Generative adversarial networks for imputing missing data for big data clinical research

Unravelling single-cell DNA replication timing dynamics using machine learning reveals heterogeneity in cancer progression

Genomic heterogeneity has largely been overlooked in single-cell replication timing (scRT) studies. Here, we develop MnM, an efficient machine learning-based tool that allows disentangling scRT profiles from heterogenous samples. We use single-cell copy number data to accurately perform missing value imputation, identify cell replication states, and detect genomic heterogeneity. This allows us to separate somatic copy number alterations from copy number changes resulting from DNA replication. Our methodology brings critical insights into chromosomal aberrations and highlights the ubiquitous aneuploidy process during tumorigenesis. The copy number and scRT profiles obtained by analysing >119,000 high-quality human single cells from different cell lines, patient tumours and patient-derived xenograft samples leads to a multi-sample heterogeneity-resolved scRT atlas. This atlas is an important resource for cancer research and demonstrates that scRT profiles can be used to study replication timing heterogeneity in cancer. Our findings also highlight the importance of studying cancer tissue samples to comprehensively grasp the complexities of DNA replication because cell lines, although convenient, lack dynamic environmental factors. These results facilitate future research at the interface of genomic instability and replication stress during cancer progression.

Addressing Missing Data Challenges in Geriatric Health Monitoring: A Study of Statistical and Machine Learning Imputation Methods

In geriatric healthcare, missing data pose significant challenges, especially in systems used for frailty monitoring in elderly individuals. This study explores advanced imputation techniques used to enhance data quality and maintain model performance in a system designed to detect frailty insights. We introduce missing data mechanisms-Missing Completely at Random (MCAR), Missing at Random (MAR), and Missing Not at Random (MNAR)-into a dataset collected from smart bracelets, simulating real-world conditions. Imputation methods, including Expectation-Maximization (EM), matrix completion, Bayesian networks, K-Nearest Neighbors (KNN), Support Vector Machines (SVMs), Generative Adversarial Imputation Networks (GAINs), Variational Autoencoder (VAE), and GRU-D, were evaluated based on normalized Mean Squared Error (MSE), Mean Absolute Error (MAE), and R2 metrics. The results demonstrate that KNN and SVM consistently outperform other methods across all three mechanisms due to their ability to adapt to diverse patterns of missingness. Specifically, KNN and SVM excel in MAR conditions by leveraging observed data relationships to accurately infer missing values, while their robustness to randomness enables superior performance under MCAR scenarios. In MNAR contexts, KNN and SVM effectively handle unobserved dependencies by identifying underlying patterns in the data, outperforming methods like GRU-D and VAE. These findings highlight the importance of selecting imputation methods based on the characteristics of missing data mechanisms, emphasizing the versatility and reliability of KNN and SVM in healthcare applications. This study advocates for hybrid approaches in healthcare applications like the cINnAMON project, which supports elderly individuals at risk of frailty through non-intrusive home monitoring systems.

Development and validation of HBV surveillance models using big data and machine learning

BACKGROUND

The construction of a robust healthcare information system is fundamental to enhancing countries' capabilities in the surveillance and control of hepatitis B virus (HBV). Making use of China's rapidly expanding primary healthcare system, this innovative approach using big data and machine learning (ML) could help towards the World Health Organization's (WHO) HBV infection elimination goals of reaching 90% diagnosis and treatment rates by 2030. We aimed to develop and validate HBV detection models using routine clinical data to improve the detection of HBV and support the development of effective interventions to mitigate the impact of this disease in China.

METHODS

Relevant data records extracted from the Family Medicine Clinic of the University of Hong Kong-Shenzhen Hospital's Hospital Information System were structuralized using state-of-the-art Natural Language Processing techniques. Several ML models have been used to develop HBV risk assessment models. The performance of the ML model was then interpreted using the Shapley value (SHAP) and validated using cohort data randomly divided at a ratio of 2:1 using a five-fold cross-validation framework.

RESULTS

The patterns of physical complaints of patients with and without HBV infection were identified by processing 158,988 clinic attendance records. After removing cases without any clinical parameters from the derivation sample (n = 105,992), 27,392 cases were analysed using six modelling methods. A simplified model for HBV using patients' physical complaints and parameters was developed with good discrimination (AUC = 0.78) and calibration (goodness of fit test p-value >0.05).

CONCLUSIONS

Suspected case detection models of HBV, showing potential for clinical deployment, have been developed to improve HBV surveillance in primary care setting in China. (Word count: 264).

A novel MissForest-based missing values imputation approach with recursive feature elimination in medical applications

BACKGROUND

Missing values in datasets present significant challenges for data analysis, particularly in the medical field where data accuracy is crucial for patient diagnosis and treatment. Although MissForest (MF) has demonstrated efficacy in imputation research and recursive feature elimination (RFE) has proven effective in feature selection, the potential for enhancing MF through RFE integration remains unexplored.

METHODS

This study introduces a novel imputation method, "recursive feature elimination-MissForest" (RFE-MF), designed to enhance imputation quality by reducing the impact of irrelevant features. A comparative analysis is conducted between RFE-MF and four classical imputation methods: mean/mode, k-nearest neighbors (kNN), multiple imputation by chained equations (MICE), and MF. The comparison is carried out across ten medical datasets containing both numerical and mixed data types. Different missing data rates, ranging from 10 to 50%, are evaluated under the missing completely at random (MCAR) mechanism. The performance of each method is assessed using two evaluation metrics: normalized root mean squared error (NRMSE) and predictive fidelity criterion (PFC). Additionally, paired samples t-tests are employed to analyze the statistical significance of differences among the outcomes.

RESULTS

The findings indicate that RFE-MF demonstrates superior performance across the majority of datasets when compared to four classical imputation methods (mean/mode, kNN, MICE, and MF). Notably, RFE-MF consistently outperforms the original MF, irrespective of variable type (numerical or categorical). Mean/mode imputation exhibits consistent performance across various scenarios. Conversely, the efficacy of kNN imputation fluctuates in relation to varying missing data rates.

CONCLUSION

This study demonstrates that RFE-MF holds promise as an effective imputation method for medical datasets, providing a novel approach to addressing missing data challenges in medical applications.

Using Machine Learning Models to Predict Pathologic Complete Response to Neoadjuvant Chemotherapy in Breast Cancer

PURPOSE

Neoadjuvant chemotherapy (NAC) is increasingly used in breast cancer. Predictive modeling is useful in predicting pathologic complete response (pCR) to NAC. We test machine learning (ML) models to predict pCR in breast cancer and explore methods of handling missing data.

METHODS

Four hundred and ninety-nine patients with breast cancer treated with NAC in two centers in Singapore (National Cancer Centre Singapore [NCCS] and KK Hospital) between January 2014 and December 2017 were included. Eleven clinical features were used to train five different ML models. Listwise deletion and imputation were evaluated on handling missing data. Model performance was evaluated by AUC and calibration (Brier score). Feature importance from the best performing model in the external testing data set was calculated using Shapley additive explanations.

RESULTS

Seventy-two (24.6%), 18 (24.7%), and 31 (24.8%) patients attained pCR in NCCS training, NCCS testing, and KK Women's and Children's Hospital (KKH) testing data sets, respectively. The random forest (RF) base and imputed models have the highest AUCs in the KKH cohort of 0.794 (95% CI, 0.709 to 0.873) and 0.795 (95% CI, 0.706 to 0.871), respectively, and were the best calibrated with the lowest Brier score. No statistically significant difference was noted between AUCs of the base and imputed models in all data sets. The imputed model had a larger positive predictive value (PPV; 98.2% v 95.1%) and negative predictive value (NPV; 96.7% v 90.0%) than the base model in the KKH data set. Estrogen receptor intensity, human epidermal growth factor 2 intensity, and age at diagnosis were the three most important predictors.

CONCLUSION

ML, particularly RF, demonstrates reasonable accuracy in pCR prediction after NAC. Imputing missing fields in the data can improve the PPV and NPV of the pCR prediction model.

Machine learning-based remission prediction in rheumatoid arthritis patients treated with biologic disease-modifying anti-rheumatic drugs: findings from the Kuwait rheumatic disease registry

Background

Rheumatoid arthritis (RA) is a common condition treated with biological disease-modifying anti-rheumatic medicines (bDMARDs). However, many patients exhibit resistance, necessitating the use of machine learning models to predict remissions in patients treated with bDMARDs, thereby reducing healthcare costs and minimizing negative effects.

Objective

The study aims to develop machine learning models using data from the Kuwait Registry for Rheumatic Diseases (KRRD) to identify clinical characteristics predictive of remission in RA patients treated with biologics.

Methods

The study collected follow-up data from 1,968 patients treated with bDMARDs from four public hospitals in Kuwait from 2013 to 2022. Machine learning techniques like lasso, ridge, support vector machine, random forest, XGBoost, and Shapley additive explanation were used to predict remission at a 1-year follow-up.

Results

The study used the Shapley plot in explainable Artificial Intelligence (XAI) to analyze the effects of predictors on remission prognosis across different types of bDMARDs. Top clinical features were identified for patients treated with bDMARDs, each associated with specific mean SHAP values. The findings highlight the importance of clinical assessments and specific treatments in shaping treatment outcomes.

Conclusion

The proposed machine learning model system effectively identifies clinical features predicting remission in bDMARDs, potentially improving treatment efficacy in rheumatoid arthritis patients.

Development and validation of 10-year risk prediction models of cardiovascular disease in Chinese type 2 diabetes mellitus patients in primary care using interpretable machine learning-based methods

AIM

To develop 10-year cardiovascular disease (CVD) risk prediction models in Chinese patients with type 2 diabetes mellitus (T2DM) managed in primary care using machine learning (ML) methods.

METHODS

In this 10-year population-based retrospective cohort study, 141 516 Chinese T2DM patients aged 18 years or above, without history of CVD or end-stage renal disease and managed in public primary care clinics in 2008, were included and followed up until December 2017. Two-thirds of the patients were randomly selected to develop sex-specific CVD risk prediction models. The remaining one-third of patients were used as the validation sample to evaluate the discrimination and calibration of the models. ML-based methods were applied to missing data imputation, predictor selection, risk prediction modelling, model interpretation, and model evaluation. Cox regression was used to develop the statistical models in parallel for comparison.

RESULTS

During a median follow-up of 9.75 years, 32 445 patients (22.9%) developed CVD. Age, T2DM duration, urine albumin-to-creatinine ratio (ACR), estimated glomerular filtration rate (eGFR), systolic blood pressure variability and glycated haemoglobin (HbA1c) variability were the most important predictors. ML models also identified nonlinear effects of several predictors, particularly the U-shaped effects of eGFR and body mass index. The ML models showed a Harrell's C statistic of >0.80 and good calibration. The ML models performed significantly better than the Cox regression models in CVD risk prediction and achieved better risk stratification for individual patients.

CONCLUSION

Using routinely available predictors and ML-based algorithms, this study established 10-year CVD risk prediction models for Chinese T2DM patients in primary care. The findings highlight the importance of renal function indicators, and variability in both blood pressure and HbA1c as CVD predictors, which deserve more clinical attention. The derived risk prediction tools have the potential to support clinical decision making and encourage patients towards self-care, subject to further research confirming the models' feasibility, acceptability and applicability at the point of care.

Identify the most appropriate imputation method for handling missing values in clinical structured datasets: a systematic review

BACKGROUND AND OBJECTIVES

Comprehending the research dataset is crucial for obtaining reliable and valid outcomes. Health analysts must have a deep comprehension of the data being analyzed. This comprehension allows them to suggest practical solutions for handling missing data, in a clinical data source. Accurate handling of missing values is critical for producing precise estimates and making informed decisions, especially in crucial areas like clinical research. With data's increasing diversity and complexity, numerous scholars have developed a range of imputation techniques. To address this, we conducted a systematic review to introduce various imputation techniques based on tabular dataset characteristics, including the mechanism, pattern, and ratio of missingness, to identify the most appropriate imputation methods in the healthcare field.

MATERIALS AND METHODS

We searched four information databases namely PubMed, Web of Science, Scopus, and IEEE Xplore, for articles published up to September 20, 2023, that discussed imputation methods for addressing missing values in a clinically structured dataset. Our investigation of selected articles focused on four key aspects: the mechanism, pattern, ratio of missingness, and various imputation strategies. By synthesizing insights from these perspectives, we constructed an evidence map to recommend suitable imputation methods for handling missing values in a tabular dataset.

RESULTS

Out of 2955 articles, 58 were included in the analysis. The findings from the development of the evidence map, based on the structure of the missing values and the types of imputation methods used in the extracted items from these studies, revealed that 45% of the studies employed conventional statistical methods, 31% utilized machine learning and deep learning methods, and 24% applied hybrid imputation techniques for handling missing values.

CONCLUSION

Considering the structure and characteristics of missing values in a clinical dataset is essential for choosing the most appropriate data imputation technique, especially within conventional statistical methods. Accurately estimating missing values to reflect reality enhances the likelihood of obtaining high-quality and reusable data, contributing significantly to precise medical decision-making processes. Performing this review study creates a guideline for choosing the most appropriate imputation methods in data preprocessing stages to perform analytical processes on structured clinical datasets.

Abdominal perfusion pressure is critical for survival analysis in patients with intra-abdominal hypertension: mortality prediction using incomplete data

BACKGROUND

Abdominal perfusion pressure (APP) is a salient feature in the design of a prognostic model for patients with intra-abdominal hypertension (IAH). However, incomplete data significantly limits the size of the beneficiary patient population in clinical practice. Using advanced artificial intelligence methods, we developed a robust mortality prediction model with APP from incomplete data.

METHODS

We retrospectively evaluated the patients with IAH from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Incomplete data were filled in using generative adversarial imputation nets (GAIN). Lastly, demographic, clinical, and laboratory findings were combined to build a 7-day mortality prediction model.

RESULTS

We included 1354 patients in this study, of which 63 features were extracted. Data imputation with GAIN achieved the best performance. Patients with an APP< 60 mmHg had significantly higher all-cause mortality within 7 to 90 days. The difference remained significant in long-term survival even after propensity score matching (PSM) eliminated other mortality risks between groups. Lastly, the built machine learning model for 7-day modality prediction achieved the best results with an AUC of 0.80 in patients with confirmed IAH outperforming the other four traditional clinical scoring systems.

CONCLUSIONS

APP reduction is an important survival predictor affecting the survival prognosis of patients with IAH. We constructed a robust model to predict the 7-day mortality probability of patients with IAH, which is superior to the commonly used clinical scoring systems.

Method for Incomplete and Imbalanced Data Based on Multivariate Imputation by Chained Equations and Ensemble Learning

The classification analysis of incomplete and imbalanced data is still a challenging task since these issues could negatively impact the training of classifiers, which were also found in our study on the physical fitness assessments of patients. And in fields such as healthcare, there are higher requirements for the accuracy of the generated imputation values. To train a high-performance classifier and pursue high accuracy, we attempted to resolve any potential negative impact by using a novel algorithmic approach based on the combination of multivariate imputation by chained equations and the ensemble learning method (MICEEN), which can solve the two problems simultaneously. We used multivariate imputation by chained equations to generate more accurate imputation values for the training set passed to ensemble learning to build a predictor. On the other hand, missing values were introduced into minority classes and used them to generate new samples belonging to the minority classes in order to balance the distribution of classes. On real-world datasets, we perform extensive experiments to assess our method and compare it to other state-of-the-art approaches. The advantages of the proposed method are demonstrated by experimental results for the benchmark datasets and self-collected datasets of physical fitness assessment of tumor patients with varying missing rates.

Missing Data Imputation Method Combining Random Forest and Generative Adversarial Imputation Network

(1) Background: In order to solve the problem of missing time-series data due to the influence of the acquisition system or external factors, a missing time-series data interpolation method based on random forest and a generative adversarial interpolation network is proposed. (2) Methods: First, the position of the missing part of the data is calibrated, and the trained random forest algorithm is used for the first data interpolation. The output value of the random forest algorithm is used as the input value of the generative adversarial interpolation network, and the generative adversarial interpolation network is used to calibrate the position. The data are interpolated for the second time, and the advantages of the two algorithms are combined to make the interpolation result closer to the true value. (3) Results: The filling effect of the algorithm is tested on a certain bearing data set, and the root mean square error (RMSE) is used to evaluate the interpolation results. The results show that the RMSE of the interpolation results based on the random forest and generative adversarial interpolation network algorithms in the case of single-segment and multi-segment missing data is only 0.0157, 0.0386, and 0.0527, which is better than the random forest algorithm, generative adversarial interpolation network algorithm, and K-nearest neighbor algorithm. (4) Conclusions: The proposed algorithm performs well in each data set and provides a reference method in the field of data filling.

Handling missing values in healthcare data: A systematic review of deep learning-based imputation techniques

OBJECTIVE

The proper handling of missing values is critical to delivering reliable estimates and decisions, especially in high-stakes fields such as clinical research. In response to the increasing diversity and complexity of data, many researchers have developed deep learning (DL)-based imputation techniques. We conducted a systematic review to evaluate the use of these techniques, with a particular focus on the types of data, intending to assist healthcare researchers from various disciplines in dealing with missing data.

MATERIALS AND METHODS

We searched five databases (MEDLINE, Web of Science, Embase, CINAHL, and Scopus) for articles published prior to February 8, 2023 that described the use of DL-based models for imputation. We examined selected articles from four perspectives: data types, model backbones (i.e., main architectures), imputation strategies, and comparisons with non-DL-based methods. Based on data types, we created an evidence map to illustrate the adoption of DL models.

RESULTS

Out of 1822 articles, a total of 111 were included, of which tabular static data (29%, 32/111) and temporal data (40%, 44/111) were the most frequently investigated. Our findings revealed a discernible pattern in the choice of model backbones and data types, for example, the dominance of autoencoder and recurrent neural networks for tabular temporal data. The discrepancy in imputation strategy usage among data types was also observed. The "integrated" imputation strategy, which solves the imputation task simultaneously with downstream tasks, was most popular for tabular temporal data (52%, 23/44) and multi-modal data (56%, 5/9). Moreover, DL-based imputation methods yielded a higher level of imputation accuracy than non-DL methods in most studies.

CONCLUSION

The DL-based imputation models are a family of techniques, with diverse network structures. Their designation in healthcare is usually tailored to data types with different characteristics. Although DL-based imputation models may not be superior to conventional approaches across all datasets, it is highly possible for them to achieve satisfactory results for a particular data type or dataset. There are, however, still issues with regard to portability, interpretability, and fairness associated with current DL-based imputation models.

Utilizing an artificial intelligence framework (conditional generative adversarial network) to enhance telemedicine strategies for cancer pain management

BACKGROUND

The utilization of artificial intelligence (AI) in healthcare has significant potential to revolutionize the delivery of medical services, particularly in the field of telemedicine. In this article, we investigate the capabilities of a specific deep learning model, a generative adversarial network (GAN), and explore its potential for enhancing the telemedicine approach to cancer pain management.

MATERIALS AND METHODS

We implemented a structured dataset comprising demographic and clinical variables from 226 patients and 489 telemedicine visits for cancer pain management. The deep learning model, specifically a conditional GAN, was employed to generate synthetic samples that closely resemble real individuals in terms of their characteristics. Subsequently, four machine learning (ML) algorithms were used to assess the variables associated with a higher number of remote visits.

RESULTS

The generated dataset exhibits a distribution comparable to the reference dataset for all considered variables, including age, number of visits, tumor type, performance status, characteristics of metastasis, opioid dosage, and type of pain. Among the algorithms tested, random forest demonstrated the highest performance in predicting a higher number of remote visits, achieving an accuracy of 0.8 on the test data. The simulations based on ML indicated that individuals who are younger than 45 years old, and those experiencing breakthrough cancer pain, may require an increased number of telemedicine-based clinical evaluations.

CONCLUSION

As the advancement of healthcare processes relies on scientific evidence, AI techniques such as GANs can play a vital role in bridging knowledge gaps and accelerating the integration of telemedicine into clinical practice. Nonetheless, it is crucial to carefully address the limitations of these approaches.

A simulation study on missing data imputation for dichotomous variables using statistical and machine learning methods

The problem of missing data, particularly for dichotomous variables, is a common issue in medical research. However, few studies have focused on the imputation methods of dichotomous data and their performance, as well as the applicability of these imputation methods and the factors that may affect their performance. In the arrangement of application scenarios, different missing mechanisms, sample sizes, missing rates, the correlation between variables, value distributions, and the number of missing variables were considered. We used data simulation techniques to establish a variety of different compound scenarios for missing dichotomous variables and conducted real-data validation on two real-world medical datasets. We comprehensively compared the performance of eight imputation methods (mode, logistic regression (LogReg), multiple imputation (MI), decision tree (DT), random forest (RF), k-nearest neighbor (KNN), support vector machine (SVM), and artificial neural network (ANN)) in each scenario. Accuracy and mean absolute error (MAE) were applied to evaluating their performance. The results showed that missing mechanisms, value distributions and the correlation between variables were the main factors affecting the performance of imputation methods. Machine learning-based methods, especially SVM, ANN, and DT, achieved relatively high accuracy with stable performance and were of potential applicability. Researchers should explore the correlation between variables and their distribution pattern in advance and prioritize machine learning-based methods for practical applications when encountering dichotomous missing data.

Long-term spill-over impact of COVID-19 on health and healthcare of people with non-communicable diseases: a study protocol for a population-based cohort and health economic study

INTRODUCTION

The COVID-19 pandemic has a significant spill-over effect on people with non-communicable diseases (NCDs) over the long term, beyond the direct effect of COVID-19 infection. Evaluating changes in health outcomes, health service use and costs can provide evidence to optimise care for people with NCDs during and after the pandemic, and to better prepare outbreak responses in the future.

METHODS AND ANALYSIS

This is a population-based cohort study using electronic health records of the Hong Kong Hospital Authority (HA) CMS, economic modelling and serial cross-sectional surveys on health service use. This study includes people aged ≥18 years who have a documented diagnosis of diabetes mellitus, hypertension, cardiovascular disease, cancer, chronic respiratory disease or chronic kidney disease with at least one attendance at the HA hospital or clinic between 1 January 2010 and 31 December 2019, and without COVID-19 infection. Changes in all-cause mortality, disease-specific outcomes, and health services use rates and costs will be assessed between pre-COVID-19 and-post-COVID-19 pandemic or during each wave using an interrupted time series analysis. The long-term health economic impact of healthcare disruptions during the COVID-19 pandemic will be studied using microsimulation modelling. Multivariable Cox proportional hazards regression and Poisson/negative binomial regression will be used to evaluate the effect of different modes of supplementary care on health outcomes.

ETHICS AND DISSEMINATION

The study was approved by the institutional review board of the University of Hong Kong, the HA Hong Kong West Cluster (reference number UW 21-297). The study findings will be disseminated through peer-reviewed publications and international conferences.

“Big Data” Approaches for Prevention of the Metabolic Syndrome

Metabolic syndrome (MetS) is characterized by the concurrence of multiple metabolic disorders resulting in the increased risk of a variety of diseases related to disrupted metabolism homeostasis. The prevalence of MetS has reached a pandemic level worldwide. In recent years, extensive amount of data have been generated throughout the research targeted or related to the condition with techniques including high-throughput screening and artificial intelligence, and with these “big data”, the prevention of MetS could be pushed to an earlier stage with different data source, data mining tools and analytic tools at different levels. In this review we briefly summarize the recent advances in the study of “big data” applications in the three-level disease prevention for MetS, and illustrate how these technologies could contribute tobetter preventive strategies.

Missing Data Imputation – A Survey

Many real world datasets may contain missing values for various reasons. These incomplete datasets can pose severe issues to the underlying machine learning algorithms and decision support systems. It may result in high computational cost, skewed output and invalid deductions. Various solutions exist to mitigate this issue; the most popular strategy is to estimate the missing values by applying inferential techniques such as linear regression, decision trees or Bayesian inference. In this paper, the missing data problem is discussed in detail with a comprehensive review of the approaches to tackle it. The paper concludes with a discussion on the effectiveness of three imputation methods namely, imputation based on Multiple Linear Regression (MLR), Predictive Mean Matching (PMM) and Classification And Regression Tree (CART) in the context of subspace clustering. The experimental results obtained on real benchmark datasets and high-dimensional synthetic datasets highlight that, MLR based imputation method is more efficient on high-dimensional incomplete datasets.