Synthetic Clinical Trial Dataset – Hypertension Drug Trial (CardioX vs. Active Comparator vs. Placebo)

📝 About This Dataset

This synthetic dataset simulates a Phase III randomized controlled clinical trial evaluating CardioX (Drug A) versus an active comparator (Drug B) and a placebo for treating hypertension. It is designed for clinical data analysis, anomaly detection, and risk-based monitoring (RBM) applications.

The dataset includes 1,000 patients across 50 trial sites, with realistic patient demographics, blood pressure readings, cholesterol levels, dropout rates, and adverse event reporting. Several anomalies have been embedded to simulate real-world data quality issues commonly encountered in clinical trials.

This dataset is ideal for data quality assessments, statistical anomaly detection (Z-scores, IQR, clustering), and risk-based management (RBM) in clinical research.

🚀 Potential Use Cases

🔹 Clinical Trial Data Analysis – Investigate treatment efficacy and safety trends.

🔹 Anomaly Detection – Apply Z-scores, IQR, and ML-based clustering methods to identify outliers.

🔹 Risk-Based Monitoring (RBM) – Detect potential site-level risks and data inconsistencies.

🔹 Machine Learning Applications – Train models for adverse event prediction or dropout risk estimation.

📊 Dataset Features

📢 Acknowledgment & Licensing

This dataset is fully synthetic and does not contain real patient data. It is created for educational, analytical, and research purposes in clinical data science and biostatistics.

🔗 If you use this dataset, tag me! Let’s discuss insights & findings! 🚀

Code of simulation algorithm and graphics plot in R. (DOCX)

182 simulated datasets (first set contains small datasets and second set contains large datasets) with different cluster compositions – i.e., different number clusters and separation values – generated using clusterGeneration package in R. Each set of simulation datasets consists of 91 datasets in comma separated values (csv) format (total of 182 csv files) with 3-15 clusters and 0.1 to 0.7 separation values. Separation values can range between (−0.999, 0.999), where a higher separation value indicates cluster structure with more separable clusters.

Size of the dataset, number of clusters, and separation value of the clusters in the dataset is printed in file name. size_X_n_Y_sepval_Z.csv: Size of the dataset = X number of clusters in the dataset = Y separation value of the clusters in the dataset = Z

This archive contains the summarization corpus generated as a result of the filtering stages (trials-final.csv), the rouge scores for the generated summaries (rouge-results-parsed.csv), the data and results of the human evaluation (evaluation/ subfolder), the code used to generate the corpus (extract.r, filter.r, and determine_similarity_threshold.r). The summaries were generated using the summarize_all.py script.

This repository stores synthetic datasets derived from the database of the UK Biobank (UKB) cohort.

The datasets were generated for illustrative purposes, in particular for reproducing specific analyses on the health risks associated with long-term exposure to air pollution using the UKB cohort. The code used to create the synthetic datasets is available and documented in a related GitHub repo, with details provided in the section below. These datasets can be freely used for code testing and for illustrating other examples of analyses on the UKB cohort.

Note: while the synthetic versions of the datasets resemble the real ones in several aspects, the users should be aware that these data are fake and must not be used for testing and making inferences on specific research hypotheses. Even more importantly, these data cannot be considered a reliable description of the original UKB data, and they must not be presented as such.

The original datasets are described in the article by Vanoli et al in Epidemiology (2024) (DOI: 10.1097/EDE.0000000000001796) [freely available here], which also provides information about the data sources.

The work was supported by the Medical Research Council-UK (Grant ID: MR/Y003330/1).

Content

The series of synthetic datasets (stored in two versions with csv and RDS formats) are the following:

• synthbdcohortinfo: basic cohort information regarding the follow-up period and birth/death dates for 502,360 participants.
• synthbdbasevar: baseline variables, mostly collected at recruitment.
• synthpmdata: annual average exposure to PM_2.5 for each participant reconstructed using their residential history.
• synthoutdeath: death records that occurred during the follow-up with date and ICD-10 code.

In addition, this repository provides these additional files:

• codebook: a pdf file with a codebook for the variables of the various datasets, including references to the fields of the original UKB database.
• asscentre: a csv file with information on the assessment centres used for recruitment of the UKB participants, including code, names, and location (as northing/easting coordinates of the British National Grid).
• Countries_December_2022_GB_BUC: a zip file including the shapefile defining the boundaries of the countries in Great Britain (England, Wales, and Scotland), used for mapping purposes [source].

Generation of the synthetic data

The datasets resemble the real data used in the analysis, and they were generated using the R package synthpop (www.synthpop.org.uk). The generation process involves two steps, namely the synthesis of the main data (cohort info, baseline variables, annual PM_2.5 exposure) and then the sampling of death events. The R scripts for performing the data synthesis are provided in the GitHub repo (subfolder Rcode/synthcode).

The first part merges all the data including the annual PM_2.5 levels in a single wide-format dataset (with a row for each subject), generates a synthetic version, adds fake IDs, and then extracts (and reshapes) the single datasets. In the second part, a Cox proportional hazard model is fitted on the original data to estimate risks associated with various predictors (including the main exposure represented by PM_2.5), and then these relationships are used to simulate death events in each year. Details on the modelling aspects are provided in the article.

This process guarantees that the synthetic data do not hold specific information about the original records, thus preserving confidentiality. At the same time, the multivariate distribution and correlation across variables as well as the mortality risks resemble those of the original data, so the results of descriptive and inferential analyses are similar to those in the original assessments. However, as noted above, the data are used only for illustrative purposes, and they must not be used to test other research hypotheses.

The goal of this research project was to develop an efficient mental health screen that would aid in the early identification of severe mental illnesses and other acute psychiatric problems during the jail intake process. The researchers sought to validate the Brief Jail Mental Health Screen (BJMHS) as such a tool. Participants in the study included male and female jail detainees admitted to one of four county jails, two in Maryland and two in New York, from November 2005 to June 2006. A total of 10,562 jail detainees were screened using the BJMHS-R (Part 1). The screening data were used to identify a sub-sample of detainees who were systematically sampled for a detailed clinical assessment, the Structured Clinical Interview for DSM-IV (SCID), which was conducted by a trained research interviewer in order to validate the screen. A subset of 464 jail detainees completed the SCID interviews (Part 2). Part 1, Tracking Data, contains 54 variables, including items and scores from the BJMHS-R, that were used to used to identify and generate a list of potential detainee participants for the SCID interview. Part 2, Interview Data, contains 326 variables, including items and scores from both the BJMHS-R and the SCID interviews, that were used to validate the screen.

Image quality assessment (IQA) is extremely important in computed tomography (CT) imaging, since it facilitates the optimization of radiation dose and the development of novel algorithms in medical imaging, such as restoration. In addition, since an excessive dose of radiation can cause harmful effects in patients, generating high- quality images from low-dose images is a popular topic in the medical domain. However, even though peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) are the most widely used evaluation metrics for these algorithms, their correlation with radiologists’ opinion of the image quality has been proven to be insufficient in previous studies, since they calculate the image score based on numeric pixel values (1-3). In addition, the need for pristine reference images to calculate these metrics makes them ineffective in real clinical environments, considering that pristine, high-quality images are often impossible to obtain due to the risk posed to patients as a result of radiation dosage. To overcome these limitations, several studies have aimed to develop a no-reference novel image quality metric that correlates well with radiologists’ opinion on image quality without any reference images (2, 4, 5).

Nevertheless, due to the lack of open-source datasets specifically for CT IQA, experiments have been conducted with datasets that differ from each other, rendering their results incomparable and introducing difficulties in determining a standard image quality metric for CT imaging. Besides, unlike real low-dose CT images with quality degradation due to various combinations of artifacts, most studies are conducted with only one type of artifact (e.g., low-dose noise (6-11), view aliasing (12), metal artifacts (13), scattering (14-16), motion artifacts (17-22), etc.). Therefore, this challenge aims to 1) evaluate various NR-IQA models on CT images containing complex noise/artifacts, 2) to compare their correlations with scores produced by radiologists, and 3) to grant insights into the determination of the best-performing metric of CT imaging in terms of correlating with the perception of radiologists’.

Furthermore, considering that low-dose CT images are achieved by reducing the number of projections per rotation and by reducing the X-ray current, the combination of two major artifacts, namely the sparse view streak and noise generated by these methods, is dealt with in this challenge so that the best-performing IQA model applicable in real clinical environments can be verified.

Funding Declaration:

This research was partly supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No.RS-2022-00155966, Artificial Intelligence Convergence Innovation Human Resources Development (Ewha Womans University)), and by the National Research Foundation of Korea (NRF-2022R1A2C1092072), and by the Korea Medical Device Development Fund grant funded by the Korea government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: 1711174276, RS-2020-KD000016).

References:

Lee W, Cho E, Kim W, Choi J-H. Performance evaluation of image quality metrics for perceptual assessment of low-dose computed tomography images. Medical Imaging 2022: Image Perception, Observer Performance, and Technology Assessment: SPIE, 2022.

Lee W, Cho E, Kim W, Choi H, Beck KS, Yoon HJ, Baek J, Choi J-H. No-reference perceptual CT image quality assessment based on a self-supervised learning framework. Machine Learning: Science and Technology 2022.

Choi D, Kim W, Lee J, Han M, Baek J, Choi J-H. Integration of 2D iteration and a 3D CNN-based model for multi-type artifact suppression in C-arm cone-beam CT. Machine Vision and Applications 2021;32(116):1-14.

Pal D, Patel B, Wang A. SSIQA: Multi-task learning for non-reference CT image quality assessment with self-supervised noise level prediction. 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI): IEEE, 2021; p. 1962-1965.

Mittal A, Moorthy AK, Bovik AC. No-reference image quality assessment in the spatial domain. IEEE Trans Image Process 2012;21(12):4695-4708. doi: 10.1109/TIP.2012.2214050

Lee J-YK, Wonjin; Lee, Yebin; Lee, Ji-Yeon; Ko, Eunji; Choi, Jang-Hwan. Unsupervised Domain Adaptation for Low-dose Computed Tomography Denoising. IEEE Access 2022.

Jeon S-Y, Kim W, Choi J-H. MM-Net: Multi-frame and Multi-mask-based Unsupervised Deep Denoising for Low-dose Computed Tomography. IEEE Transactions on Radiation and Plasma Medical Sciences 2022.

Kim W, Lee J, Kang M, Kim JS, Choi J-H. Wavelet subband-specific learning for low-dose computed tomography denoising. PloS one 2022;17(9):e0274308.

Han M, Shim H, Baek J. Low-dose CT denoising via convolutional neural network with an observer loss function. Med Phys 2021;48(10):5727-5742. doi: 10.1002/mp.15161

Kim B, Shim H, Baek J. Weakly-supervised progressive denoising with unpaired CT images. Med Image Anal 2021;71:102065. doi: 10.1016/j.media.2021.102065

Wagner F, Thies M, Gu M, Huang Y, Pechmann S, Patwari M, Ploner S, Aust O, Uderhardt S, Schett G, Christiansen S, Maier A. Ultralow-parameter denoising: Trainable bilateral filter layers in computed tomography. Med Phys 2022;49(8):5107-5120. doi: 10.1002/mp.15718

Kim B, Shim H, Baek J. A streak artifact reduction algorithm in sparse-view CT using a self-supervised neural representation. Med Phys 2022. doi: 10.1002/mp.15885

Kim S, Ahn J, Kim B, Kim C, Baek J. Convolutional neural network-based metal and streak artifacts reduction in dental CT images with sparse-view sampling scheme. Med Phys 2022;49(9):6253-6277. doi: 10.1002/mp.15884

Bier B, Berger M, Maier A, Kachelrieß M, Ritschl L, Müller K, Choi JH, Fahrig R. Scatter correction using a primary modulator on a clinical angiography Carm CT system. Med Phys 2017;44(9):e125-e137.

Maul N, Roser P, Birkhold A, Kowarschik M, Zhong X, Strobel N, Maier A. Learning-based occupational x-ray scatter estimation. Phys Med Biol 2022;67(7). doi: 10.1088/1361-6560/ac58dc

Roser P, Birkhold A, Preuhs A, Syben C, Felsner L, Hoppe E, Strobel N, Kowarschik M, Fahrig R, Maier A. X-Ray Scatter Estimation Using Deep Splines. IEEE Trans Med Imaging 2021;40(9):2272-2283. doi: 10.1109/TMI.2021.3074712

Maier J, Nitschke M, Choi JH, Gold G, Fahrig R, Eskofier BM, Maier A. Rigid and Non-Rigid Motion Compensation in Weight-Bearing CBCT of the Knee Using Simulated Inertial Measurements. IEEE Trans Biomed Eng 2022;69(5):1608-1619. doi: 10.1109/TBME.2021.3123673

Choi JH, Maier A, Keil A, Pal S, McWalter EJ, Beaupré GS, Gold GE, Fahrig R. Fiducial markerbased correction for involuntary motion in weightbearing Carm CT scanning of knees. II. Experiment. Med Phys 2014;41(6Part1):061902.

Choi JH, Fahrig R, Keil A, Besier TF, Pal S, McWalter EJ, Beaupré GS, Maier A. Fiducial markerbased correction for involuntary motion in weightbearing Carm CT scanning of knees. Part I. Numerical modelbased optimization. Med Phys 2013;40(9):091905.

Berger M, Muller K, Aichert A, Unberath M, Thies J, Choi JH, Fahrig R, Maier A. Marker-free motion correction in weight-bearing cone-beam CT of the knee joint. Med Phys 2016;43(3):1235-1248. doi: 10.1118/1.4941012

Ko Y, Moon S, Baek J, Shim H. Rigid and non-rigid motion artifact reduction in X-ray CT using attention module. Med Image Anal 2021;67:101883. doi: 10.1016/j.media.2020.101883

Preuhs A, Manhart M, Roser P, Hoppe E, Huang Y, Psychogios M, Kowarschik M, Maier A. Appearance Learning for Image-Based Motion Estimation in Tomography. IEEE Trans Med Imaging 2020;39(11):3667-3678. doi: 10.1109/TMI.2020.3002695

Additional file 2 Analytical vs. simulated operating characteristics comparison. R code to replicate our comparison of the analytical operating characteristics returned by the web application against those based on simulation.

DESCRIPTIONThis repository contains analysis scripts (with outputs), figures from the manuscript, and supplementary files the HIV Pain (HIP) Intervention Study. All analysis scripts (and their outputs -- /outputs subdirectory) are found in HIP-study.zip, while PDF copies of the analysis outputs that are cited in the manuscript as supplementary material are found in the relevant supplement-*.pdf file.Note: Participant consent did not provide for the publication of their data, and hence neither the original nor cleaned data have been made available. However, we do not wish to bar access to the data unnecessarily and we will judge requests to access the data on a case-by-case basis. Examples of potential use cases include independent assessments of our analyses, and secondary data analyses. Please contact Peter Kamerman (peter.kamerman@gmail.com), Dr Tory Madden (torymadden@gmail.com, or open an issue on the GitHub repo (https://github.com/kamermanpr/HIP-study/issues).BIBLIOGRAPHIC INFORMATIONRepository citationKamerman PR, Madden VJ, Parker R, Devan D, Cameron S, Jackson K, Reardon C, Wadley A. Analysis scripts and supplementary files: Barriers to implementing clinical trials on non-pharmacological treatments in developing countries – lessons learnt from addressing pain in HIV. DOI: 10.6084/m9.figshare.7654637.Manuscript citationParker R, Madden VJ, Devan D, Cameron S, Jackson K, Kamerman P, Reardon C, Wadley A. Barriers to implementing clinical trials on non-pharmacological treatments in developing countries – lessons learnt from addressing pain in HIV. Pain Reports [submitted 2019-01-31]Manuscript abstractintroduction: Pain affects over half of people living with HIV/AIDS (LWHA) and pharmacological treatment has limited efficacy. Preliminary evidence supports non-pharmacological interventions. We previously piloted a multimodal intervention in amaXhosa women LWHA and chronic pain in South Africa with improvements seen in all outcomes, in both intervention and control groups. Methods: A multicentre, single-blind randomised controlled trial with 160 participants recruited was conducted to determine whether the multimodal peer-led intervention reduced pain in different populations of both male and female South Africans LWHA. Participants were followed up at Weeks 4, 8, 12, 24 and 48 to evaluate effects on the primary outcome of pain, and on depression, self-efficacy and health-related quality of life. Results: We were unable to assess the efficacy of the intervention due to a 58% loss to follow up (LTFU). Secondary analysis of the LTFU found that sociocultural factors were not predictive of LTFU. Depression, however, did associate with LTFU, with greater severity of depressive symptoms predicting LTFU at week 8 (p=0.01). Discussion: We were unable to evaluate the effectiveness of the intervention due to the high LTFU and the risk of retention bias. The different sociocultural context in South Africa may warrant a different approach to interventions for pain in HIV compared to resource-rich countries, including a concurrent strategy to address barriers to health care service delivery. We suggest that assessment of pain and depression need to occur simultaneously in those with pain in HIV. We suggest investigation of the effect of social inclusion on pain and depression. USING DOCKER TO RUN THE HIP-STUDY ANALYSIS SCRIPTSThese instructions are for running the analysis on your local machine.You need to have Docker installed on your computer. To do so, go to docker.com (https://www.docker.com/community-edition#/download) and follow the instructions for downloading and installing Docker for your operating system. Once Docker has been installed, follow the steps below, noting that Docker commands are entered in a terminal window (Linux and OSX/macOS) or command prompt window (Windows). Windows users also may wish to install GNU Make (http://gnuwin32.sourceforge.net/downlinks/make.php) (required for the make method of running the scripts) and Git (https://gitforwindows.org/) version control software (not essential).Download the latest imageEnter: docker pull kamermanpr/docker-hip-study:v2.0.0Run the containerEnter: docker run -d -p 8787:8787 -v :/home/rstudio --name threshold -e USER=hip -e PASSWORD=study kamermanpr/docker-hip-study:v2.0.0Where refers to the path to the HIP-study directory on your computer, which you either cloned from GitHub (https://github.com/kamermanpr/HIP-study.git), git clone https://github.com/kamermanpr/HIP-study, or downloaded and extracted from figshare (https://doi.org/10.6084/m9.figshare.7654637).Login to RStudio Server- Open a web browser window and navigate to: localhost:8787- Use the following login credentials: - Username: hip - Password: study Prepare the HIP-study directoryThe HIP-study directory comes with the outputs for all the analysis scripts in the /outputs directory (html and md formats). However, should you wish to run the scripts yourself, there are several preparatory steps that are required:1. Acquire the data. The data required to run the scripts have not been included in the repo because participants in the studies did not consent to public release of their data. However, the data are available on request from Peter Kamerman (peter.kamerman@gmail.com). Once the data have been obtained, the files should be copied into a subdirectory named /data-original.2. Clean the /outputs directory by entering make clean in the Terminal tab in RStudio.Run the HIP-study analysis scriptsTo run all the scripts (including the data cleaning scripts), enter make all in the Terminal tab in RStudio.To run individual RMarkdown scripts (*.Rmd files)1. Generate the cleaned data using one of the following methods: - Enter make data-cleaned/demographics.rds in the Terminal tab in RStudio. - Enter source('clean-data-script.R') in the Console tab in RStudio. - Open the clean-data-script.R script through the File tab in RStudio, and then click the 'Source' button on the right of the Script console in RStudio for each script. 2. Run the individual script by: - Entering make outputs/.html in the Terminal tab in RStudio, OR - Opening the relevant *.Rmd file through the File tab in RStudio, and then clicking the 'knit' button on the left of the Script console in RStudio. Shutting downOnce done, log out of RStudio Server and enter the following into a terminal to stop the Docker container: docker stop hip. If you then want to remove the container, enter: docker rm threshold. If you also want to remove the Docker image you downloaded, enter: docker rmi kamermanpr/docker-hip-study:v2.0.0

BackgroundChatGPT-4 is a large language model with promising healthcare applications. However, its ability to analyze complex clinical data and provide consistent results is poorly known. Compared to validated tools, this study evaluated ChatGPT-4’s risk stratification of simulated patients with acute nontraumatic chest pain.MethodsThree datasets of simulated case studies were created: one based on the TIMI score variables, another on HEART score variables, and a third comprising 44 randomized variables related to non-traumatic chest pain presentations. ChatGPT-4 independently scored each dataset five times. Its risk scores were compared to calculated TIMI and HEART scores. A model trained on 44 clinical variables was evaluated for consistency.ResultsChatGPT-4 showed a high correlation with TIMI and HEART scores (r = 0.898 and 0.928, respectively), but the distribution of individual risk assessments was broad. ChatGPT-4 gave a different risk 45–48% of the time for a fixed TIMI or HEART score. On the 44-variable model, a majority of the five ChatGPT-4 models agreed on a diagnosis category only 56% of the time, and risk scores were poorly correlated (r = 0.605).ConclusionWhile ChatGPT-4 correlates closely with established risk stratification tools regarding mean scores, its inconsistency when presented with identical patient data on separate occasions raises concerns about its reliability. The findings suggest that while large language models like ChatGPT-4 hold promise for healthcare applications, further refinement and customization are necessary, particularly in the clinical risk assessment of atraumatic chest pain patients.

The ongoing Antibody Mediated Prevention (AMP) trials will uncover whether passive infusion of the broadly neutralizing antibody (bNAb) VRC01 can protect against HIV acquisition. Previous statistical simulations indicate these trials may be partially protective. In that case, it will be crucial to identify the mechanism of breakthrough infections. To that end, we developed a mathematical modeling framework to simulate the AMP trials and infer the breakthrough mechanisms using measurable trial outcomes. This framework combines viral dynamics with antibody pharmacokinetics and pharmacodynamics, and will be generally applicable to forthcoming bNAb prevention trials. We fit our model to human viral load data (RV217). Then, we incorporated VRC01 neutralization using serum pharmacokinetics (HVTN 104) and in vitro pharmacodynamics (LANL CATNAP database). We systematically explored trial outcomes by reducing in vivo potency and varying the distribution of sensitivity to VRC01 in circulating strains. We found trial outcomes could be used in a clinical trial regression model (CTRM) to reveal whether partially protective trials were caused by large fractions of VRC01-resistant (IC50>50 μg/mL) circulating strains or rather a global reduction in VRC01 potency against all strains. The former mechanism suggests the need to enhance neutralizing antibody breadth; the latter suggests the need to enhance VRC01 delivery and/or in vivo binding. We will apply the clinical trial regression model to data from the completed trials to help optimize future approaches for passive delivery of anti-HIV neutralizing antibodies.

BackgroundWith the increasing availability and use of digital tools such as virtual reality in medical education, there is a need to evaluate their impact on clinical performance and decision-making among healthcare professionals. The Trauma SimVR study is investigating the efficacy of virtual reality training in the context of traumatic in-hospital cardiac arrest.Methods and analysisThis study protocol (clinicaltrials.gov identifier: NCT06445764) for a single-center, prospective, randomized, controlled trial focuses on first-year residents in anesthesiology/intensive care, traumatology, and emergency medicine. The study will compare the clinical performance in a simulated scenario between participants who received virtual reality training and those who received traditional e-learning courses for preparation. The primary endpoint is the time to a predefined intervention to treat the underlying cause of the simulated traumatic cardiac arrest. Secondary endpoints include protocol deviations, cognitive load during simulated scenarios, and the influence of gender and personality characteristics on learning outcomes. The e-learning and the virtual reality training content will be developed in collaboration with experts from various medical specialties and nursing, focusing on procedural processes, guideline adherence specific to trauma patient care, and traumatic in-hospital cardiac arrest.ResultsThe results of this study will provide valuable insights into the efficacy of virtual reality training, contributing to the advancement of medical education, and serve as a foundation for future research in this rapidly evolving field.

Prior work applied hierarchical clustering, coarsened exact matching (CEM), time series regressions with lagged variables as inputs, and microsimulation to data from three randomized clinical trials (RCTs) and a large German observational study (OS) to predict pregabalin pain reduction outcomes for patients with painful diabetic peripheral neuropathy. Here, data were added from six RCTs to reduce covariate bias of the same OS and improve accuracy and/or increase the variety of patients for pain response prediction. Using hierarchical cluster analysis and CEM, a matched dataset was created from the OS (N = 2642) and nine total RCTs (N = 1320). Using a maximum likelihood method, we estimated weekly pain scores for pregabalin-treated patients for each cluster (matched dataset); the models were validated with RCT data that did not match with OS data. We predicted novel ‘virtual’ patient pain scores over time using simulations including instance-based machine learning techniques to assign novel patients to a cluster, then applying cluster-specific regressions to predict pain response trajectories. Six clusters were identified according to baseline variables (gender, age, insulin use, body mass index, depression history, pregabalin monotherapy, prior gabapentin, pain score, and pain-related sleep interference score). CEM yielded 1766 patients (matched dataset) having lower covariate imbalances. Regression models for pain performed well (adjusted R-squared 0.90–0.93; root mean square errors 0.41–0.48). Simulations showed positive predictive values for achieving >50% and >30% change-from-baseline pain score improvements (range 68.6–83.8% and 86.5–93.9%, respectively). Using more RCTs (nine vs. the earlier three) enabled matching of 46.7% more patients in the OS dataset, with substantially reduced global imbalance vs. not matching. This larger RCT pool covered 66.8% of possible patient characteristic combinations (vs. 25.0% with three original RCTs) and made prediction possible for a broader spectrum of patients.Trial Registration: www.clinicaltrials.gov (as applicable): NCT00156078, NCT00159679, NCT00143156, NCT00553475.

ProblemLow-quality fundus images with complex degredation can cause costly re-examinations of patients or inaccurate clinical diagnosis.AimThis study aims to create an automatic fundus macular image enhancement framework to improve low-quality fundus images and remove complex image degradation.MethodWe propose a new deep learning-based model that automatically enhances low-quality retinal fundus images that suffer from complex degradation. We collected a dataset, comprising 1068 pairs of high-quality (HQ) and low-quality (LQ) fundus images from the Kangbuk Samsung Hospital’s health screening program and ophthalmology department from 2017 to 2019. Then, we used these dataset to develop data augmentation methods to simulate major aspects of retinal image degradation and to propose a customized convolutional neural network (CNN) architecture to enhance LQ images, depending on the nature of the degradation. Peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), r-value (linear index of fuzziness), and proportion of ungradable fundus photographs before and after the enhancement process are calculated to assess the performance of proposed model. A comparative evaluation is conducted on an external database and four different open-source databases.ResultsThe results of the evaluation on the external test dataset showed an significant increase in PSNR and SSIM compared with the original LQ images. Moreover, PSNR and SSIM increased by over 4 dB and 0.04, respectively compared with the previous state-of-the-art methods (P < 0.05). The proportion of ungradable fundus photographs decreased from 42.6% to 26.4% (P = 0.012).ConclusionOur enhancement process improves LQ fundus images that suffer from complex degradation significantly. Moreover our customized CNN achieved improved performance over the existing state-of-the-art methods. Overall, our framework can have a clinical impact on reducing re-examinations and improving the accuracy of diagnosis.

Additional file 1 Stata code to generate Fig. 1.

Top 10 pathways of selected miRNAs from the CCLE data using mirPath 3.0#.

• p-value is for the for Kolmogorov-Smirnov goodness of fit test.

Selective serotonin re-uptake inhibitors (SSRI) widely used in the treatment of depression, anxiety, obsessive compulsive disorder, fibromyalgia, and migraine are among the most heavily prescribed drug class in the United States (US). Along with an overall rise in SSRI use, these medications are increasingly used by pregnant individuals and recent preclinical and clinical studies have indicated that SSRIs may increase the prevalence of congenital abnormalities and birth defects of the craniofacial region. Our group has developed pre-clinical models of study, including those that mimic the clinical use of SSRI in mice. Here we designed a study to interrogate a commonly prescribed SSRI drug, Citalopram, for its effects on craniofacial and dental development when introduced in utero. Pre-natal exposure to a clinically relevant dose of citalopram resulted in changes in craniofacial form identified by an increase in endocast volume in SSRI exposed postnatal day 15 mouse pups. More specifically, cranial length and synchondrosis length increased in SSRI exposed pups as compared to control pups of the same age. Additionally, growth center (synchondrosis) height and width and palate length and width decreased in SSRI exposed pups as compared to control un-exposed pups. Effects of SSRI on the molars was minimal. Craniofacial growth and development continue to be an area of interest in the investigation of in utero pharmaceutical drug exposure. Altogether these data indicate that prenatal SSRI exposure affects craniofacial form in multiple tissues and specifically at growth sites and centers of the skull.