Background: Various machine learning (ML) models have been developed for the prediction of clinical outcomes, but there is missing evidence on their performance in clinical routine and external validation. Objectives: Our aim was to deploy and prospectively evaluate an already developed delirium prediction software in clinical routine of an external hospital. Methods: We compared updated ML models of the software and models re-trained with the external hospital’s data. The best models were deployed in clinical routine for one month, and risk predictions for all admitted patients were compared to the risk ratings of a senior physician. After using the software, clinicians completed a questionnaire assessing technology acceptance. Results: Re-trained models achieved a high discriminative performance (AUROC > 0.92). Compared to clinical risk ratings, the software achieved a sensitivity of 100.0% and a specificity of 90.6%. Usefulness, ease of use and output quality were rated positively by the users. Conclusion: A ML based delirium prediction software achieved a high discriminative performance and high technology acceptance at an external hospital using re-trained ML models.

Due to an ever-increasing amount of data generated in healthcare each day, healthcare professionals are more and more challenged with information. Predictive models based on machine learning algorithms can help to quickly identify patterns in clinical data. Requirements for data driven decision support systems for health and care (DS4H) are similar in many ways to applications in other domains. However, there are also various challenges which are specific to health and care settings. The present paper describes a) healthcare specific requirements for DS4H and b) how they were addressed in our Predictive Analytics Toolset for Health and care (PATH). PATH supports the following process: objective definition, data cleaning and pre-processing, feature engineering, evaluation, result visualization, interpretation and validation and deployment. The current state of the toolset already allows the user to switch between the various involved levels, i. e. raw data (ECG), pre-processed data (averaged heartbeat), extracted features (QT time), built models (to classify the ECG into a certain rhythm abnormality class) and outcome evaluation (e. g. a false positive case) and to assess the relevance of a given feature in the currently evaluated model as a whole and for the individual decision. This allows us to gain insights as a basis for improvements in the various steps from raw data to decisions.

In situations like the COVID-19 pandemic, healthcare systems are under enormous pressure as they can rapidly collapse under the burden of the crisis. Machine learning (ML) based risk models could lift the burden by identifying patients with a high risk of severe disease progression. Electronic Health Records (EHRs) provide crucial sources of information to develop these models because they rely on routinely collected healthcare data. However, EHR data is challenging for training ML models because it contains irregularly timestamped diagnosis, prescription, and procedure codes. For such data, transformer-based models are promising. We extended the previously published Med-BERT model by including age, sex, medications, quantitative clinical measures, and state information. After pre-training on approximately 988 million EHRs from 3.5 million patients, we developed models to predict Acute Respiratory Manifestations (ARM) risk using the medical history of 80,211 COVID-19 patients. Compared to Random Forests, XGBoost, and RETAIN, our transformer-based models more accurately forecast the risk of developing ARM after COVID-19 infection. We used Integrated Gradients and Bayesian networks to understand the link between the essential features of our model. Finally, we evaluated adapting our model to Austrian in-patient data. Our study highlights the promise of predictive transformer-based models for precision medicine.

Background: Patients with major adverse cardiovascular events (MACE) such as myocardial infarction or stroke suffer from frequent hospitalizations and have high mortality rates. By identifying patients at risk at an early stage, MACE can be prevented with the right interventions. Objectives: The aim of this study was to develop machine learning-based models for the 5-year risk prediction of MACE. Methods: The data used for modelling included electronic medical records of more than 128,000 patients including 29,262 patients with MACE. A feature selection based on filter and embedded methods resulted in 826 features for modelling. Different machine learning methods were used for modelling on the training data. Results: A random forest model achieved the best calibration and discriminative performance on a separate test data set with an AUROC of 0.88. Conclusion: The developed risk prediction models achieved an excellent performance in the test data. Future research is needed to determine the performance of these models and their clinical benefit in prospective settings.

Objectives: To identify the ways in which healthcare information and communication technologies can be improved to address the challenges raised by the COVID-19 pandemic. Methods: The study population included health informatics experts who had been involved with the planning, development and deployment of healthcare information and communication technologies in healthcare settings in response to the challenges presented by the COVID-19 pandemic. Data were collected via an online survey. A non-probability convenience sampling strategy was employed. Data were analyzed with content analysis. Results: A total of 65 participants from 16 countries responded to the conducted survey. The four major themes regarding recommended improvements identified from the content analysis included: improved technology availability, improved interoperability, intuitive user interfaces and adoption of standards of care. Respondents also identified several key healthcare information and communication technologies that can help to provide better healthcare to patients during the COVID-19 pandemic, including telehealth, advanced software, electronic health records, remote work technologies (e.g., remote desktop computer access), and clinical decision support tools. Conclusions: Our results help to identify several important healthcare information and communication technologies, recommended by health informatics experts, which can help to provide better care to patients during the COVID-19 pandemic. The results also highlight the need for improved interoperability, intuitive user interfaces and advocating the adoption of standards of care.