China
Africa
Explore chapters and articles related to this topic
Healthcare Analytics
Published in Qurban A. Memon, Shakeel Ahmed Khoja, Data Science, 2019
In today’s digital world, patient data is easily available in many forms, such as electronic health records, biomedical images, sensor data, genomic data, biomedical signals, data gathered from social media, and clinical text. Once the patient data is available, medical organizations need to not only store the patient data but also use the patient data to track key healthcare analytics metrics. The healthcare analytics metrics help clinicians to understand the effectiveness of patient treatments and to be more proactive when the patient treatment proves to be ineffective. Healthcare analytics will help clinicians to build individualized patient profiles that can accurately compute the likelihood of an individual patient to suffer from a medical complication or condition in the near future.
Big Data Application and Analytics in a Large-Scale Power System
Published in Ahmed F. Zobaa, Trevor J. Bihl, Big Data Analytics in Future Power Systems, 2018
Jeremy Lin, Elham Foruzan, Fernando H. Magnago
Health care analytics is also growing in importance, due to heath industry stakeholders’ thirst for information, the need to manage large and diverse data sets, increased competition and growing regulatory complexity. Innovations ranging from precision medicine to value-based care to population health management are also driving forces behind this. Value-based care relies on the foundation of robust data and analytics. The shift in the US health care system to value-based care is likely to demand significant analytic infrastructure investments and expansions across all health industry stakeholders interested in fully realizing and optimizing its value: health care providers and health systems, plans and payers, life sciences, and biopharma.
Big Data Analytics in Healthcare Data Processing
Published in Punit Gupta, Dinesh Kumar Saini, Rohit Verma, Healthcare Solutions Using Machine Learning and Informatics, 2023
Tanveer Ahmed, Rishav Singh, Ritika Singh
Veracity: Data veracity refers to the degree of certainty that a data interpretation is consistent [11]. Varied data sources have different levels of data reliability and dependability [12]. Unsupervised machine learning algorithms, on the other hand, are used in healthcare for automated machines to make decisions based on data which may be deceptive or useless [10].The purpose of healthcare analytics is to obtain useful information that can be used to make better decisions and provide better patient care.
A long short-term memory model for forecasting the surgical case volumes at a hospital
Published in IISE Transactions on Healthcare Systems Engineering, 2023
Hieu Bui, Sandra D. Ekşiog˜lu, Adria A. Villafranca, Joseph A. Sanford, Kevin W. Sexton
Most of the literature provides examples of time-series forecasting models being used to determine the expected number of emergency patients, surgical volume, patient flow, and demand for resources (Aravazhi, 2021). The most popular methods used in healthcare analytics are the auto-regressive integrated moving average (ARIMA), seasonal ARIMA (SARIMA), vector auto-regressive (VAR), VAR moving average (VARMA), etc. (Box et al., 2015; Ekström et al., 2015; Lütkepohl, 2006). The underlying assumption of these models is that the time series is a linear function of past values and random errors. However, ARIMA models fail to capture the nonlinear patterns often observed in time series from real-life problems, providing accurate forecasts only for a short period of time, etc. (Zhang, 2003). The aforementioned limitations have motivated researchers to develop and use machine learning (ML) and deep learning models for time series forecasting. Some of the algorithms used include support vector machine (SVM), artificial neural networks (ANN), convolutional neural networks (CNN), recurrent neural networks (RNN), long short-term memory network (LSTM), multilayer perceptron (MLP), etc. (Ahmed et al., 2010; Cui et al., 2016; Kaushik et al., 2020; Lipton et al., 2015; Pham et al., 2016; Widiasari et al., 2017; Zhao et al., 2017). Although these approaches show improvement over the statistical time-series techniques, their performance varies depending on the applications, especially in health care.
Routing and staffing in emergency departments: A multiclass queueing model with workload dependent service times
Published in IISE Transactions on Healthcare Systems Engineering, 2023
Siddhartha Nambiar, Maria E. Mayorga, Yunan Liu
In our work we consider team-based care; few analytical models for resource allocation in healthcare consider the fact that resources within units are partially shared, central resources. In general service systems, the use of pooled resources is related to the concept of “processor sharing” (Kleinrock, 1967). Processor sharing is a service policy where customers are all served simultaneously in a queueing system. Under processor sharing, each customer receives an equal fraction of the service capacity available. Sharing resources within a unit is an idea that is relatively new in healthcare analytics literature. Agor et al. (2017) developed a simulation model in which incoming patients are assigned to teams of providers of different skill levels. Mandelbaum et al. (2012) showed that based on empirical hospital data the Inverted-V queueing model best models patients spending time in units within a hospital. The Inverted-V model assumes that upon entering a queueing system, an agent (patient) is assigned to a “pool” of servers instead of being assigned to a single server. Several authors continued to build on this by proposing a variety of patient/customer routing algorithms in an Inverted-V queueing context (Almehdawe et al., 2013; Armony & Ward, 2010; Ward & Armony, 2013). In addition to considering pooled service, we model state-dependent service.
Differentiating patients with radiculopathy from chronic low back pain patients by single surface EMG parameter
Published in Automatika, 2018
S. Ostojić, S. Peharec, V. Srhoj-Egekher, M. Cifrek
The most dominant classification methods were different types of discriminant analysis [1–4,6,7,19,26]. There is no apparent explanation for this dominance or occasional use of linear regression [8,13]. As noticed by Peach and McGill [8], the drawback of discriminant analysis is inconsistent selection of input parameters which they attributed to overfitting of the data or not using the holdout group. The overfitting of the data leads to classification model that performs well on the training data but negatively impacts its ability to generalize, and omitting of holdout group for evaluation of the classification model does not provide objective insight into classification accuracy. There are other possible choices for classification methods from a vast range of machine learning techniques [30–32]. Among them, decision trees are used in medicine and health care applications over several decades [33], and they seem to represent prevalent algorithm for classification in healthcare analytics [34]. Since decision trees have not been used for sEMG-based classification between LBP and NLBP they are selected for implementation in this research.