A Comprehensive Review on Smart Decision Support Systems for Health Care

Moreira, Mário W. L.; Rodrigues, Joel J. P. C.; Korotaev, Valery V.; Al‐Muhtadi, Jalal; Kumar, Neeraj

doi:10.1109/jsyst.2018.2890121

Cited by 112 publications

(60 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the resent past, machine learning models are very popular to solve various problems like image classification [11], text processing [12], real-time fault diagnosis [13] and healthcare [14,15]. It is very common to use ML algorithms to address disease prediction [16,17] [18].…”

Section: Related Workmentioning

confidence: 99%

Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction

et al. 2020

View full text Add to dashboard Cite

Diabetic Retinopathy (DR) is one of the major causes of visual impairment and blindness across the world. It is usually found in patients who suffer from diabetes for a long period. Major focus of this work is to derive optimal representation of retinal images that further helps to improve the performance of DR recognition models. In order to extract optimal representation, features extracted from multiple pre-trained ConvNet models are blended using proposed multi-modal fusion module. These final representations are used to train a Deep Neural Network (DNN) used for DR identification and severity level prediction. As each ConvNet extract different features, fusing them using 1-D pooling, and cross pooling lead to better representation than using features extracted from a single ConvNet. Experimental studies on benchmark Kaggle APTOS 2019 contest dataset reveals that the model trained on proposed blended feature representations is superior to the existing methods. In addition, we notice that cross average pooling based fusion of features from Xception and VGG16 is the most appropriate for DR recognition. With the proposed model, we achieve an accuracy of 97.41%, and a kappa statistic of 94.82 for DR identification and an accuracy of 81.7% and a kappa statistic of 71.1% for severity level prediction. Another interesting observation is that, DNN with dropout at input layer converges faster when trained using blended features, than compared to the same model trained using uni-modal deep features.

show abstract

Section: Related Workmentioning

confidence: 99%

Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Although physical exercises are regarded as one of the most effective way to maintain the health condition of the elderly (both cognitive and physical), technology is only very recently catching up with solutions for intelligently suggest and monitor people performing exercises. Furthermore, exercise suggestion was just a guideline-based method, although currently these suggestion systems are being upgraded to encompass new features like sensor systems and artificial intelligence procedures, following the path of well known decision support systems applied in healthcare [9]. In this section, we present the most relevant projects and platforms in relation to ME 3 CA.…”

Section: Related Workmentioning

confidence: 99%

ME3CA: A Cognitive Assistant for Physical Exercises that Monitors Emotions and the Environment

Rincon

Costa

Nováis

et al. 2020

Sensors

View full text Add to dashboard Cite

Recent studies show that the elderly population has increased considerably in European society in recent years. This fact has led the European Union and many countries to propose new policies for caring services directed to this group. The current trend is to promote the care of the elderly in their own homes, thus avoiding inverting resources on residences. With this in mind, there are now new solutions in this direction, which try to make use of the continuous advances in computer science. This paper tries to advance in this area by proposing the use of a personal assistant to help older people at home while carrying out their daily activities. The proposed personal assistant is called ME3CA, and can be described as a cognitive assistant that offers users a personalised exercise plan for their rehabilitation. The system consists of a sensorisation platform along with decision-making algorithms paired with emotion detection models. ME3CA detects the users’ emotions, which are used in the decision-making process allowing for more precise suggestions and an accurate (and unbiased) knowledge about the users’ opinion towards each exercise.

show abstract

“…Studies show that most turn to the Web first when having a health-related query and that very few decide to talk directly to a health care provider instead [10], indicating that the Web now dominates as a first-line source of information. The Web has the potential to serve as a source of tailored and multimodal information that could aid in making healthrelated decisions through the dissemination of information and possibilities to promote interaction between health professionals and service users [11]. More specifically, high-quality and accessible web-based information could potentially help expectant parents decide whether or not to undergo the second trimester ultrasound examination [12].…”

Section: Introductionmentioning

confidence: 99%

Quality of consumer-oriented websites containing information about the second trimester ultrasound examination during pregnancy

Georgsson

Carlsson

2020

BMC Pregnancy Childbirth

View full text Add to dashboard Cite

Background: Providing information about prenatal tests is a clinical challenge and the public frequently accesses the Web to read pregnancy-related information. The overarching aim of this study was to investigate the quality of consumer-oriented websites addressing obstetric ultrasound examination in the second trimester of pregnancy. Methods: Swedish websites were identified with Google, using 20 search strings and screening 400 hits (n = 71 included websites). Reliability and information about the examination were assessed with the DISCERN instrument, completeness was assessed according to national guidelines, and readability analyzed with the Readability Index. Popularity was determined with the ALEXA tool and search rank was determined according to Google hit lists. Results: The mean total DISCERN score was 29.7/80 (SD 11.4), with > 50% having low quality for 15 of the 16 questions. The mean completeness score was 6.8/24 (SD 4.5). The Readability Index ranged between 22 and 63, with a mean of 42.7 (SD 6.8), indicating difficult readability. Weak and non-significant correlations were observed between ALEXA/search rank and the investigated quality variables, except for search rank and reliability.Conclusions: The quality of consumer-oriented websites addressing the second trimester ultrasound examination is low. Health professionals need to discuss this with expectant parents considering undergoing the examination. There is a need for efforts that aim to improve the poor quality of online sources in the field of prenatal examinations.

show abstract

A Comprehensive Review on Smart Decision Support Systems for Health Care

Cited by 112 publications

References 74 publications

Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction

Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction

ME3CA: A Cognitive Assistant for Physical Exercises that Monitors Emotions and the Environment

Quality of consumer-oriented websites containing information about the second trimester ultrasound examination during pregnancy

Contact Info

Product

Resources

About