Hybrid Bayesian Network-Based Modeling: COVID-19-Pneumonia Case.

The primary goal of this paper is to develop an approach for predicting important clinical indicators, which can be used to improve treatment. Using mathematical predictive modeling algorithms, we examined the course of COVID-19-based pneumonia (CP) with inpatient treatment. Algorithms used include dynamic and ordinary Bayesian networks (OBN and DBN), popular ML algorithms, the state-of-the-art auto ML approach and our new hybrid method based on DBN and auto ML approaches. Predictive targets include treatment outcomes, length of stay, dynamics of disease severity indicators, and facts of prescribed drugs for different time intervals of observation. Models are validated using expert knowledge, current clinical recommendations, preceding research and classic predictive metrics. The characteristics of the best models are as follows: MAE of 3.6 days of predicting LOS (DBN plus FEDOT auto ML framework), 0.87 accuracy of predicting treatment outcome (OBN); 0.98 F1 score for predicting facts of prescribed drug (DBN). Moreover, the advantage of the proposed approach is Bayesian network-based interpretability, which is very important in the medical field. After the validation of other CP datasets for other hospitals, the proposed models can be used as part of the decision support systems for improving COVID-19-based pneumonia treatment. Another important finding is the significant differences between COVID-19 and non-COVID-19 pneumonia.

Three-stage intelligent support of clinical decision making for higher trust, validity, and explainability.

The paper presents a conceptual framework for building practically applicable clinical decision support systems (CDSSs) using data-driven (DD) predictive modelling. With the proposed framework we have tried to fill the gap between experimental CDSS implementations widely covered in the literature and solutions acceptable by physicians in daily practice. The framework is based on a three-stage approach where DD model definition is accomplished with practical norms referencing (scales, clinical recommendations, etc.) and explanation of the prediction results and recommendations. The approach is aimed at increasing the applicability of CDSSs based on DD models through better integration into decision context and higher explainability. The approach has been implemented in software solutions and tested within a case study in type 2 diabetes mellitus (T2DM) prediction, enabling us to improve known clinical scales (such as FINDRISK) while keeping the problem-specific reasoning interface similar to existing applications. A survey was performed to assess and investigate the acceptance level and provide insights on the influences of the introduced framework's element on physicians' behavior.

Assessing Acceptance Level of a Hybrid Clinical Decision Support Systems.

We present a user acceptance study of a clinical decision support system (CDSS) for Type 2 Diabetes Mellitus (T2DM) risk prediction. We focus on how a combination of data-driven and rule-based models influence the efficiency and acceptance by doctors. To evaluate the perceived usefulness, we randomly generated CDSS output in three different settings: Data-driven (DD) model output; DD model with a presence of known risk scale (FINDRISK); DD model with presence of risk scale and explanation of DD model. For each case, a physician was asked to answer 3 questions: if a doctor agrees with the result, if a doctor understands it, if the result is useful for the practice. We employed a Lankton's model to evaluate the user acceptance of the clinical decision support system. Our analysis has proved that without the presence of scales, a physician trust CDSS blindly. From the answers, we can conclude that interpretability plays an important role in accepting a CDSS.

Extraction of Temporal Structures for Clinical Events in Unlabeled Free-Text Electronic Health Records in Russian.

The important information about a patient is often stored in a free-form text to describe the events in the patient's medical history. In this work, we propose and evaluate a hybrid approach based on rules and syntactical analysis to normalise temporal expressions and assess uncertainty depending on the remoteness of the event. A dataset of 500 sentences was manually labelled to measure the accuracy. On this dataset, the accuracy of extracting temporal expressions is 95,5%, and the accuracy of normalization is 94%. The event extraction accuracy is 74.80%. The essential advantage of this work is the implementation of the considered approach for the non-English language where NLP tools are limited.

Machine Learning-Based Factor Analysis of Carbohydrate Metabolism Compensation for TDM2 Patients.

Type 2 diabetes is one of the most common chronic diseases in the world. World Diabetes Federation experts predict that the diabetes patients' number by 2035 will increase by 205 million to reach 592 million. For health care, this diabetes type is one of the highest priority problems. This disease is associated with many concomitant diseases leading to early disability and high cardiovascular risk. A severity disease indicator is the degree of carbohydrate metabolism compensation. Decompensated and subcompensated carbohydrate metabolism patients have increased cardiovascular risks. Therefore, it is important to be able to select the right therapy to control carbohydrate metabolism. In this study, we propose a new method for selecting the optimal therapy automatically. The method includes creating personal optimal therapies. This kind of therapy has the highest probability of compensating carbohydrate metabolism for a patient within a six-month. The method includes models for predicting the results of different therapies. It is based on data from the previous medical history and current medical indicators of patients. This method provides high-quality predictions and medical recommendations. Therefore, medical professionals can use this method as part of the Support and Decision-Making Systems for working with T2DM patients.

Simulation of patient flow in multiple healthcare units using process and data mining techniques for model identification.

INTRODUCTION: An approach to building a hybrid simulation of patient flow is introduced with a combination of data-driven methods for automation of model identification. The approach is described with a conceptual framework and basic methods for combination of different techniques. The implementation of the proposed approach for simulation of the acute coronary syndrome (ACS) was developed and used in an experimental study. METHODS: A combination of data, text, process mining techniques, and machine learning approaches for the analysis of electronic health records (EHRs) with discrete-event simulation (DES) and queueing theory for the simulation of patient flow was proposed. The performed analysis of EHRs for ACS patients enabled identification of several classes of clinical pathways (CPs) which were used to implement a more realistic simulation of the patient flow. The developed solution was implemented using Python libraries (SimPy, SciPy, and others). RESULTS: The proposed approach enables more a realistic and detailed simulation of the patient flow within a group of related departments. An experimental study shows an improved simulation of patient length of stay for ACS patient flow obtained from EHRs in Almazov National Medical Research Centre in Saint Petersburg, Russia. CONCLUSION: The proposed approach, methods, and solutions provide a conceptual, methodological, and programming framework for the implementation of a simulation of complex and diverse scenarios within a flow of patients for different purposes: decision making, training, management optimization, and others.