China
Africa
Explore chapters and articles related to this topic
Diagnosis and Prediction of Type-2 Chronic Kidney Disease Using Machine Learning Approaches
Published in Meenu Gupta, Rachna Jain, Arun Solanki, Fadi Al-Turjman, Cancer Prediction for Industrial IoT 4.0: A Machine Learning Perspective, 2021
Ritu Aggarwal, Prateek Thakral
For data mining, the knowledge-based and Decision Support System (DSS) is an important area to process or detect the various stages of data processing. In data processing, various methods could be used for feature selection. In the pre-processing stage, the data are taken from the UCI dataset that is the ML repository. The key feature is set to identify the large dataset for evaluation. With the help of CKD datasets, the useful data is extracted and transformed by using data mining or ML algorithms. This chapter is implemented on four ML algorithms: Random Forest, SVM, logistic regression, and decision tree. With the help of these classifiers, we could analyze the occurrence of CKD as shown in Figure 5.1. The following methodology is used to detect CKD.
Chemical injuries
Published in Jan de Boer, Marcel Dubouloz, Handbook of Disaster Medicine, 2020
In order to ensure effective and efficient emergency response, those medical authorities in charge of the emergency management must make decisions about countermeasures to be implemented. They must be able to conduct a quick balance of the various potential medical response strategies. Decision support systems (DSS) have been and are being developed to assist decision makers in selecting and implementing response plans28. The DSS does not replace the decision maker. A DSS is generally an automated system in the form of computer software and its components include registration of accident information, product/material information including health hazards and recommendations for rescue and medical personnel, topographic information with combined data on population density, transportation routes and special sites, hazard level and damage calculations, evaluation of different countermeasure strategies, operational information, and automatic emergency response actions28. However, handbooks, written procedures, protocols, maps and other paper material can provide very useful decision support28. Despite some disadvantages due to the need for maintenance, up-dating and training of these systems, a computerised DSS has substantial advantages. A large body of information is rapidly accessible, great quantities of data can be processed quickly and the results displayed in an orderly manner both in text and in image28.
Introduction
Published in A Stewart Whitley, Jan Dodgeon, Angela Meadows, Jane Cullingworth, Ken Holmes, Marcus Jackson, Graham Hoadley, Randeep Kumar Kulshrestha, Clark’s Procedures in Diagnostic Imaging: A System-Based Approach, 2020
A Stewart Whitley, Jan Dodgeon, Angela Meadows, Jane Cullingworth, Ken Holmes, Marcus Jackson, Graham Hoadley, Randeep Kumar Kulshrestha
DSS as deployed within imaging departments provides reporting staff with a choice of likely differential diagnosis based on the clinical request. This then aids the reporter in choosing the most likely diagnosis and also serves to provide well-formatted structured reports, allowing external (non-radiology) systems to ingest reporting data in a more machine accessible way (e.g. to trigger escalation systems in other departments when an unexpected cancer is reported).
How to assess the risks associated with the usage of a medical device based on predictive modeling: the case of an anemia control model certified as medical device
Published in Expert Review of Medical Devices, 2021
Carlo Barbieri, Luca Neri, Milena Chermisi, Elena Bolzoni, Isabella Cattinelli, Wolfgang Decker, Stefano Stuard, José D. Martín-Guerrero, Flavio Mari
This paper proposes a structured method exploiting inherent generalizing properties of ML algorithms to estimate credible AE probabilities for DSS from retrospective electronic health records. This approach exploits the abundance and convenience of retrospective data while guaranteeing the generalizability of results to the real-world use of the DSS. Our goal is to come up with a systematic way of estimating risks in medical devices that are based on ML. A standard way of assessing risks is to compute them as the combination of severity and probability of hazards; since severities are usually evaluated by clinicians, we focus on the probabilities of AEs, which are closely related to the performance of the model. Therefore, the proposed method evaluates the risks of possible hazards before the actual implementation of medical devices.
Home care service employees’ contribution to patient safety in clients with dementia who use dietary supplements: a Norwegian survey
Published in Scandinavian Journal of Primary Health Care, 2021
Hilde Risvoll, Frauke Musial, Marit Waaseth, Trude Giverhaug, Kjell Halvorsen
Up to 57% of persons with dementia use dietary supplements (DSs) [7–9]. The United States Dietary Supplements Health and Education Act (DSHEA) of 1994 defines a DS as a product meant to supplement the diet and includes vitamins, minerals, herbs, botanical products, amino acids, or dietary substances [10]. Generally, people use DSs to improve their health and wellbeing [11]. Although considered natural and safe by many, DSs can compromise health by causing adverse events and/or interact with ongoing PD treatment [12,13] and have also been associated with fatal outcomes [13]. Unapproved pharmaceutical drugs have been found in cognitive enhancement supplements [14]. No specific effect on dementia has been proven so far, even though some single studies may have shown promising results [15–18]. Clients with dementia are at particular risk because their cognitive problems may compromise the correct use of DSs and PDs [7]. Moreover, persons with dementia seldom disclose their DS use to health care personnel [9], leaving general practitioners (GPs) and other health care providers, such as home care services unaware of their use. Dementia symptoms reduce a person’s ability to administer both PDs and DSs correctly, and these clients may therefore need help to administer their PDs [5] and DSs [7].
Challenges in Using Big Data to Develop Decision Support Systems for Social Work in Germany
Published in Journal of Technology in Human Services, 2019
Diana Schneider, Udo Seelmeyer
Monnickendam and colleagues (2005, p. 22) research has focused on examining “the thinking processes that workers brought to bear on their use of the DSS.” Their findings underline that social workers use the DSS in various ways: On the one hand, when the cases are typical, they use DSS in a perfunctory manner. In such cases, the DSS cannot make a valuable contribution because they can draw on their own experiences and their greater familiarity with their everyday work. On the other hand, a DSS was useful in atypical cases in which the social workers were uncertain how to decide. In such cases, the recommendation given by the DSS was viewed as an aid to thinking and reflection. This result is neither new nor surprising (e.g., Dreyfus, Dreyfus, & Athanasiou, 1986). It has also been confirmed by Shiller and Strydom (2018, p. 413) who pointed out that their Family Assessment for Least Development Countries (FA-LDC) instrument helped social workers “to get a more comprehensive view.” It helped to “provide a sense of the wellbeing of the family, and serve as indicators for decision making in child protection services” (Shiller & Strydom, 2018, p. 409). In both studies, the DSS (or to be precise: the DSS and the instrument used to support the decision-making process of social workers) is similar to a so-called expert system. It is reasonable to assume that such a DSS is based on or similar to knowledge-based and/or evidence-based approaches. Therefore, the skepticism described previously toward systems that make recommendations based on data could be a typical phenomenon to be found in the hermeneutic approach to social work.