Journal of Healthcare Informatics Research最新文献

Early diagnosis of neurodegenerative diseases has always been a major challenge that physicians and medical practitioners face. Therefore, using any method or device that helps with prognostics is of great importance. In recent years, deep neural networks have become popular in medical fields, and the reason is that these networks can help diagnose diseases quickly and precisely. In this research, two novel models based on a CNN-LSTM network are introduced. The main goal is to classify three neurodegenerative diseases, including ALS, Parkinson's disease, and Huntington's disease, from one another and from healthy control patients using the gait signals, which are transformed into spectrogram images. In the first model, the spectrogram images derived from the gait signals are fed into a CNN-LSTM network directly. This model achieved 99.42% accuracy. In the second model, the same input data was used to be classified using a CNN-LSTM network, which uses wavelet transform as a feature extractor before the LSTM unit. During the experiments with the second model, the detail sub-bands were eliminated one by one, and the classification results were compared. Comparing these two models has shown that using the wavelet transform and, in particular, the approximation sub-bands can result in a lighter and faster prognosis with nearly 103 times fewer training parameters overall. The classification result using only approximation sub-bands was 95.37%, using three sub-bands was 94.04%, and including all sub-bands was 94.53%, which is remarkable.

Dementia and mild cognitive impairment can be underrecognized in primary care practice and research. Free-text fields in electronic medical records (EMRs) are a rich source of information which might support increased detection and enable a better understanding of populations at risk of dementia. We used natural language processing (NLP) to identify dementia-related features in EMRs and compared the performance of supervised machine learning models to classify patients with dementia. We assembled a cohort of primary care patients aged 66 + years in Ontario, Canada, from EMR notes collected until December 2016: 526 with dementia and 44,148 without dementia. We identified dementia-related features by applying published lists, clinician input, and NLP with word embeddings to free-text progress and consult notes and organized features into thematic groups. Using machine learning models, we compared the performance of features to detect dementia, overall and during time periods relative to dementia case ascertainment in health administrative databases. Over 900 dementia-related features were identified and grouped into eight themes (including symptoms, social, function, cognition). Using notes from all time periods, LASSO had the best performance (F1 score: 77.2%, sensitivity: 71.5%, specificity: 99.8%). Model performance was poor when notes written before case ascertainment were included (F1 score: 14.4%, sensitivity: 8.3%, specificity 99.9%) but improved as later notes were added. While similar models may eventually improve recognition of cognitive issues and dementia in primary care EMRs, our findings suggest that further research is needed to identify which additional EMR components might be useful to promote early detection of dementia.

Supplementary information: The online version contains supplementary material available at 10.1007/s41666-023-00125-6.

A novel approach of data augmentation based on irregular superpixel decomposition is proposed. This approach called SuperpixelGridMasks permits to extend original image datasets that are required by training stages of machine learning-related analysis architectures towards increasing their performances. Three variants named SuperpixelGridCut, SuperpixelGridMean, and SuperpixelGridMix are presented. These grid-based methods produce a new style of image transformations using the dropping and fusing of information. Extensive experiments using various image classification models as well as precision health and surrounding real-world datasets show that baseline performances can be significantly outperformed using our methods. The comparative study also shows that our methods can overpass the performances of other data augmentations. SuperpixelGridCut, SuperpixelGridMean, and SuperpixelGridMix codes are publicly available at https://github.com/hammoudiproject/SuperpixelGridMasks.

A foundational component of digital health involves collecting and leveraging electronic health data to improve health and wellbeing. One of the central technologies for collecting these data are electronic health records (EHRs). In this commentary, the authors explore intersection between digital health and data-driven reflective practice that is described, including an overview of the role of EHRs underpinning technology innovation in healthcare. Subsequently, they argue that EHRs are a rich but under-utilised source of information on the performance of health professionals and healthcare teams that could be harnessed to support reflective practice and behaviour change. EHRs currently act as systems of data collection, not systems of data engagement and reflection by end users such as health professionals and healthcare organisations. Further consideration should be given to supporting reflective practice by health professionals in the design of EHRs and other clinical information systems.

Venous thromboembolism (VTE) is a well-recognized complication that is prevalent in patients undergoing major orthopedic surgery (e.g., total hip arthroplasty and total knee arthroplasty). For years, to identify patients at high risk of developing VTE, physicians have relied on traditional risk scoring systems, which are too simplistic to capture the risk level accurately. In this paper, we propose a data-driven machine learning framework to identify such high-risk patients before they undergo a major hip or knee surgery. Using electronic health records of more than 392,000 patients who undergone a major orthopedic surgery, and following a guided feature selection using the genetic algorithm, we trained a fully connected deep neural network model to predict high-risk patients for developing VTE. We identified several risk factors for VTE that were not previously recognized. The best FCDNN model trained using the selected features yielded an area under the ROC curve (AUC) of 0.873, which was remarkably higher than the best AUC obtained by including only risk factors previously known in the medical literature. Our findings suggest several interesting and important insights. The traditional risk scoring tables that are being widely used by physicians to identify high-risk patients are not considering a comprehensive set of risk factors, nor are they as powerful as cutting-edge machine learning methods in distinguishing low- from high-risk patients.

With increasing numbers of people living with dementia, there is growing interest in the automatic monitoring of agitation. Current assessments rely on carer observations within a framework of behavioural scales. Automatic monitoring of agitation can supplement existing assessments, providing carers and clinicians with a greater understanding of the causes and extent of agitation. Despite agitation frequently manifesting in repetitive hand movements, the automatic assessment of repetitive hand movements remains a sparsely researched field. Monitoring hand movements is problematic due to the subtle differences between different types of hand movements and variations in how they can be carried out; the lack of training data creates additional challenges. This paper proposes a novel approach to assess the type and intensity of repetitive hand movements using skeletal model data derived from video. We introduce a video-based dataset of five repetitive hand movements symptomatic of agitation. Using skeletal keypoint locations extracted from video, we demonstrate a system to recognise repetitive hand movements using discriminative poses. By first learning characteristics of the movement, our system can accurately identify changes in the intensity of repetitive movements. Wide inter-subject variation in agitated behaviours suggests the benefit of personalising the recognition model with some end-user information. Our results suggest that data captured using a single conventional RGB video camera can be used to automatically monitor agitated hand movements of sedentary patients.

Evaluating appropriate methodologies for imputation of missing outcome data from electronic medical records (EMRs) is crucial but lacking for observational studies. Using US EMR in people with type 2 diabetes treated over 12 and 24 months with dipeptidyl peptidase 4 inhibitors (DPP-4i, n = 38,483) and glucagon-like peptide 1 receptor agonists (GLP-1RA, n = 8,977), predictors of missingness of disease biomarker (HbA1c) were explored. Robustness of multiple imputation (MI) by chained equations, two-fold MI (MI-2F) and MI with Monte Carlo Markov Chain were compared to complete case analyses for drawing inferences. Compared to younger people (age quartile Q1), those in age quartile Q3 and Q4 were less likely to have missing HbA1c by 25-32% (range of OR CI: 0.55-0.88) at 6-month follow-up and by 26-39% (range of OR CI: 0.50-0.80) at 12-month follow-up. People with HbA1c ≥ 7.5% at baseline were 12% (OR CI: 0.83, 0.93) and 14% (OR CI: 0.77, 0.97) less likely to have missing data at 6-month follow-up in the DPP-4i and GLP-1RA groups, respectively. All imputation methods provided similar HbA1c distributions during follow-up as observed with complete case analyses. The clinical inferences based on absolute change in HbA1c and by proportion of people reducing HbA1c to a clinically acceptable level (≤ 7%) were also similar between imputed data and complete case analyses. MI-2F method provided marginally smaller mean difference between observed and imputed data with relatively smaller standard error of difference, compared to other methods, while evaluating for consistency through artificial within-sample analyses. The established MI techniques can be reliably employed for missing outcome data imputations in large EMR-based relational databases, leading to efficiently designing and drawing robust clinical inferences in pharmaco-epidemiological studies.

Supplementary information: The online version contains supplementary material available at 10.1007/s41666-022-00119-w.

The use of machine learning (ML) and artificial intelligence (AI) applications in medicine has attracted a great deal of attention in the medical literature, but little is known about how to use Conformal Predictions (CP) to assess the accuracy of individual predictions in clinical applications. We performed a comprehensive search in SCOPUS® to find papers reporting the use of CP in clinical applications. We identified 14 papers reporting the use of CP for clinical applications, and we briefly describe the methods and results reported in these papers. The literature reviewed shows that CP methods can be used in clinical applications to provide important insight into the accuracy of individual predictions. Unfortunately, the review also shows that most of the studies have been performed in isolation, without input from practicing clinicians, not providing comparisons among different approaches and not considering important socio-technical considerations leading to clinical adoption.

Sensitivity analysis is an important aspect of model development as it can be used to assess the level of confidence that is associated with the outcomes of a study. In many practical problems, sensitivity analysis involves evaluating a large number of parameter combinations which may require an extensive amount of time and resources. However, such a computational burden can be avoided by identifying smaller subsets of parameter combinations that can be later used to generate the desired outcomes for other parameter combinations. In this study, we investigate machine learning-based approaches for speeding up the sensitivity analysis. Furthermore, we apply feature selection methods to identify the relative importance of quantitative model parameters in terms of their predictive ability on the outcomes. Finally, we highlight the effectiveness of active learning strategies in improving the sensitivity analysis processes by reducing the total number of quantitative model runs required to construct a high-performance prediction model. Our experiments on two datasets obtained from the sensitivity analysis performed for two disease screening modeling studies indicate that ensemble methods such as Random Forests and XGBoost consistently outperform other machine learning algorithms in the prediction task of the associated sensitivity analysis. In addition, we note that active learning can lead to significant speed-ups in sensitivity analysis by enabling the selection of more useful parameter combinations (i.e., instances) to be used for prediction models.

Telehealth helps to facilitate access to medical professionals by enabling remote medical services for the patients. These services have become gradually popular over the years with the advent of necessary technological infrastructure. The benefits of telehealth have been even more apparent since the beginning of the COVID-19 crisis, as people have become less inclined to visit doctors in person during the pandemic. In this paper, we focus on facilitating chat sessions between a doctor and a patient. We note that the quality and efficiency of the chat experience can be critical as the demand for telehealth services increases. Accordingly, we develop a smart auto-response generation mechanism for medical conversations that helps doctors respond to consultation requests efficiently, particularly during busy sessions. We explore over 900,000 anonymous, historical online messages between doctors and patients collected over 9 months. We implement clustering algorithms to identify the most frequent responses by doctors and manually label the data accordingly. We then train machine learning algorithms using this preprocessed data to generate the responses. The considered algorithm has two steps: a filtering (i.e., triggering) model to filter out infeasible patient messages and a response generator to suggest the top-3 doctor responses for the ones that successfully pass the triggering phase. Among the models utilized, BERT provides an accuracy of 85.41% for precision@3 and shows robustness to its parameters.