Toward Big Data Analytics

Cichosz, Simon Lebech; Johansen, Mette Dencker; Hejlesen, Ole

doi:10.1177/1932296815611680

Cited by 83 publications

(34 citation statements)

References 125 publications

(146 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These limitations are in line with other reviews that addressed the benefits of big data analytics for Diabetes type 1 and 2 and Alzheimer’s disease [25, 26].…”

Section: Discussionsupporting

confidence: 84%

Are big data analytics helpful in caring for multimorbid patients in general practice? - A scoping review

Waschkau¹,

Wilfling²,

Steinhäuser³

2019

BMC Fam Pract

View full text Add to dashboard Cite

Background The treatment of multimorbid patients is one crucial task in general practice as multimorbidity is highly prevalent in this setting. However, there is little evidence how to treat these patients and consequently there are but a few guidelines that focus primarily on multimorbidity. Big data analytics are defined as a method that obtains results for high volume data with high variety generated at high velocity. Yet, the explanatory power of these results is not completely understood. Nevertheless, addressing multimorbidity as a complex condition might be a promising field for big data analytics. The aim of this scoping review was to evaluate whether applying big data analytics on patient data does already contribute to the treatment of multimorbid patients in general practice. Methods In January 2018, a review searching the databases PubMed, The Cochrane Library, and Web of Science, using defined search terms for “big data analytics” and “multimorbidity”, supplemented by a search of grey literature with Google Scholar, was conducted. Studies were not filtered by type of study, publication year or language. Validity of studies was evaluated independently by two researchers. Results In total, 2392 records were identified for screening. After title and abstract screening, six articles were included in the full-text analysis. Of those articles, one reported on a model generated with big data techniques to help caring for one group of multimorbid patients. The other five articles dealt with the analysis of multimorbidity clusters. No article defined big data analytics explicitly. Conclusions Although the usage of the phrase “Big Data” is growing rapidly, there is nearly no practical use case for big data analysis techniques in the treatment of multimorbidity in general practice yet. Furthermore, in publications addressing big data analytics, the term is rarely defined. However, possible models and algorithms to address multimorbidity in the future are already published. Electronic supplementary material The online version of this article (10.1186/s12875-019-0928-5) contains supplementary material, which is available to authorized users.

show abstract

“…These limitations are in line with other reviews that addressed the benefits of big data analytics for Diabetes type 1 and 2 and Alzheimer’s disease [25, 26].…”

Section: Discussionsupporting

confidence: 84%

Are big data analytics helpful in caring for multimorbid patients in general practice? - A scoping review

Waschkau¹,

Wilfling²,

Steinhäuser³

2019

BMC Fam Pract

View full text Add to dashboard Cite

show abstract

“…To have high impact and be adopted on a broader scale, a prognostic model must be accepted and understood by clinicians. Prediction models developed through clinical-learning are traditionally better understood by clinicians than machine learning models 70 , while machine-learning models are challenging to evaluate and apply without a basic understanding of the underlying logic on which they are based 71 . A partial solution may be to incorporate a priori knowledge into machine-learning approaches 72 .…”

Section: Discussionmentioning

confidence: 99%

Clinical-learning versus machine-learning for transdiagnostic prediction of psychosis onset in individuals at-risk

et al. 2019

View full text Add to dashboard Cite

Predicting the onset of psychosis in individuals at-risk is based on robust prognostic model building methods including a priori clinical knowledge (also termed clinical-learning) to preselect predictors or machine-learning methods to select predictors automatically. To date, there is no empirical research comparing the prognostic accuracy of these two methods for the prediction of psychosis onset. In a first experiment, no improved performance was observed when machine-learning methods (LASSO and RIDGE) were applied—using the same predictors—to an individualised, transdiagnostic, clinically based, risk calculator previously developed on the basis of clinical-learning (predictors: age, gender, age by gender, ethnicity, ICD-10 diagnostic spectrum), and externally validated twice. In a second experiment, two refined versions of the published model which expanded the granularity of the ICD-10 diagnosis were introduced: ICD-10 diagnostic categories and ICD-10 diagnostic subdivisions. Although these refined versions showed an increase in apparent performance, their external performance was similar to the original model. In a third experiment, the three refined models were analysed under machine-learning and clinical-learning with a variable event per variable ratio (EPV). The best performing model under low EPVs was obtained through machine-learning approaches. The development of prognostic models on the basis of a priori clinical knowledge, large samples and adequate events per variable is a robust clinical prediction method to forecast psychosis onset in patients at-risk, and is comparable to machine-learning methods, which are more difficult to interpret and implement. Machine-learning methods should be preferred for high dimensional data when no a priori knowledge is available.

show abstract

“…For instance, taking advantage of patients' integrated data, dashboards to identify diabetic patients with poor glycaemic control and high risk of developing diabetes-related complications can be designed, e.g., by implementation of pattern recognition techniques and risk models [103]. Rich individual-level data will also allow the development of precision medicine applications, like personalized decision support systems and telemedicine services, with the aim of tailoring the patient's therapy around his personal needs.…”

Section: Integration Of Cgm Data With Other Data Sources: Towards Bigmentioning

confidence: 99%

Wearable Continuous Glucose Monitoring Sensors: A Revolution in Diabetes Treatment

et al. 2017

View full text Add to dashboard Cite

Worldwide, the number of people affected by diabetes is rapidly increasing due to aging populations and sedentary lifestyles, with the prospect of exceeding 500 million cases in 2030, resulting in one of the most challenging socio-health emergencies of the third millennium. Daily management of diabetes by patients relies on the capability of correctly measuring glucose concentration levels in the blood by using suitable sensors. In recent years, glucose monitoring has been revolutionized by the development of Continuous Glucose Monitoring (CGM) sensors, wearable non/minimally-invasive devices that measure glucose concentration by exploiting different physical principles, e.g., glucose-oxidase, fluorescence, or skin dielectric properties, and provide real-time measurements every 1-5 min. CGM opened new challenges in different disciplines, e.g., medicine, physics, electronics, chemistry, ergonomics, data/signal processing, and software development to mention but a few. This paper first makes an overview of wearable CGM sensor technologies, covering both commercial devices and research prototypes. Then, the role of CGM in the actual evolution of decision support systems for diabetes therapy is discussed. Finally, the paper presents new possible horizons for wearable CGM sensor applications and perspectives in terms of big data analytics for personalized and proactive medicine.

show abstract

Toward Big Data Analytics

Cited by 83 publications

References 125 publications

Are big data analytics helpful in caring for multimorbid patients in general practice? - A scoping review

Are big data analytics helpful in caring for multimorbid patients in general practice? - A scoping review

Clinical-learning versus machine-learning for transdiagnostic prediction of psychosis onset in individuals at-risk

Wearable Continuous Glucose Monitoring Sensors: A Revolution in Diabetes Treatment

Contact Info

Product

Resources

About