Search

Document classification is a widely used task for analyzing mental healthcare texts. This systematic literature review focuses on the document classification of electronic health records in mental healthcare. Over the last decade, there has been a shift from rule-based to machine-learning methods. Despite this shift, no systematic comparison of these two approaches exists for mental healthcare applications. This review examines the evolution, applications, and performance of these methods over time. We find that for most of the last decade, rule-based methods have outperformed machine-learning approaches. However, with the development of more advanced machine-learning techniques, performance has improved. In particular, Transformer-based models enable machine learning approaches to outperform rule-based methods for the first time.

Abstract Objective This paper presents a comprehensive analysis of perioperative patient deterioration by developing predictive models that evaluate unanticipated ICU admissions and in-hospital mortality both as distinct and combined outcomes. Materials and Methods With less than 1% of cases resulting in at least one of these outcomes, we investigated 98 features to identify their role in predicting patient deterioration, using univariate analyses. Additionally, multivariate analyses were performed by employing logistic regression (LR) with LASSO regularization. We also assessed classification models, including non-linear classifiers like Support Vector Machines, Random Forest, and XGBoost. Results During evaluation, careful attention was paid to the data imbalance therefore multiple evaluation metrics were used, which are less sensitive to imbalance. These metrics included the area under the receiver operating characteristics, precision-recall and kappa curves, and the precision, sensitivity, kappa, and F1-score. Combining unanticipated ICU admissions and mortality into a single outcome improved predictive performance overall. However, this led to reduced accuracy in predicting individual forms of deterioration, with LR showing the best performance for the combined prediction. Discussion The study underscores the significance of specific perioperative features in predicting patient deterioration, especially revealed by univariate analysis. Importantly, interpretable models like logistic regression outperformed complex classifiers, suggesting their practicality. Especially, when combined in an ensemble model for predicting multiple forms of deterioration. These findings were mostly limited by the large imbalance in data as post-operative deterioration is a rare occurrence. Future research should therefore focus on capturing more deterioration events and possibly extending validation to multi-center studies. Conclusions This work demonstrates the potential for accurate prediction of perioperative patient deterioration, highlighting the importance of several perioperative features and the practicality of interpretable models like logistic regression, and ensemble models for the prediction of several outcome types. In future clinical practice these data-driven prediction models might form the basis for post-operative risk stratification by providing an evidence-based assessment of risk.

Topic modeling is a prevalent task for discovering the latent structure of a corpus, identifying a set of topics that represent the underlying themes of the documents. Despite its popularity, issues with its evaluation metric, the coherence score, result in two common challenges: algorithm selection and determining the number of topics. To address these two issues, we propose the topic specificity metric, which captures the relative frequency of topic words in the corpus and is used as a proxy for the specificity of a word. In this work, we formulate the metric firstly. Secondly, we demonstrate that algorithms train topics at different specificity levels. This insight can be used to address algorithm selection as it allows users to distinguish and select algorithms with the desired specificity level. Lastly, we show a strictly positive monotonic correlation between the topic specificity and the number of topics for LDA, FLSA-W, NMF and LSI. This correlation can be used to address the selection of the number of topics, as it allows users to adjust the number of topics to their desired level. Moreover, our descriptive metric provides a new perspective to characterize topic models, allowing them to be understood better.

Abstract Background In the Diabetes domain, events such as meals and exercises play an important role in the disease management. For that, many studies focus on automatic meal detection, specially as part of the so-called artificial $$\beta$$ β -cell systems. Meals are associated to blood glucose (BG) variations, however such variations are not peculiar to meals, it mostly comes as a combination of external factors. Thus, general approaches such as the ones focused on glucose signal rate of change are not enough to detect personalized influence of such factors. By using a data-driven individualized approach for meal detection, our method is able to fit real data, detecting personalized meal responses even when such external factors are implicitly present. Methods The method is split into model training and selection. In the training phase, we start observing meal responses for each individual, and identifying personalized patterns. Occurrences of such patterns are searched over the BG signal, evaluating the similarity of each pattern to each possible signal subsequence. The most similar occurrences are then selected as possible meal event candidates. For that, we include steps for excluding less relevant neighbors per pattern, and grouping close occurrences in time globally. Each candidate is represented by a set of time and response signal related qualitative variables. These variables are used as input features for different binary classifiers in order to learn to classify a candidate as Meal or Non-Meal. In the model selection phase, we compare all trained classifiers to select the one that performs better with the data of each individual. Results The results show that the method is able to detect daily meals, providing a result with a balanced proportion between detected meals and false alarms. The analysis on multiple patients indicate that the approach achieves good outcomes when there is enough reliable training data, as this is reflected on the testing results. Conclusions The approach aims at personalizing the meal detection task by relying solely on data. The premise is that a model trained with data that contains the implicit influence of external factors is able to recognize the nuances of the individual that generated the data. Besides, the approach can also be used to improve data quality by detecting meals, opening opportunities to possible applications such as detecting and reminding users of missing or wrongly informed meal events.

Uncertainty is an essential feature of many concepts, data sets, and operations encountered in various applications related to computer science and engineering, and medical diagnostics. This paper introduces an extension to the Simpful library, enhancing it with capabilities for interval-valued fuzzy sets (IVFSs) and generalized fuzzy inference. Addressing the need for comprehensive uncertainty modeling in various applications, this extension offers intuitive definitions and operations for interval-valued fuzzy sets, facilitating advanced reasoning in uncertain environments.

Abstract Real time bidding is one of the most popular ways of selling impressions in online advertising, where online ad publishers allocate some blocks in their websites to sell in online auctions. In real time bidding, ad networks connect publishers and advertisers. There are many available ad networks for publishers to choose from. A possible approach for selecting ad networks and sending ad requests is called Waterfall Strategy, in which ad networks are selected sequentially. The ordering of the ad networks is very important for publishers, and finding the ordering that will provide maximum revenue is a hard problem due to the highly dynamic environment. In this paper, we propose a dynamic ad network ordering method to find the best ordering of ad networks for publishers that opt for Waterfall Strategy to select ad networks. This method consists of two steps. The first step is a prediction model that is trained on real time bidding historical data and provides an estimation of revenue for each impression. These estimations are used as initial values for the Q-table in the second step. The second step is based on Reinforcement Learning and improves the output of the prediction model. By calculating the revenue of our method and comparing that with the revenue of a fixed and predefined ordering method, we show that our proposed dynamic ad network ordering method increases publishers’ revenue.

Gathering diabetes-related data requires effort from the patient side to log specific events throughout experiments. This is an error-prone task that the patients usually handle by following a prescribed protocol. However, patients often do not follow the protocol, causing missing or imperfect data. This study investigates the possibility of generating Markov models from existing/logged data and using them for imputation. The models are used to infer information related to missing events (types/activities) in data recorded by diabetes patients, allowing for improvements in the quality and continuity of such data. Our results indicate that such an approach can help improve the quality of the data collected.

Abstract Background Tremor severity assessment is an important step for the diagnosis and treatment decision-making of essential tremor (ET) patients. Traditionally, tremor severity is assessed by using questionnaires (e.g., ETRS and QUEST surveys). In this work we assume the possibility of assessing tremor severity using sensor data and computerized analyses. The goal of this work is to assess severity of tremor objectively, to be better able to asses improvement in ET patients due to deep brain stimulation or other treatments. Methods We collect tremor data by strapping smartphones to the wrists of ET patients. The resulting raw sensor data is then pre-processed to remove any artifact due to patient’s intentional movement. Finally, this data is exploited to automatically build a transparent, interpretable, and succinct fuzzy model for the severity assessment of ET. For this purpose, we exploit pyFUME, a tool for the data-driven estimation of fuzzy models. It leverages the FST-PSO swarm intelligence meta-heuristic to identify optimal clusters in data, reducing the possibility of a premature convergence in local minima which would result in a sub-optimal model. pyFUME was also combined with GRABS, a novel methodology for the automatic simplification of fuzzy rules. Results Our model is able to assess tremor severity of patients suffering from Essential Tremor, notably without the need for subjective questionnaires nor interviews. The fuzzy model improves the mean absolute error (MAE) metric by 78–81% compared to linear models and by 71–74% compared to a model based on decision trees. Conclusion This study confirms that tremor data gathered using the smartphones is useful for the constructing of machine learning models that can be used to support the diagnosis and monitoring of patients who suffer from Essential Tremor. The model produced by our methodology is easy to inspect and, notably, characterized by a lower error with respect to approaches based on linear models or decision trees.

Nowadays organizations often need to employ data-driven techniques to audit their business processes and ensure they comply with laws and internal/external regulations. Failing in complying with the expected process behavior can indeed pave the way to inefficiencies or, worse, to frauds or abuses. An increasingly popular approach to automatically assess the compliance of the executions of organization processes is represented by alignment-based conformance checking. These techniques are able to compare real process executions with models representing the expected behaviors, providing diagnostics able to pinpoint possible discrepancies. However, the diagnostics generated by state of the art techniques still suffer from some limitations. They perform a crisp evaluation of process compliance, marking process behavior either as compliant or deviant, without taking into account the severity of the identified deviation. This hampers the accuracy of the obtained diagnostics and can lead to misleading results, especially in contexts where there is some tolerance with respect to violations of the process guidelines. In the present work, we discuss the impact and the drawbacks of a crisp deviation assessment approach. Then, we propose a novel conformance checking approach aimed at representing actors’ tolerance with respect to process deviations, taking it into account when assessing the severity of the deviations. As a proof of concept, we performed a set of synthetic experiments to assess the approach. The obtained results point out the potential of the usage of a more flexible evaluation of process deviations, and its impact on the quality and the interpretation of the obtained diagnostics.

Abstract Background The interpretability of results predicted by the machine learning models is vital, especially in the critical fields like healthcare. With the increasingly adoption of electronic healthcare records (EHR) by the medical organizations in the last decade, which accumulated abundant electronic patient data, neural networks or deep learning techniques are gradually being applied to clinical tasks by utilizing the huge potential of EHR data. However, typical deep learning models are black-boxes, which are not transparent and the prediction outcomes of which are difficult to interpret. Methods To remedy this limitation, we propose an attention neural network model for interpretable clinical prediction. In detail, the proposed model employs an attention mechanism to capture critical/essential features with their attention signals on the prediction results, such that the predictions generated by the neural network model can be interpretable. Results We evaluate our proposed model on a real-world clinical dataset consisting of 736 samples to predict readmissions for heart failure patients. The performance of the proposed model achieved 66.7 and 69.1% in terms of accuracy and AUC, respectively, and outperformed the baseline models. Besides, we displayed patient-specific attention weights, which can not only help clinicians understand the prediction outcomes, but also assist them to select individualized treatment strategies or intervention plans. Conclusions The experimental results demonstrate that the proposed model can improve both the prediction performance and interpretability by equipping the model with an attention mechanism.

The clinical notes in electronic health records have many possibilities for predictive tasks in text classification. The interpretability of these classification models for the clinical domain is critical for decision making. Using topic models for text classification of electronic health records for a predictive task allows for the use of topics as features, thus making the text classification more interpretable. However, selecting the most effective topic model is not trivial. In this work, we propose considerations for selecting a suitable topic model based on the predictive performance and interpretability measure for text classification. We compare 17 different topic models in terms of both interpretability and predictive performance in an inpatient violence prediction task using clinical notes. We find no correlation between interpretability and predictive performance. In addition, our results show that although no model outperforms the other models on both variables, our proposed fuzzy topic modeling algorithm (FLSA-W) performs best in most settings for interpretability, whereas two state-of-the-art methods (ProdLDA and LSI) achieve the best predictive performance.

Many researchers have used fuzzy set theory and fuzzy logic in a variety of applications related to computer science and engineering, given the capability of fuzzy inference systems to deal with uncertainty, represent vague concepts, and connect human language to numerical data. In this work we propose Simpful, a general-purpose and user-friendly Python library designed to facilitate the definition, analysis, and interpretation of fuzzy inference systems. Simpful provides a lightweight Application Programming Interface that allows to intuitively define fuzzy sets and fuzzy rules, and to perform fuzzy inference. Worthy of note, in Simpful the fuzzy rules are specified by means of strings of text written in natural language. We provide here some practical examples to show that Simpful represents a valuable addition to the open-source software that supports fuzzy reasoning.

Abstract Background Safety checklist is a type of cognitive tool enforcing short term memory of medical workers with the purpose of reducing medical errors caused by overlook and ignorance. To facilitate the daily use of safety checklists, computerized systems embedded in the clinical workflow and adapted to patient-context are increasingly developed. However, the current hard-coded approach of implementing checklists in these systems increase the cognitive efforts of clinical experts and coding efforts for informaticists. This is due to the lack of a formal representation format that is both understandable by clinical experts and executable by computer programs. Methods We developed a dynamic checklist meta-model with a three-step approach. Dynamic checklist modeling requirements were extracted by performing a domain analysis. Then, existing modeling approaches and tools were investigated with the purpose of reusing these languages. Finally, the meta-model was developed by eliciting domain concepts and their hierarchies. The feasibility of using the meta-model was validated by two case studies. The meta-model was mapped to specific modeling languages according to the requirements of hospitals. Results Using the proposed meta-model, a comprehensive coronary artery bypass graft peri-operative checklist set and a percutaneous coronary intervention peri-operative checklist set have been developed in a Dutch hospital and a Chinese hospital, respectively. The result shows that it is feasible to use the meta-model to facilitate the modeling and execution of dynamic checklists. Conclusions We proposed a novel meta-model for the dynamic checklist with the purpose of facilitating creating dynamic checklists. The meta-model is a framework of reusing existing modeling languages and tools to model dynamic checklists. The feasibility of using the meta-model is validated by implementing a use case in the system.

Machine Prognostics and Health Management (PHM) is often concerned with the prediction of the Remaining Useful Lifetime (RUL) of assets. Accurate real-time RUL predictions enable equipment health assessment and maintenance planning. In this work, we propose a Long Short-Term Memory (LSTM) network combined with global Attention mechanisms to learn RUL relationships directly from time-series sensor data. We use the NASA Commercial Modular Aero- Propulsion System Simulation (C-MAPPS) datasets to assess the performance of our proposed method. We compare our approach with current state-of-the-art methods on the same datasets and show that our results yield competitive results. Moreover, our method does not require previous degradation knowledge, and attention weights can be used to visualise temporal relationships between inputs and predicted outputs.

Purpose: : To develop a clinical prediction model to predict a clinically relevant adrenal disorder for patients with adrenal incidentaloma. Materials and methods: : This retrospective study is approved by the institutional review board, with waiver of informed consent. Natural language processing is used for filtering of adrenal incidentaloma cases in all thoracic and abdominal CT reports from 2010 till 2012. A total of 635 patients are identified. Stepwise logistic regression is used to construct the prediction model. The model predicts if a patient is at risk for malignancy or hormonal hyperfunction of the adrenal gland at the moment of initial presentation, thus generates a predicted probability for every individual patient. The prediction model is evaluated on its usefulness in clinical practice using decision curve analysis (DCA) based on different threshold probabilities. For patients whose predicted probability is lower than the predetermined threshold probability, further workup could be omitted. Results: : A prediction model is successfully developed, with an area under the curve (AUC) of 0.78. Results of the DCA indicate that up to 11% of patients with an adrenal incidentaloma can be avoided from unnecessary workup, with a sensitivity of 100% and specificity of 11%. Conclusion: : A prediction model can accurately predict if an adrenal incidentaloma patient is at risk for malignancy or hormonal hyperfunction of the adrenal gland based on initial imaging features and patient demographics. However, with most adrenal incidentalomas labeled as nonfunctional adrenocortical adenomas requiring no further treatment, it is likely that more patients could be omitting from unnecessary diagnostics. Keywords: Adrenal incidentaloma, Patient-specific workup, Prediction model

Emergency care in elderly patients has gained attention by researchers due to high utilization rate and the importance of emergency services in elderly care. We examine if there is a clear age threshold between young and old patients at which there is a need for extra care and facilities in the emergency department. This retrospective cohort study uses emergency department (ED) data collected over the course of a year, containing information about 31,491 patient visits. The measured variables are treatment time, waiting time, number of tests, number of medical procedures, number of specialties involved and the patient's length of stay on the ED. To examine the multivariate differences between different patient groups, the data set is split into eighteen age groups and a MANOVA analysis is conducted to compare group means. The results show that older patients tend to have a longer stay on the ED. They also require more medical tests, have higher resource utilization and admission rates to the hospital. When the patients are grouped according to life stages (