Obesity Prediction with EHR Data: A deep learning approach with interpretable elements

Unraveling the Potential of Attentive Bi-LSTM for Accurate Obesity Prognosis: Advancing Public Health towards Sustainable Cities

The global prevalence of obesity presents a pressing challenge to public health and healthcare systems, necessitating accurate prediction and understanding for effective prevention and management strategies. This article addresses the need for improved obesity prediction models by conducting a comprehensive analysis of existing machine learning (ML) and deep learning (DL) approaches. This study introduces a novel hybrid model, Attention-based Bi-LSTM (ABi-LSTM), which integrates attention mechanisms with bidirectional Long Short-Term Memory (Bi-LSTM) networks to enhance interpretability and performance in obesity prediction. Our study fills a crucial gap by bridging healthcare and urban planning domains, offering insights into data-driven approaches to promote healthier living within urban environments. The proposed ABi-LSTM model demonstrates exceptional performance, achieving a remarkable accuracy of 96.5% in predicting obesity levels. Comparative analysis showcases its superiority over conventional approaches, with superior precision, recall, and overall classification balance. This study highlights significant advancements in predictive accuracy and positions the ABi-LSTM model as a pioneering solution for accurate obesity prognosis. The implications extend beyond healthcare, offering a precise tool to address the global obesity epidemic and foster sustainable development in smart cities.

Prediction of adolescent weight status by machine learning: a population-based study

BACKGROUND

Adolescent weight problems have become a growing public health concern, making early prediction of non-normal weight status crucial for effective prevention. However, few temporal prediction tools for adolescent four weight status have been developed. This study aimed to predict the short- and long-term weight status of Hong Kong adolescents and assess the importance of predictors.

METHODS

A population-based retrospective cohort study of adolescents was conducted using data from a territory-wide voluntary annual health assessment service provided by the Department of Health in Hong Kong. Using diet habits, physical activity, psychological well-being, and demographics, we generated six prediction models for successive weight status (normal, overweight, obese and underweight) using multiclass Decision Tree, Random Forest, k-Nearest Neighbor, eXtreme gradient boosting, support vector machine, logistic regression. Model performance was evaluated by multiple standard classifier metrics and the overall accuracy. Predictors' importance was assessed using Shapley values.

RESULTS

442,898 Primary 4 (P4, Grade 4 in the US) and 344,186 in Primary 6 (P6, Grade 6 in the US) students, with followed up until their Secondary 6 (Grade 12 in the US) during the academic years 1995/96 to 2014/15 were included. The XG Boosts model consistently outperformed all other model in predicting the long-term weight status at S6 from P4 or P6. It achieved an overall accuracy of 0.72 or 0.74, a micro-averaging AUC of 0.92 or 0.93, and a macro-averaging AUC of 0.83 or 0.86, respectively. XG Boost also demonstrated accurate predictions for each predicted weight status, surpassing the AUC values obtained by other models. Weight, height, sex, age, frequency and hours of aerobic exercise were consistently the most important predictors for both cohorts.

CONCLUSIONS

The machine learning approaches accurately predict adolescent weight status in both short- and long-term. The developed multiclass model that utilizing easy-assessed variables enables accurate long-term prediction on weight status, which can be used by adolescents and parents for self-prediction when applied in health care system. The interpretable models may help to provide the early and individualized interventions suggestions for adolescents with weight problems particularly.

A review of the application of deep learning in obesity: From early prediction aid to advanced management assistance

BACKGROUND AND AIMS

Obesity is a chronic disease which can cause severe metabolic disorders. Machine learning (ML) techniques, especially deep learning (DL), have proven to be useful in obesity research. However, there is a dearth of systematic reviews of DL applications in obesity. This article aims to summarize the current trend of DL usage in obesity research.

METHODS

An extensive literature review was carried out across multiple databases, including PubMed, Embase, Web of Science, Scopus, and Medline, to collate relevant studies published from January 2018 to September 2023. The focus was on research detailing the application of DL in the context of obesity. We have distilled critical insights pertaining to the utilized learning models, encompassing aspects of their development, principal results, and foundational methodologies.

RESULTS

Our analysis culminated in the synthesis of new knowledge regarding the application of DL in the context of obesity. Finally, 40 research articles were included. The final collection of these research can be divided into three categories: obesity prediction (n = 16); obesity management (n = 13); and body fat estimation (n = 11).

CONCLUSIONS

This is the first review to examine DL applications in obesity. It reveals DL's superiority in obesity prediction over traditional ML methods, showing promise for multi-omics research. DL also innovates in obesity management through diet, fitness, and environmental analyses. Additionally, DL improves body fat estimation, offering affordable and precise monitoring tools. The study is registered with PROSPERO (ID: CRD42023475159).

Prediction models for children/adolescents with obesity/overweight: A systematic review and meta-analysis

The incidence of obesity and overweight in children and adolescents is increasing worldwide and becomes a global health concern. This study aims to evaluate the accuracy of available prediction models in early identification of obesity and overweight in general children or adolescents and identify predictive factors for the models, thus provide a reference for subsequent development of risk prediction tools for obesity and overweight in children or adolescents. Related publications were obtained from several databases such as PubMed, Embase, Cochrane Library, and Web of Science from their inception to September 18th, 2022. The novel Prediction Model Risk of Bias Assessment Tool (PROBAST) was employed to assess the bias risk of the included studies. R4.2.0 and Stata15.1 softwares were used to conduct meta-analysis. This study involved 45 cross-sectional and/or prospective studies with 126 models. Meta-analyses showed that the overall pooled index of concordance (c-index) of prediction models for children/adolescents with obesity and overweight in the training set was 0.769 (95% CI 0.754-0.785) and 0.835(95% CI 0.792-0.879), respectively. Additionally, a large number of predictors were found to be related to children's lifestyles, such as sleep duration, sleep quality, and eating speed. In conclusions, prediction models can be employed to predict obesity/overweight in children and adolescents. Most predictors are controllable factors and are associated with lifestyle. Therefore, the prediction model serves as an excellent tool to formulate effective strategies for combating obesity/overweight in pediatric patients.

TGRA-P: Task-driven model predicts 90-day mortality from ICU clinical notes on mechanical ventilation

BACKGROUND

With the outbreak and spread of COVID-19 worldwide, limited ventilators fail to meet the surging demand for mechanical ventilation in the ICU. Clinical models based on structured data that have been proposed to rationalize ventilator allocation often suffer from poor ductility due to fixed fields and laborious normalization processes. The advent of pre-trained models and downstream fine-tuning methods allows for learning large amounts of unstructured clinical text for different tasks. But the hardware requirements of large-scale pre-trained models and purposeless networks downstream have led to a lack of promotion in the clinical domain.

OBJECTIVE

In this study, an innovative architecture of a task-driven predictive model is proposed and a Task-driven Gated Recurrent Attention Pool model (TGRA-P) is developed based on the architecture. TGRA-P predicts early mortality risk from patients' clinical notes on mechanical ventilation in the ICU, which is used to assist clinicians in diagnosis and decision-making.

METHODS

Specifically, a Task-Specific Embedding Module is proposed to fine-tune the embedding with task labels and save it as static files for downstream calls. It serves the task better and prevents GPU overload. The Gated Recurrent Attention Unit (GRA) is proposed to further enhance the dependency of the information preceding and following the text sequence with fewer parameters. In addition, we propose a Residual Max Pool (RMP) to avoid ignoring words in common text classification tasks by incorporating all word-level features of the notes for prediction. Finally, we use a fully connected decoding network as a classifier to predict the mortality risk.

RESULT

The proposed model shows very promising results with an AUROC of 0.8245±0.0096, an AUPRC of 0.7532±0.0115, an accuracy of 0.7422±0.0028 and F1-score of 0.6612±0.0059 for 90-day mortality prediction using clinical notes of ICU mechanically ventilated patients on the MIMIC-III dataset, all of which are better than previous studies. Moreover, the superiority of the proposed model in comparison with other baseline models is also statistically validated through the calculated Cohen's d effect sizes.

CONCLUSION

The experimental results show that TGRA-P based on the innovative task-driven prognostic architecture obtains state-of-the-art performance. In future work, we will build upon the provided code and investigate its applicability to different datasets. The model balances performance and efficiency, not only reducing the cost of early mortality risk prediction but also assisting physicians in making timely clinical interventions and decisions. By incorporating textual records that are challenging for clinicians to utilize, the model serves as a valuable complement to physicians' judgment, enhancing their decision-making process.

Improving Diagnostics with Deep Forest Applied to Electronic Health Records

An electronic health record (EHR) is a vital high-dimensional part of medical concepts. Discovering implicit correlations in the information of this data set and the research and informative aspects can improve the treatment and management process. The challenge of concern is the data sources' limitations in finding a stable model to relate medical concepts and use these existing connections. This paper presents Patient Forest, a novel end-to-end approach for learning patient representations from tree-structured data for readmission and mortality prediction tasks. By leveraging statistical features, the proposed model is able to provide an accurate and reliable classifier for predicting readmission and mortality. Experiments on MIMIC-III and eICU datasets demonstrate Patient Forest outperforms existing machine learning models, especially when the training data are limited. Additionally, a qualitative evaluation of Patient Forest is conducted by visualising the learnt representations in 2D space using the t-SNE, which further confirms the effectiveness of the proposed model in learning EHR representations.

Predicting Visit Cost of Obstructive Sleep Apnea Using Electronic Healthcare Records With Transformer

BACKGROUND

Obstructive sleep apnea (OSA) is growing increasingly prevalent in many countries as obesity rises. Sufficient, effective treatment of OSA entails high social and financial costs for healthcare.

OBJECTIVE

For treatment purposes, predicting OSA patients' visit expenses for the coming year is crucial. Reliable estimates enable healthcare decision-makers to perform careful fiscal management and budget well for effective distribution of resources to hospitals. The challenges created by scarcity of high-quality patient data are exacerbated by the fact that just a third of those data from OSA patients can be used to train analytics models: only OSA patients with more than 365 days of follow-up are relevant for predicting a year's expenditures.

METHODS AND PROCEDURES

The authors propose a translational engineering method applying two Transformer models, one for augmenting the input via data from shorter visit histories and the other predicting the costs by considering both the material thus enriched and cases with more than a year's follow-up. This method effectively adapts state-of-the-art Transformer models to create practical cost prediction solutions that can be implemented in OSA management, potentially enhancing patient care and resource allocation.

RESULTS

The two-model solution permits putting the limited body of OSA patient data to productive use. Relative to a single-Transformer solution using only a third of the high-quality patient data, the solution with two models improved the prediction performance's [Formula: see text] from 88.8% to 97.5%. Even using baseline models with the model-augmented data improved the [Formula: see text] considerably, from 61.6% to 81.9%.

CONCLUSION

The proposed method makes prediction with the most of the available high-quality data by carefully exploiting details, which are not directly relevant for answering the question of the next year's likely expenditure. Clinical and Translational Impact Statement: Public Health- Lack of high-quality source data hinders data-driven analytics-based research in healthcare. The paper presents a method that couples data augmentation and prediction in cases of scant healthcare data.

Machine Learning Algorithms to Predict Breast Cancer Recurrence Using Structured and Unstructured Sources from Electronic Health Records

Recurrence is a critical aspect of breast cancer (BC) that is inexorably tied to mortality. Reuse of healthcare data through Machine Learning (ML) algorithms offers great opportunities to improve the stratification of patients at risk of cancer recurrence. We hypothesized that combining features from structured and unstructured sources would provide better prediction results for 5-year cancer recurrence than either source alone. We collected and preprocessed clinical data from a cohort of BC patients, resulting in 823 valid subjects for analysis. We derived three sets of features: structured information, features from free text, and a combination of both. We evaluated the performance of five ML algorithms to predict 5-year cancer recurrence and selected the best-performing to test our hypothesis. The XGB (eXtreme Gradient Boosting) model yielded the best performance among the five evaluated algorithms, with precision = 0.900, recall = 0.907, F1-score = 0.897, and area under the receiver operating characteristic AUROC = 0.807. The best prediction results were achieved with the structured dataset, followed by the unstructured dataset, while the combined dataset achieved the poorest performance. ML algorithms for BC recurrence prediction are valuable tools to improve patient risk stratification, help with post-cancer monitoring, and plan more effective follow-up. Structured data provides the best results when fed to ML algorithms. However, an approach based on natural language processing offers comparable results while potentially requiring less mapping effort.

Systematic Review of Machine Learning applied to the Prediction of Obesity and Overweight

Obesity and overweight has increased in the last year and has become a pandemic disease, the result of sedentary lifestyles and unhealthy diets rich in sugars, refined starches, fats and calories. Machine learning (ML) has proven to be very useful in the scientific community, especially in the health sector. With the aim of providing useful tools to help nutritionists and dieticians, research focused on the development of ML and Deep Learning (DL) algorithms and models is searched in the literature. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol has been used, a very common technique applied to carry out revisions. In our proposal, 17 articles have been filtered in which ML and DL are applied in the prediction of diseases, in the delineation of treatment strategies, in the improvement of personalized nutrition and more. Despite expecting better results with the use of DL, according to the selected investigations, the traditional methods are still the most used and the yields in both cases fluctuate around positive values, conditioned by the databases (transformed in each case) to a greater extent than by the artificial intelligence paradigm used. Conclusions: An important compilation is provided for the literature in this area. ML models are time-consuming to clean data, but (like DL) they allow automatic modeling of large volumes of data which makes them superior to traditional statistics.

Predicting Childhood Obesity Based on Single and Multiple Well-Child Visit Data Using Machine Learning Classifiers

Childhood obesity is a public health concern in the United States. Consequences of childhood obesity include metabolic disease and heart, lung, kidney, and other health-related comorbidities. Therefore, the early determination of obesity risk is needed and predicting the trend of a child's body mass index (BMI) at an early age is crucial. Early identification of obesity can lead to early prevention. Multiple methods have been tested and evaluated to assess obesity trends in children. Available growth charts help determine a child's current obesity level but do not predict future obesity risk. The present methods of predicting obesity include regression analysis and machine learning-based classifications and risk factor (threshold)-based categorizations based on specific criteria. All the present techniques, especially current machine learning-based methods, require longitudinal data and information on a large number of variables related to a child's growth (e.g., socioeconomic, family-related factors) in order to predict future obesity-risk. In this paper, we propose three different techniques for three different scenarios to predict childhood obesity based on machine learning approaches and apply them to real data. Our proposed methods predict obesity for children at five years of age using the following three data sets: (1) a single well-child visit, (2) multiple well-child visits under the age of two, and (3) multiple random well-child visits under the age of five. Our models are especially important for situations where only the current patient information is available rather than having multiple data points from regular spaced well-child visits. Our models predict obesity using basic information such as birth BMI, gestational age, BMI measures from well-child visits, and gender. Our models can predict a child's obesity category (normal, overweight, or obese) at five years of age with an accuracy of 89%, 77%, and 89%, for the three application scenarios, respectively. Therefore, our proposed models can assist healthcare professionals by acting as a decision support tool to aid in predicting childhood obesity early in order to reduce obesity-related complications, and in turn, improve healthcare.

Obesity Prediction with EHR Data: A deep learning approach with interpretable elements

Childhood obesity is a major public health challenge. Early prediction and identification of the children at an elevated risk of developing childhood obesity may help in engaging earlier and more effective interventions to prevent and manage obesity. Most existing predictive tools for childhood obesity primarily rely on traditional regression-type methods using only a few hand-picked features and without exploiting longitudinal patterns of children's data. Deep learning methods allow the use of high-dimensional longitudinal datasets. In this paper, we present a deep learning model designed for predicting future obesity patterns from generally available items on children's medical history. To do this, we use a large unaugmented electronic health records dataset from a large pediatric health system in the US. We adopt a general LSTM network architecture and train our proposed model using both static and dynamic EHR data. To add interpretability, we have additionally included an attention layer to calculate the attention scores for the timestamps and rank features of each timestamp. Our model is used to predict obesity for ages between 3-20 years using the data from 1-3 years in advance. We compare the performance of our LSTM model with a series of existing studies in the literature and show it outperforms their performance in most age ranges.

Flexible-Window Predictions on Electronic Health Records

Various types of machine learning techniques are available for analyzing electronic health records (EHRs). For predictive tasks, most existing methods either explicitly or implicitly divide these time-series datasets into predetermined observation and prediction windows. Patients have different lengths of medical history and the desired predictions (for purposes such as diagnosis or treatment) are required at different times in the future. In this paper, we propose a method that uses a sequence-to-sequence generator model to transfer an input sequence of EHR data to a sequence of user-defined target labels, providing the end-users with "flexible" observation and prediction windows to define. We use adversarial and semi-supervised approaches in our design, where the sequence-to-sequence model acts as a generator and a discriminator distinguishes between the actual (observed) and generated labels. We evaluate our models through an extensive series of experiments using two large EHR datasets from adult and pediatric populations. In an obesity predicting case study, we show that our model can achieve superior results in flexible-window prediction tasks, after being trained once and even with large missing rates on the input EHR data. Moreover, using a number of attention analysis experiments, we show that the proposed model can effectively learn more relevant features in different prediction tasks.