CPAS: the UK's national machine learning-based hospital capacity planning system for COVID-19

AutoML-Driven Insights into Patient Outcomes and Emergency Care During Romania's First Wave of COVID-19

BACKGROUND

The COVID-19 pandemic severely impacted healthcare systems, affecting patient outcomes and resource allocation. This study applied automated machine learning (AutoML) to analyze key health outputs, such as discharge conditions, mortality, and COVID-19 cases, with the goal of improving responses to future crises.

METHODS

AutoML was used to train and validate models on an ICD-10 dataset covering the first wave of COVID-19 in Romania (January-September 2020).

RESULTS

For discharge outcomes, Light Gradient Boosted models achieved an F1 score of 0.9644, while for mortality 0.7545 was reached. A Generalized Linear Model blender achieved an F1 score of 0.9884 for "acute or emergency" cases, and an average blender reached 0.923 for COVID-19 cases. Older age, specific hospitals, and oncology wards were less associated with improved recovery rates, while mortality was linked to abnormal lab results and cardiovascular/respiratory diseases. Patients admitted without referral, or patients in hospitals in the central region and the capital region of Romania were more likely to be acute cases. Finally, counties such as Argeş (South-Muntenia) and Brașov (Center) showed higher COVID-19 infection rates regardless of age.

CONCLUSIONS

AutoML provided valuable insights into patient outcomes, highlighting variations in care and the need for targeted health strategies for both COVID-19 and other health challenges.

Using Automated Machine Learning to Predict Necessary Upcoming Therapy Changes in Patients With Psoriasis Vulgaris and Psoriatic Arthritis and Uncover New Influences on Disease Progression: Retrospective Study

BACKGROUND

Psoriasis vulgaris (PsV) and psoriatic arthritis (PsA) are complex, multifactorial diseases significantly impacting health and quality of life. Predicting treatment response and disease progression is crucial for optimizing therapeutic interventions, yet challenging. Automated machine learning (AutoML) technology shows promise for rapidly creating accurate predictive models based on patient features and treatment data.

OBJECTIVE

This study aims to develop highly accurate machine learning (ML) models using AutoML to address key clinical questions for PsV and PsA patients, including predicting therapy changes, identifying reasons for therapy changes, and factors influencing skin lesion progression or an abnormal Bath Ankylosing Spondylitis Disease Activity Index (BASDAI) score.

METHODS

Clinical study data from 309 PsV and PsA patients were extensively prepared and analyzed using AutoML to build and select the most accurate predictive models for each variable of interest.

RESULTS

Therapy change at 24 weeks follow-up was modeled using the extreme gradient boosted trees classifier with early stopping (area under the receiver operating characteristic curve [AUC] of 0.9078 and logarithmic loss [LogLoss] of 0.3955 for the holdout partition). Key influencing factors included the initial systemic therapeutic agent, the Classification Criteria for Psoriatic Arthritis score at baseline, and changes in quality of life. An average blender incorporating three models (gradient boosted trees classifier, ExtraTrees classifier, and Eureqa generalized additive model classifier) with an AUC of 0.8750 and LogLoss of 0.4603 was used to predict therapy changes for 2 hypothetical patients, highlighting the significance of these factors. Treatments such as methotrexate or specific biologicals showed a lower propensity for change. An average blender of a random forest classifier, an extreme gradient boosted trees classifier, and a Eureqa classifier (AUC of 0.9241 and LogLoss of 0.4498) was used to estimate PASI (Psoriasis Area and Severity Index) change after 24 weeks. Primary predictors included the initial PASI score, change in pruritus levels, and change in therapy. A lower initial PASI score and consistently low pruritus were associated with better outcomes. BASDAI classification at onset was analyzed using an average blender of a Eureqa generalized additive model classifier, an extreme gradient boosted trees classifier with early stopping, and a dropout additive regression trees classifier with an AUC of 0.8274 and LogLoss of 0.5037. Influential factors included initial pain, disease activity, and Hospital Anxiety and Depression Scale scores for depression and anxiety. Increased pain, disease activity, and psychological distress generally led to higher BASDAI scores.

CONCLUSIONS

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

Neural machine translation of clinical text: an empirical investigation into multilingual pre-trained language models and transfer-learning

Clinical text and documents contain very rich information and knowledge in healthcare, and their processing using state-of-the-art language technology becomes very important for building intelligent systems for supporting healthcare and social good. This processing includes creating language understanding models and translating resources into other natural languages to share domain-specific cross-lingual knowledge. In this work, we conduct investigations on clinical text machine translation by examining multilingual neural network models using deep learning such as Transformer based structures. Furthermore, to address the language resource imbalance issue, we also carry out experiments using a transfer learning methodology based on massive multilingual pre-trained language models (MMPLMs). The experimental results on three sub-tasks including (1) clinical case (CC), (2) clinical terminology (CT), and (3) ontological concept (OC) show that our models achieved top-level performances in the ClinSpEn-2022 shared task on English-Spanish clinical domain data. Furthermore, our expert-based human evaluations demonstrate that the small-sized pre-trained language model (PLM) outperformed the other two extra-large language models by a large margin in the clinical domain fine-tuning, which finding was never reported in the field. Finally, the transfer learning method works well in our experimental setting using the WMT21fb model to accommodate a new language space Spanish that was not seen at the pre-training stage within WMT21fb itself, which deserves more exploitation for clinical knowledge transformation, e.g. to investigate into more languages. These research findings can shed some light on domain-specific machine translation development, especially in clinical and healthcare fields. Further research projects can be carried out based on our work to improve healthcare text analytics and knowledge transformation. Our data is openly available for research purposes at: https://github.com/HECTA-UoM/ClinicalNMT.

Using Machine Learning to Predict Suitability for Surgery at an Ambulatory Surgical Center

This Surgical Innovation describes the use of a site optimization model that uses machine learning to stratify patients according to whether they can have surgery at an ambulatory surgical center vs a hospital-based outpatient department.

AutoPrognosis 2.0: Democratizing diagnostic and prognostic modeling in healthcare with automated machine learning

Diagnostic and prognostic models are increasingly important in medicine and inform many clinical decisions. Recently, machine learning approaches have shown improvement over conventional modeling techniques by better capturing complex interactions between patient covariates in a data-driven manner. However, the use of machine learning introduces technical and practical challenges that have thus far restricted widespread adoption of such techniques in clinical settings. To address these challenges and empower healthcare professionals, we present an open-source machine learning framework, AutoPrognosis 2.0, to facilitate the development of diagnostic and prognostic models. AutoPrognosis leverages state-of-the-art advances in automated machine learning to develop optimized machine learning pipelines, incorporates model explainability tools, and enables deployment of clinical demonstrators, without requiring significant technical expertise. To demonstrate AutoPrognosis 2.0, we provide an illustrative application where we construct a prognostic risk score for diabetes using the UK Biobank, a prospective study of 502,467 individuals. The models produced by our automated framework achieve greater discrimination for diabetes than expert clinical risk scores. We have implemented our risk score as a web-based decision support tool, which can be publicly accessed by patients and clinicians. By open-sourcing our framework as a tool for the community, we aim to provide clinicians and other medical practitioners with an accessible resource to develop new risk scores, personalized diagnostics, and prognostics using machine learning techniques. Software: https://github.com/vanderschaarlab/AutoPrognosis.

Data science in the intensive care unit

In this editorial, we comment on the current development and deployment of data science in intensive care units (ICUs). Data in ICUs can be classified into qualitative and quantitative data with different technologies needed to translate and interpret them. Data science, in the form of artificial intelligence (AI), should find the right interaction between physicians, data and algorithm. For individual patients and physicians, sepsis and mechanical ventilation have been two important aspects where AI has been extensively studied. However, major risks of bias, lack of generalizability and poor clinical values remain. AI deployment in the ICUs should be emphasized more to facilitate AI development. For ICU management, AI has a huge potential in transforming resource allocation. The coronavirus disease 2019 pandemic has given opportunities to establish such systems which should be investigated further. Ethical concerns must be addressed when designing such AI.

Associations between the COVID-19 Pandemic and Hospital Infrastructure Adaptation and Planning-A Scoping Review

The SARS-CoV-2 pandemic has put unprecedented pressure on the hospital sector around the world. It has shown the importance of preparing and planning in the future for an outbreak that overwhelms every aspect of a hospital on a rapidly expanding scale. We conducted a scoping review to identify, map, and systemize existing knowledge about the relationships between COVID-19 and hospital infrastructure adaptation and capacity planning worldwide. We searched the Web of Science, Scopus, and PubMed and hand-searched gray papers published in English between December 2019 and December 2021. A total of 106 papers were included: 102 empirical studies and four technical reports. Empirical studies entailed five reviews, 40 studies focusing on hospital infrastructure adaptation and planning during the pandemics, and 57 studies on modeling the hospital capacity needed, measured mostly by the number of beds. The majority of studies were conducted in high-income countries and published within the first year of the pandemic. The strategies adopted by hospitals can be classified into short-term (repurposing medical and non-medical buildings, remote adjustments, and establishment of de novo structures) and long-term (architectural and engineering modifications, hospital networks, and digital approaches). More research is needed, focusing on specific strategies and the quality assessment of the evidence.

Statistical analysis of blood characteristics of COVID-19 patients and their survival or death prediction using machine learning algorithms

This study's main purpose is to provide helpful information using blood samples from COVID-19 patients as a non-medical approach for helping healthcare systems during the pandemic. Also, this paper aims to evaluate machine learning algorithms for predicting the survival or death of COVID-19 patients. We use a blood sample dataset of 306 infected patients in Wuhan, China, compiled by Tangji Hospital. The dataset consists of blood's clinical indicators and information about whether patients are recovering or not. The used methods include K-nearest neighbor (KNN), decision tree (DT), logistic regression (LR), support vector machine (SVM), random forest (RF), stochastic gradient descent (SGD), bagging classifier (BC), and adaptive boosting (AdaBoost). We compare the performance of machine learning algorithms using statistical hypothesis testing. The results show that the most critical feature is age, and there is a high correlation between LD and CRP, and leukocytes and CRP. Furthermore, RF, SVM, DT, AdaBoost, DT, and KNN outperform other machine learning algorithms in predicting the survival or death of COVID-19 patients.

The medical and societal impact of big data analytics and artificial intelligence applications in combating pandemics: A review focused on Covid-19

With Covid-19 impacting communities in different ways, research has increasingly turned to big data analytics (BDA) and artificial intelligence (AI) tools to track and monitor the virus's spread and its effect on humanity and the global economy. The purpose of this study is to conduct an in-depth literature review to identify how BDA and AI were involved in the management of Covid-19 (while considering diversity, equity, and inclusion (DEI)). The rigorous search resulted in a portfolio of 607 articles, retrieved from the Web of Science database, where content analysis has been conducted. This study identifies the BDA and AI applications developed to deal with the initial Covid-19 outbreak and the containment of the pandemic, along with their benefits for the social good. Moreover, this study reveals the DEI challenges related to these applications, ways to mitigate the concerns, and how to develop viable techniques to deal with similar crises in the future. The article pool recognized the high presence of machine learning (ML) and the role of mobile technology, social media and telemedicine in the use of BDA and AI during Covid-19. This study offers a collective insight into many of the key issues and underlying complexities affecting public health and society from Covid-19, and the solutions offered from information systems and technological perspectives.

Enhancing the prediction of hospitalization from a COVID-19 agent-based model: A Bayesian method for model parameter estimation

Agent-based models (ABMs) have become a common tool for estimating demand for hospital beds during the COVID-19 pandemic. A key parameter in these ABMs is the probability of hospitalization for agents with COVID-19. Many published COVID-19 ABMs use either single point or age-specific estimates of the probability of hospitalization for agents with COVID-19, omitting key factors: comorbidities and testing status (i.e., received vs. did not receive COVID-19 test). These omissions can inhibit interpretability, particularly by stakeholders seeking to use an ABM for transparent decision-making. We introduce a straightforward yet novel application of Bayes' theorem with inputs from aggregated hospital data to better incorporate these factors in an ABM. We update input parameters for a North Carolina COVID-19 ABM using this approach, demonstrate sensitivity to input data selections, and highlight the enhanced interpretability and accuracy of the method and the predictions. We propose that even in tumultuous scenarios with limited information like the early months of the COVID-19 pandemic, straightforward approaches like this one with discrete, attainable inputs can improve ABMs to better support stakeholders.

Review on COVID-19 diagnosis models based on machine learning and deep learning approaches

COVID-19 is the disease evoked by a new breed of coronavirus called the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Recently, COVID-19 has become a pandemic by infecting more than 152 million people in over 216 countries and territories. The exponential increase in the number of infections has rendered traditional diagnosis techniques inefficient. Therefore, many researchers have developed several intelligent techniques, such as deep learning (DL) and machine learning (ML), which can assist the healthcare sector in providing quick and precise COVID-19 diagnosis. Therefore, this paper provides a comprehensive review of the most recent DL and ML techniques for COVID-19 diagnosis. The studies are published from December 2019 until April 2021. In general, this paper includes more than 200 studies that have been carefully selected from several publishers, such as IEEE, Springer and Elsevier. We classify the research tracks into two categories: DL and ML and present COVID-19 public datasets established and extracted from different countries. The measures used to evaluate diagnosis methods are comparatively analysed and proper discussion is provided. In conclusion, for COVID-19 diagnosing and outbreak prediction, SVM is the most widely used machine learning mechanism, and CNN is the most widely used deep learning mechanism. Accuracy, sensitivity, and specificity are the most widely used measurements in previous studies. Finally, this review paper will guide the research community on the upcoming development of machine learning for COVID-19 and inspire their works for future development. This review paper will guide the research community on the upcoming development of ML and DL for COVID-19 and inspire their works for future development.

Clinical prediction system of complications among patients with COVID-19: A development and validation retrospective multicentre study during first wave of the pandemic

Clinical evidence suggests that some patients diagnosed with coronavirus disease 2019 (COVID-19) experience a variety of complications associated with significant morbidity, especially in severe cases during the initial spread of the pandemic. To support early interventions, we propose a machine learning system that predicts the risk of developing multiple complications. We processed data collected from 3,352 patient encounters admitted to 18 facilities between April 1 and April 30, 2020, in Abu Dhabi (AD), United Arab Emirates. Using data collected during the first 24 h of admission, we trained machine learning models to predict the risk of developing any of three complications after 24 h of admission. The complications include Secondary Bacterial Infection (SBI), Acute Kidney Injury (AKI), and Acute Respiratory Distress Syndrome (ARDS). The hospitals were grouped based on geographical proximity to assess the proposed system's learning generalizability, AD Middle region and AD Western & Eastern regions, A and B, respectively. The overall system includes a data filtering criterion, hyperparameter tuning, and model selection. In test set A, consisting of 587 patient encounters (mean age: 45.5), the system achieved a good area under the receiver operating curve (AUROC) for the prediction of SBI (0.902 AUROC), AKI (0.906 AUROC), and ARDS (0.854 AUROC). Similarly, in test set B, consisting of 225 patient encounters (mean age: 42.7), the system performed well for the prediction of SBI (0.859 AUROC), AKI (0.891 AUROC), and ARDS (0.827 AUROC). The performance results and feature importance analysis highlight the system's generalizability and interpretability. The findings illustrate how machine learning models can achieve a strong performance even when using a limited set of routine input variables. Since our proposed system is data-driven, we believe it can be easily repurposed for different outcomes considering the changes in COVID-19 variants over time.

Kaplan-Meier Type Survival Curves for COVID-19: A Health Data Based Decision-Making Tool

Countries are recording health information on the global spread of COVID-19 using different methods, sometimes changing the rules after a few days. All of them are publishing the number of new individuals infected, recovered and dead individuals, along with some supplementary material. These data are often recorded in a non-uniform manner and do not conform the standard definitions of these variables. In this paper we show that, using data from the first wave of the epidemic (February-June), Kaplan-Meier curves calculated with them could provide useful information on the dynamics of the disease in different countries. We developed our scheme based on the cumulative total number of infected, recovered and dead individuals provided by the countries. We present a robust and simple model to show certain characteristics of the evolution of the dynamic process, showing that the differences in evolution between countries are reflected in the corresponding Kaplan-Meier-type curves. We compare the curves obtained for the most affected countries at that time, with the corresponding interpretation of the properties that distinguish them. The model is revealed as a practical tool for countries in the management of the Healthcare System.

Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark

The COVID-19 pandemic has put massive strains on hospitals, and tools to guide hospital planners in resource allocation during the ebbs and flows of the pandemic are urgently needed. We investigate whether machine learning (ML) can be used for predictions of intensive care requirements a fixed number of days into the future. Retrospective design where health Records from 42,526 SARS-CoV-2 positive patients in Denmark was extracted. Random Forest (RF) models were trained to predict risk of ICU admission and use of mechanical ventilation after n days (n = 1, 2, …, 15). An extended analysis was provided for n = 5 and n = 10. Models predicted n-day risk of ICU admission with an area under the receiver operator characteristic curve (ROC-AUC) between 0.981 and 0.995, and n-day risk of use of ventilation with an ROC-AUC between 0.982 and 0.997. The corresponding n-day forecasting models predicted the needed ICU capacity with a coefficient of determination (R2) between 0.334 and 0.989 and use of ventilation with an R2 between 0.446 and 0.973. The forecasting models performed worst, when forecasting many days into the future (for large n). For n = 5, ICU capacity was predicted with ROC-AUC 0.990 and R2 0.928, and use of ventilator was predicted with ROC-AUC 0.994 and R2 0.854. Random Forest-based modelling can be used for accurate n-day forecasting predictions of ICU resource requirements, when n is not too large.

Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study

The COVID-19 pandemic has created an urgent need for robust, scalable monitoring tools supporting stratification of high-risk patients. This research aims to develop and validate prediction models, using the UK Biobank, to estimate COVID-19 mortality risk in confirmed cases. From the 11,245 participants testing positive for COVID-19, we develop a data-driven random forest classification model with excellent performance (AUC: 0.91), using baseline characteristics, pre-existing conditions, symptoms, and vital signs, such that the score could dynamically assess mortality risk with disease deterioration. We also identify several significant novel predictors of COVID-19 mortality with equivalent or greater predictive value than established high-risk comorbidities, such as detailed anthropometrics and prior acute kidney failure, urinary tract infection, and pneumonias. The model design and feature selection enables utility in outpatient settings. Possible applications include supporting individual-level risk profiling and monitoring disease progression across patients with COVID-19 at-scale, especially in hospital-at-home settings.