12 deficiency play a major role in the development of subacute combined degeneration. Similar dysfunction of methionine metabolism and cytokine regulation is seen in alcoholic liver disease and is hypothesized in this paper to, at least in part, lead to white matter findings associated with alcoholic liver disease.