Deep Learning for Predictive Analytics in Healthcare

Muniasamy, Anandhavalli; Tabassam, Sehrish; Hussain, Mohammad A.; Sultana, Habeeba; Muniasamy, Vasanthi; Bhatnagar, Roheet

doi:10.1007/978-3-030-14118-9_4

Cited by 20 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…35 Deep learning can also contribute to predictive analytics, which uses statistical and analytical techniques that aim to predict future health-related outcomes based on patterns in data. 37,38 Predictive analytics can be used to develop health care models that can support clinical decisions by capturing characteristics of a specific event such as seizures, and then analyzing patient medical history and lifestyle, understanding genomics, and analyzing medical images. 37 When adolescents with epilepsy are reevaluated to ensure that their diagnosis is correct, deep learning techniques can be used to classify seizure types via the analysis of movement during seizures, wrist-worn accelerometer data and electrodermal activity, and medical imaging.…”

Section: Applications Of Deep Learning For Health Carementioning

confidence: 99%

“…37,38 Predictive analytics can be used to develop health care models that can support clinical decisions by capturing characteristics of a specific event such as seizures, and then analyzing patient medical history and lifestyle, understanding genomics, and analyzing medical images. 37 When adolescents with epilepsy are reevaluated to ensure that their diagnosis is correct, deep learning techniques can be used to classify seizure types via the analysis of movement during seizures, wrist-worn accelerometer data and electrodermal activity, and medical imaging. 39 The comprehensive view of clinically relevant and individual patient data can help support health care professionals treating adolescents with epilepsy by providing insight into the complexities and comorbidities of pediatric epilepsy with which they were previously unfamiliar.…”

Section: Applications Of Deep Learning For Health Carementioning

confidence: 99%

See 1 more Smart Citation

An Overview of Digital Health in the Transition of Pediatric to Adult Epilepsy Care

Bernard-Willis

Oliveira

Lakhan

2020

Journal of Pediatric Epilepsy

View full text Add to dashboard Cite

Children with epilepsy often have impairments in cognitive and behavioral functioning which may hinder socio-occupational well-being as they reach adulthood. Adolescents with epilepsy have the added worry of health problems while starting the transition from family-centered pediatric care into largely autonomous adult care. If this transition is not appropriately planned and resourced, it may result in medical mistrust, nonadherence, and worsening biopsychosocial health as an adult. In recent years, there has been increased availability of digital health solutions that may be used during this stark change in care and treating teams. The digital health landscape includes a wide variety of technologies meant to address challenges faced by patients, caregivers, medical professionals, and health care systems. These technologies include mobile health products and wearable devices (e.g., seizure monitors and trackers, smartphone passive data collection), digital therapeutics (e.g., cognitive/behavioral health management; digital speech–language therapy), telehealth services (e.g., teleneurology visits), and health information technology (e.g., electronic medical records with patient portals). Such digital health solutions may empower patients in their journey toward optimal brain health during the vulnerable period of pediatric to adult care transition. Further research is needed to validate and measure their impact on clinical outcomes, health economics, and quality of life.

show abstract

Section: Applications Of Deep Learning For Health Carementioning

confidence: 99%

Section: Applications Of Deep Learning For Health Carementioning

confidence: 99%

An Overview of Digital Health in the Transition of Pediatric to Adult Epilepsy Care

Bernard-Willis

Oliveira

Lakhan

2020

Journal of Pediatric Epilepsy

View full text Add to dashboard Cite

show abstract

“…Despite the fact that it is possible to gather a great amount of data and information from sensors, the data are often not possible to process or use. Rapidly developing areas of deep learning and predictive analysis have started to play a key role in healthcare development and research to understand patients’ feelings and needs if they are bedridden and are unable to communicate with the doctor in a standard way [68,69].…”

Section: Related Workmentioning

confidence: 99%

A Case Study of Facial Emotion Classification Using Affdex

Magdin

Benko

Koprda

2019

Sensors

View full text Add to dashboard Cite

This paper focuses on the analysis of reactions captured by the face analysis system. The experiment was conducted on a sample of 50 university students. Each student was shown 100 random images and the student´s reaction to every image was recorded. The recorded reactions were subsequently compared to the reaction of the image that was expected. The results of the experiment have shown several imperfections of the face analysis system. The system has difficulties classifying expressions and cannot detect and identify inner emotions that a person may experience when shown the image. Face analysis systems can only detect emotions that are expressed externally on a face by physiological changes in certain parts of the face.

show abstract

“…Machine learning (ML) has recently been adopted in a variety of medical problem solving or outcome predictions because it shows greater accuracy compared to conventional statistical methods due to its use of tremendous computational power [ 7 ]. Previous studies have focused on deep learning algorithms to predict CACS using chest CT, which has already shown promising results in image deep learning tasks [ 8 , 9 ]. Moreover, there have been a variety of ML algorithms to classify high and low risk for CVD more efficiently than the conventional logistic regression analysis [ 10 , 11 , 12 ].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Coronary Artery Calcium Score Using Machine Learning in a Healthy Population

Lee

Lim

Chu

et al. 2020

JPM

View full text Add to dashboard Cite

Background: Coronary artery calcium score (CACS) is a reliable predictor for future cardiovascular disease risk. Although deep learning studies using computed tomography (CT) images to predict CACS have been reported, no study has assessed the feasibility of machine learning (ML) algorithms to predict the CACS using clinical variables in a healthy general population. Therefore, we aimed to assess whether ML algorithms other than binary logistic regression (BLR) could predict high CACS in a healthy population with general health examination data. Methods: This retrospective observational study included participants who had regular health screening including coronary CT angiography. High CACS was defined by the Agatston score ≥ 100. Univariable and multivariable BLR was performed to assess predictors for high CACS in the entire dataset. When performing ML prediction for high CACS, the dataset was randomly divided into a training and test dataset with a 7:3 ratio. BLR, catboost, and xgboost algorithms with 5-fold cross-validation and grid search technique were used to find the best performing classifier. Performance comparison of each ML algorithm was evaluated with the area under the receiver operating characteristic (AUROC) curve. Results: A total of 2133 participants were included in the final analysis. Mean age and proportion of male sex were 55.4 ± 11.3 years and 1483 (69.5%), respectively. In multivariable BLR analysis, age (odds ratio [OR], 1.12; 95% confidence interval [CI], 1.10–1.15, p < 0.001), male sex (OR, 2.91; 95% CI, 1.57–5.38, p < 0.001), systolic blood pressure (OR, 1.02; 95% CI, 1.00–1.03, p = 0.019), and low-density lipoprotein cholesterol (OR, 1.00; 95% CI, 0.99–1.00, p = 0.047) were significant predictors for high CACS. Performance in predicting high CACS of xgboost was AUROC of 0.823, followed by catboost (0.750) and BLR (0.585). The comparison of AUROC between xgboost and BLR was significant (p for AUROC comparison < 0.001). Conclusions: Xgboost ML algorithm was found to be a more reliable predictor of CACS in healthy participants compared to the BLR algorithm. ML algorithms may be useful for predicting CACS with only laboratory data in healthy participants.

show abstract

Deep Learning for Predictive Analytics in Healthcare

Cited by 20 publications

References 27 publications

An Overview of Digital Health in the Transition of Pediatric to Adult Epilepsy Care

An Overview of Digital Health in the Transition of Pediatric to Adult Epilepsy Care

A Case Study of Facial Emotion Classification Using Affdex

Prediction of Coronary Artery Calcium Score Using Machine Learning in a Healthy Population

Contact Info

Product

Resources

About