Representation learning in intraoperative vital signs for heart failure risk prediction

Contactless face video based vital signs detection framework for continuous health monitoring using feature optimization and hybrid neural network

Continuous monitoring of vital signs such as respiration and heart rate is essential to detect and predict conditions that may affect the patient's well-being. To detect these vital signs most medical systems use contact sensors. They are not feasible for long term monitoring and are not repeatable. Vital signs using facial video-noncontact monitoring are becoming increasingly important. Researchers in the last few years although considerable progress has been made, challenging datasets absence timing of assessment process and the technology still has some limitations such as time consuming nature and lack of computer portability. To solve those problems, we propose a contactless video based vital signs detection framework for continuous health monitoring using feature optimization and hybrid neural network. In the proposed technique, modified war strategy optimization algorithm is proposed to segment the face portion from the input video frames. Then, we utilize the known data acquisition models to extract vital signs from the segmented face portions are heart rate, blood pressure, respiratory rate and oxygen saturation. An improved neural network structure (Lifting Net) is further used to achieve the adaptive extraction of deep hidden features for specific signs, for realizing the high precision of human health monitoring. The Hughes effect or dimensionality issue affects detection accuracy in sign classification when there are fewer training instances relative to the number of spectral features. The problem can be overcome through feature optimization here Northern goshawk optimization algorithm is used to select optimal best features which reduces the data dimensionality issue. Furthermore, hybrid deep ensemble reinforcement learning classifier is proposed for the human vital sign detection and classification which ensures the early detection of patient abnormality. Finally, we validate our framework using benchmark video datasets such as TokyoTechrPPG, PURE and COHFACE. To proves the effectiveness of proposed technique using simulation results and comparative analysis.

Knowledge-aware patient representation learning for multiple disease subtypes

Learning latent representations of patients with a target disease is a core problem in a broad range of downstream applications, such as clinical endpoint prediction. The suffering of patients may have multiple subtypes with certain similarities and differences, which need to be addressed for learning effective patient representation to facilitate the downstream tasks. However, existing studies either ignore the distinction of disease subtypes to learn disease-level representations, or neglect the correlations between subtypes and only learn disease subtype-level representations, which affects the performance of patient representation learning. To alleviate this problem, we studied how to effectively integrate data from all disease subtypes to improve the representation of each subtype. Specifically, we proposed a knowledge-aware shared-private neural network model to explicitly use disease-oriented knowledge and learn shared and specific representations from the disease and its subtype perspectives. To evaluate the feasibility of the proposed model, we conducted a particular downstream task, i.e., clinical endpoint prediction, on the basis of the learned patient presentations. The results on the real-world clinical datasets demonstrated that our model could yield a significant improvement over state-of-the-art models.

Analysis and risk estimation system for heart attack using EDENN algorithm

Heart related diseases are very common in the present scenario. In the past two decades the number of heart patients have increased to a large extent. Due to this abrupt rise in the number of patients, the death count has also increased. Thus, an efficient and accurate system must be developed for the diagnosis of heart related diseases, as the present methods available are not accurate enough and are insufficient for the Heart Attack (HA) and its Risk Analysis (RA). This paper propounds a system for HA risk estimation by the use of an Enhanced Deep Elman Neural Network (EDENN). In this system a Photoplethysmography (PPG) signal is inputted and pre-processed for noise removal. Further, Signal Decomposition (SD) is done, and the vital signs are estimated like Blood Pressure (BP), Respiratory Rate (RR) and Cardiac Autonomic Nervous System (CANS). For the BP estimation, Modified Maximum Amplitude Algorithm (MMAA) method is used and for the decomposed signal processing the Improved Incremental Merge Segmentation (IIMS) is used. As for features, Variation of amplitude, frequency and intensity are calculated and merged.

Intraoperative Hypotension Prediction Model Based on Systematic Feature Engineering and Machine Learning

Arterial hypotension is associated with incidence of postoperative complications, such as myocardial infarction or acute kidney injury. Little research has been conducted for the real-time prediction of hypotension, even though many studies have been performed to investigate the factors which affect hypotension events. This forecasting problem is quite challenging compared to diagnosis that detects high-risk patients at current. The forecasting problem that specifies when events occur is more challenging than the forecasting problem that does not specify the event time. In this work, we challenge the forecasting problem in 5 min advance. For that, we aim to build a systematic feature engineering method that is applicable regardless of vital sign species, as well as a machine learning model based on these features for real-time predictions 5 min before hypotension. The proposed feature extraction model includes statistical analysis, peak analysis, change analysis, and frequency analysis. After applying feature engineering on invasive blood pressure (IBP), we build a random forest model to differentiate a hypotension event from other normal samples. Our model yields an accuracy of 0.974, a precision of 0.904, and a recall of 0.511 for predicting hypotensive events.

Prediction of severe adverse event from vital signs for post-operative patients

Monitoring post-operative patients is important for preventing severe adverse events (SAE), which increases morbidity and mortality. Conventional bedside monitoring system has demonstrated the difficulty in long term monitoring of those patients because majority of them are ambulatory. With development of wearable system and advanced data analytics, those patients would benefit greatly from continuous and predictive monitoring. In this study, we aim to predict SAE based on monitoring of vital signs. Heart rate, respiration rate, and blood oxygen saturation were continuously acquired by wearable devices and blood pressure was measured intermittently from 453 post-operative patients. SAEs from various complications were extracted from patients' database. The trends of vital signs were first extracted with moving average. Then four descriptive statistics were calculated from trend of each modality as features. Finally, a machine learning approach based on support vector machine was employed for prediction of SAE. It has shown the averaged accuracy of 89%, sensitivity of 80%, specificity of 93% and the area under receiver operating characteristic curve (AUROC) of 93%. These findings are promising and demonstrate the feasibility of predicting SAE from vital signs acquired with wearable devices and measured intermittently.

A review of machine learning for cardiology

This paper reviews recent cardiology literature and reports how Artificial Intelligence Tools (specifically, Machine Learning techniques) are being used by physicians in the field. Each technique is introduced with enough details to allow the understanding of how it works and its intent, but without delving into details that do not add immediate benefits and require expertise in the field. We specifically focus on the principal Machine Learning based risk scores used in cardiovascular research. After introducing them and summarizing their assumptions and biases, we discuss their merits and shortcomings. We report on how frequently they are adopted in the field and suggest why this is the case based on our expertise in Machine Learning. We complete the analysis by reviewing how corresponding statistical approaches compare with them. Finally, we discuss the main open issues in applying Machine Learning tools to cardiology tasks, also drafting possible future directions. Despite the growing interest in these tools, we argue that there are many still underutilized techniques: while Neural Networks are slowly being incorporated in cardiovascular research, other important techniques such as Semi-Supervised Learning and Federated Learning are still underutilized. The former would allow practitioners to harness the information contained in large datasets that are only partially labeled, while the latter would foster collaboration between institutions allowing building larger and better models.