China 
Africa 
Explore chapters and articles related to this topic
Emerging Perspectives of Virtual Reality Techniques
Published in Christopher M. Hayre, Dave J. Muller, Marcia J. Scherer, Virtual Reality in Health and Rehabilitation, 2020
The patient was a 73-year-old woman who had a history of right wrist trauma (secondary to a fall in 16 years prior) and multiple surgeries (including total wrist arthroplasty in four years prior with a recent revision in one year prior) who presented with chief complaints of right wrist/hand pain and loss of motion that resulted in increasing difficulty with functional mobility for the past several months. Her primary goal was to improve mobility, in particular as it related to her penmanship, which had been adversely affected since her surgeries. She had seen multiple rehabilitation specialists with only very limited effects. The patient's past medical history included rheumatoid arthritis; her past surgical history included right wrist/hand tendon repair; and contracture reduction. She was a retired teacher who enjoyed golfing and photography.
A Framework for Emergency Remote Care and Monitoring Using Internet of Things
Published in Sourav Banerjee, Chinmay Chakraborty, Kousik Dasgupta, Green Computing and Predictive Analytics for Healthcare, 2020
IoT is used here for connecting the hardware interface (mostly sensors for procuring data) to the storage and analytical tools by which prediction can be done and henceforth treatment can be processed. The conclusion can be drawn through disease analysis and proceedings could be carried out either through the patient’s past medical history or else by continuous or spontaneous physical abnormalities detected by the sensors placed on their body parts or nearby areas. Using the mobile app, the proposed system creates a notification about any emergency conditions of the patient when they cannot be taken to a help center, and hence a suggestion for emergency services could be provided as a remote service. Also, even if the patient remains far away from the treatment center, through the app the consultant can make the diagnosis and provide services to the patients. Thus, an emergency situation (critical health issues) or predicted problems for a patient can be provided through the system remotely.
Extraction of Medical Entities Using a Matrix-Based Pattern-Matching Method
Published in Himansu Das, Jitendra Kumar Rout, Suresh Chandra Moharana, Nilanjan Dey, Applied Intelligent Decision Making in Machine Learning, 2020
A massive number of research papers on disease treatment, prevention, and diagnostics have been published. The medical text data provide the origin of information for biomedical study and research. However, these research papers are scattered across a huge medical informatics literature which have been published by specialist doctors. It is difficult for doctors to read all of these publications and discover new knowledge. The need is to accumulate all the information in a single place so that the specialist doctor may obtain guiding information for the most effective treatment and prevention. Health care professionals keep patient details, such as their past medical history, signs and symptoms of diseases, tests and treatments, and medication, in clinical records like discharge summaries and patients’ prescriptions. These clinical records are in the form of unstructured or semi-structured texts. Extracting medical knowledge from an unstructured clinical dataset is a real challenge.
Predicting colorectal surgery readmission risk: a surgery-specific predictive model
Published in IISE Transactions on Healthcare Systems Engineering, 2023
Thomas Clark Howell, Stephanie Lumpkin, Nicole Chaumont
In colorectal surgery patients, our model outperformed well-validated models intended to predict 30-day readmissions by including more comprehensive data fields, fields which better represent the daily discharge decision by clinicians and designing a readmission risk model specific to a more homogenous patient population. Our optimal model was not developed with AIC or BIC, but rather p-value criteria, and maintained the most candidate variables. Our most reduced model developed by minimizing BIC included clinical factors specific to colorectal surgery and not included in the LACE index or HOSPITAL score and outperformed both despite having few variables. To be fair, we must note that our implementation of the HOSPITAL model was not as the authors described. Our dataset lacked sodium levels for enough patients to be included in the analysis, and rather than patients being discharged from an oncology service, we included the oncology variable of whether or not the patient had a past medical history of cancer. Even with those differences in our implementation, we still believe readmission risk models should be developed on representative patient populations with key clinical indicators of discharge readiness or readmission risk—it is difficult to successfully apply a broad model to a specific population.
Predicting The Risk of Fall in Community-Dwelling Older Adults in Iran
Published in Journal of Aging and Environment, 2023
Sahar Keyvanloo Shahrestanaki, Farshad Sharifi, Hooman Shahsavari, Fatemeh Ghonoodi, Ian Philp, Fatemeh Bahramnezhad, Elham Navab
Demographic information, such as age, sex, living arrangements, marital status, years of schooling, occupational status, and social support was collected. Moreover, some life style data, such as smoking, addiction, and alcohol use were gathered. History of consumption of medications and past medical history data (the history of physician diagnosis of stroke, heart failure, coronary artery disease, hypertension, diabetes mellitus, liver and kidney diseases, vertigo, and dementia) was gathered through interviews with the participants. Polypharmacy is defined as the use of several different medications by one patient at the same time (in this study, we defined it as the use of 5 or more medications) (Duerden et al., 2013; Halter et al., 2009). Besides, the history of admission to hospital was collected too. Moreover, the ESAY-Care subscale, POMA, PHQ-9, and Timed Up and Go were administered for the participants by trained research staffs.
Clinical Notes Mining for Post Discharge Mortality Prediction
Published in IETE Technical Review, 2022
Vineet Kumar, Rohit Bajpai, Ram Babu Roy
Wider adoption of Electronic Health Records (EHRs) in the hospital setting has given rise to a plethora of clinical data. EHR records patient demographic details, past medical history, periodic clinical measurements like patient vitals, test reports, medical interventions, and detailed clinical/nursing notes. Structured clinical (tabular) data contain a rich but incomplete picture of the patient. Clinical notes are recorded by attending nurses in free form textual format. Murdoch et al. [1] found out that EHR contains almost 80% of unstructured data. They contain rich information relevant to the patient’s response to treatment and illness trajectory as well. In order to identify high-risk patients, health systems must leverage text analytics to derive insights from free form clinical texts. Natural Language Processing (NLP) helps in interpretation of textual data. It can aid in information extraction, conversion of unstructured to structured data, document categorization, etc. However, due to their high free form nature utilizing these unstructured clinical descriptions (UCDs) in building clinical decision support systems is not much explored. Predicting post-discharge mortality is one of the major research areas in health informatics [2].