Time Series Analysis and Forecasting with Automated Machine Learning on a National ICD-10 Database

Automated Machine Learning Predicts Necessary Upcoming Therapy Changes in Patients With Psoriasis Vulgaris et Arthritis And Uncovers New Influences On Disease Progression: Retrospective Study

BACKGROUND

Psoriasis vulgaris (PsV) and Psoriatic arthritis (PsA) are intertwined multifactorial diseases with significant impact on health and quality of life, which can be debilitating due to chronicity and treatment complexity. Predicting treatment response and disease progression in these conditions is challenging, but crucial for optimising therapeutic interventions. The advancing technology of automated machine learning (AutoML) holds great promise for rapidly building highly accurate predictive models based on patient features and treatment data.

OBJECTIVE

The study aimed to develop highly accurate ML models using AutoML to address key clinical questions in PsV and PsA patients, including predicting therapy changes and identifying reasons for therapy changes, factors influencing skin lesion progression or factors associated with an abnormal BASDAI score.

METHODS

After extensive dataset preparation of clinical study data from 309 PsV and PsA patients, a secondary dataset was created and ultimately analysed using AutoML to build a variety of predictive models and select the most accurate one for each variable of interest.

RESULTS

"Therapy change at 24 weeks follow-up" was modelled using the eXtreme Gradient Boosted Trees Classifier with Early Stopping model (AUC of 0.9078 and LogLoss of 0.3955 for the holdout partition) to gain insight into the factors influencing therapy change, such as the initial systemic therapeutic agent, the score achieved in the CASPAR classification criteria at baseline, and changes in quality of life. An AVG blender of 3 models (Gradient Boosted Trees Classifier, ExtraTrees Classifier, Eureqa Generalised Additive Model Classifier) with an AUC of 0.8750 and a LogLoss of 0.4603 was used to predict therapy changes on two hypothetical patients to highlight the importance of such influencing factors. Notably, treatments such as MTX or specific biologicals showed a lower propensity for change. A further AVG Blender of RandomForest Classifier, eXtreme Gradient Boosted Trees Classifier and Eureqa Classifier (AUC of 0.9241 and LogLoss of 0.4498) was then used to estimate "PASI change after 24 weeks" with the primary predictors being the initial PASI score, change in pruritus and change in therapy. A lower initial PASI score, and consistently low pruritus were associated with better outcomes. Finally, "BASDAI classification at baseline" was analysed using an AVG Blender of Eureqa Generalised Additive Model Classifier, eXtreme Gradient Boosted Trees Classifier with Early Stopping and Dropout Additive Regression Trees Classifier with an AUC of 0.8274 and LogLoss of 0.5037. Factors influencing BASDAI scores included initial pain, disease activity and HADS scores for depression and anxiety. Increased pain, disease activity and psychological distress were generally likely to lead to higher BASDAI scores.

CONCLUSIONS

The practical implications of these models for clinical decision making in PsV and PsA have the potential to guide early investigation and treatment, contributing to improved patient outcomes.

CLINICALTRIAL

Automated Machine Learning Analysis of Patients With Chronic Skin Disease Using a Medical Smartphone App: Retrospective Study

BACKGROUND

Rapid digitalization in health care has led to the adoption of digital technologies; however, limited trust in internet-based health decisions and the need for technical personnel hinder the use of smartphones and machine learning applications. To address this, automated machine learning (AutoML) is a promising tool that can empower health care professionals to enhance the effectiveness of mobile health apps.

OBJECTIVE

We used AutoML to analyze data from clinical studies involving patients with chronic hand and/or foot eczema or psoriasis vulgaris who used a smartphone monitoring app. The analysis focused on itching, pain, Dermatology Life Quality Index (DLQI) development, and app use.

METHODS

After extensive data set preparation, which consisted of combining 3 primary data sets by extracting common features and by computing new features, a new pseudonymized secondary data set with a total of 368 patients was created. Next, multiple machine learning classification models were built during AutoML processing, with the most accurate models ultimately selected for further data set analysis.

RESULTS

Itching development for 6 months was accurately modeled using the light gradient boosted trees classifier model (log loss: 0.9302 for validation, 1.0193 for cross-validation, and 0.9167 for holdout). Pain development for 6 months was assessed using the random forest classifier model (log loss: 1.1799 for validation, 1.1561 for cross-validation, and 1.0976 for holdout). Then, the random forest classifier model (log loss: 1.3670 for validation, 1.4354 for cross-validation, and 1.3974 for holdout) was used again to estimate the DLQI development for 6 months. Finally, app use was analyzed using an elastic net blender model (area under the curve: 0.6567 for validation, 0.6207 for cross-validation, and 0.7232 for holdout). Influential feature correlations were identified, including BMI, age, disease activity, DLQI, and Hospital Anxiety and Depression Scale-Anxiety scores at follow-up. App use increased with BMI >35, was less common in patients aged >47 years and those aged 23 to 31 years, and was more common in those with higher disease activity. A Hospital Anxiety and Depression Scale-Anxiety score >8 had a slightly positive effect on app use.

CONCLUSIONS

This study provides valuable insights into the relationship between data characteristics and targeted outcomes in patients with chronic eczema or psoriasis, highlighting the potential of smartphone and AutoML techniques in improving chronic disease management and patient care.

Exploring the influence of COVID-19 on the spread of hand, foot, and mouth disease with an automatic machine learning prediction model

Hand, foot, and mouth disease (HFMD) is an important public health problem and has received concern worldwide. Moreover, the coronavirus disease 2019 (COVID-19) epidemic also increases the difficulty of understanding and predicting the prevalence of HFMD. The purpose is to prove the usability and applicability of the automatic machine learning (Auto-ML) algorithm in predicting the epidemic trend of HFMD and to explore the influence of COVID-19 on the spread of HFMD. The AutoML algorithm and the autoregressive integrated moving average (ARIMA) model were applied to construct and validate models, based on the monthly incidence numbers of HFMD and meteorological factors from May 2008 to December 2019 in Henan province, China. A total of four models were established, among which the Auto-ML model with meteorological factors had minimum RMSE and MAE in both the model constructing phase and forecasting phase (training set: RMSE = 1424.40 and MAE = 812.55; test set: RMSE = 2107.83, MAE = 1494.41), so this model has the best performance. The optimal model was used to further predict the incidence numbers of HFMD in 2020 and then compared with the reported cases. And, for analysis, 2020 was divided into two periods. The predicted incidence numbers followed the same trend as the reported cases of HFMD before the COVID-19 outbreak; while after the COVID-19 outbreak, the reported cases have been greatly reduced than expected, with an average of only about 103 cases per month, and the incidence peak has also been delayed, which has led to significant changes in the seasonality of HFMD. Overall, the AutoML algorithm is an applicable and ideal method to predict the epidemic trend of the HFMD. Furthermore, it was found that the countermeasures of COVID-19 have a certain influence on suppressing the spread of HFMD during the period of COVID-19. The findings are helpful to health administrative departments.

Leveraging electronic health records for data science: common pitfalls and how to avoid them

Analysis of electronic health records (EHRs) is an increasingly common approach for studying real-world patient data. Use of routinely collected data offers several advantages compared with other study designs, including reduced administrative costs, the ability to update analysis as practice patterns evolve, and larger sample sizes. Methodologically, EHR analysis is subject to distinct challenges because data are not collected for research purposes. In this Viewpoint, we elaborate on the importance of in-depth knowledge of clinical workflows and describe six potential pitfalls to be avoided when working with EHR data, drawing on examples from the literature and our experience. We propose solutions for prevention or mitigation of factors associated with each of these six pitfalls-sample selection bias, imprecise variable definitions, limitations to deployment, variable measurement frequency, subjective treatment allocation, and model overfitting. Ultimately, we hope that this Viewpoint will guide researchers to further improve the methodological robustness of EHR analysis.

Hypertension and Diabetes in Akatsi South District, Ghana: Modeling and Forecasting

Background

The rising incidence of hypertension and diabetes calls for a global response. Hypertension and diabetes will rise in Ghana as the population ages, urbanization increases, and people lead unhealthy lives. Our goal was to create a time series algorithm that effectively predicts future increases to help preventative medicine and health care intervention strategies by preparing health care practitioners to control health problems.

Methods

Data on hypertension and diabetes from January 2016 to December 2020 were obtained from three health facilities. To detect patterns and predict data from a particular time series, three forecasting algorithms (SARIMAX (seasonal autoregressive integrated moving average with exogenous components), ARIMA (autoregressive integrated moving average), and LSTM (long short-term memory networks)) were implemented. We assessed the model's ability to perform by calculating the root mean square error (RMSE), mean absolute error (MAE), mean square error (MSE), and mean absolute percentage error (MAPE).

Results

The RMSE, MSE, MAE, and MAPE for ARIMA (5, 2, 4), SARIMAX (1, 1,  1) × (1, 1, 1,  7), and LSTM was 28, 769.02, 22, and 7%, 67, 4473, 56, and 14%, and 36, 1307, 27, and 8.6%, respectively. We chose ARIMA (5, 2, 4) as a more suitable model due to its lower error metrics when compared to the others.

Conclusion

All models had promising predictability and predicted a rise in the number of cases in the future, and this was essential for administrative and management planning. For appropriate and efficient strategic planning and control, the prognosis was useful enough than would have been possible without it.

Retrospective analysis and time series forecasting with automated machine learning of ascariasis, enterobiasis and cystic echinococcosis in Romania

The epidemiology of neglected tropical diseases (NTD) is persistently underprioritized, despite NTD being widespread among the poorest populations and in the least developed countries on earth. This situation necessitates thorough and efficient public health intervention. Romania is at the brink of becoming a developed country. However, this South-Eastern European country appears to be a region that is susceptible to an underestimated burden of parasitic diseases despite recent public health reforms. Moreover, there is an evident lack of new epidemiologic data on NTD after Romania's accession to the European Union (EU) in 2007. Using the national ICD-10 dataset for hospitalized patients in Romania, we generated time series datasets for 2008-2018. The objective was to gain deep understanding of the epidemiological distribution of three selected and highly endemic parasitic diseases, namely, ascariasis, enterobiasis and cystic echinococcosis (CE), during this period and forecast their courses for the ensuing two years. Through descriptive and inferential analysis, we observed a decline in case numbers for all three NTD. Several distributional particularities at regional level emerged. Furthermore, we performed predictions using a novel automated time series (AutoTS) machine learning tool and could interestingly show a stable course for these parasitic NTD. Such predictions can help public health officials and medical organizations to implement targeted disease prevention and control. To our knowledge, this is the first study involving a retrospective analysis of ascariasis, enterobiasis and CE on a nationwide scale in Romania. It is also the first to use AutoTS technology for parasitic NTD.

WITHDRAWN: Usage of deep learning in environmental health risk assessment

Ahead of Print article withdrawn by publisher.

The Deep Learning LSTM and MTD Models Best Predict Acute Respiratory Infection among Under-Five-Year Old Children in Somaliland

The most effective techniques for predicting time series patterns include machine learning and classical time series methods. The aim of this study is to search for the best artificial intelligence and classical forecasting techniques that can predict the spread of acute respiratory infection (ARI) and pneumonia among under-five-year old children in Somaliland. The techniques used in the study include seasonal autoregressive integrated moving averages (SARIMA), mixture transitions distribution (MTD), and long short term memory (LSTM) deep learning. The data used in the study were monthly observations collected from five regions in Somaliland from 2011–2014. Prediction results from the three best competing models are compared by using root mean square error (RMSE) and absolute mean deviation (MAD) accuracy measures. Results have shown that the deep learning LSTM and MTD models slightly outperformed the classical SARIMA model in predicting ARI values.

Big Data, Decision Models, and Public Health

Unlike most daily decisions, medical decision making often has substantial consequences and trade-offs. Recently, big data analytics techniques such as statistical analysis, data mining, machine learning and deep learning can be applied to construct innovative decision models. With complex decision making, it can be difficult to comprehend and compare the benefits and risks of all available options to make a decision. For these reasons, this Special Issue focuses on the use of big data analytics and forms of public health decision making based on the decision model, spanning from theory to practice. A total of 64 submissions were carefully blind peer reviewed by at least two referees and, finally, 23 papers were selected for this Special Issue.