Challenges and opportunities of big data analytics in healthcare

Goyal, Priyanshi; Malviya, Rishabha

doi:10.1002/hcs2.66

Cited by 5 publications

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Development and validation of a spontaneous preterm birth risk prediction algorithm based on maternal bioinformatics: A single-center retrospective study

Chen,

Shi,

Wang

et al. 2024

BMC Pregnancy Childbirth

View full text Add to dashboard Cite

Background Spontaneous preterm birth (sPTB) is a primary cause of adverse neonatal outcomes. The objective of this study is to analyze the factors influencing the occurrence of sPTB in pregnant women and to construct and validate a predictive model for sPTB risk based on big data from clinical and laboratory assessments during pregnancy. Methods A retrospective analysis was conducted on the clinical data of 3,082 pregnant women, categorizing those who delivered before 37 weeks of gestation as the sPTB group and those who delivered at or after 37 weeks as the full-term group. The performance of five machine learning models was compared using metrics such as the AUC, accuracy, sensitivity, specificity, and precision to identify the optimal predictive model. The top 10 predictive variables were selected based on their significance in disease prediction. The data were then divided into a training set (70%) and a validation set (30%) for validation. External data were also utilized to validate the model's predictive performance. Results A total of 24 indicators with significant differences were identified. In terms of predicting the risk of preterm birth, the XGBoost algorithm demonstrated the most outstanding performance, with an AUC ROC of 0.89 (95% CI: 0.88–0.90). The top 10 critical indicators included ALP, AFP, ALB, HCT, TC, DBP, ALT, PLT, height, and SBP, which are essential for constructing an accurate predictive model. The model exhibited stable performance on both the training and validation sets, with AUC values of 0.93 and 0.87, respectively. Furthermore, the external testing set also showed superior performance, with an AUC of 0.79. Conclusions At the time of delivery, ALP, AFP, ALB, HCT, TC, DBP, ALT, PLT, height, and SBP are influential factors for sPTB in pregnant women. The XGBoost algorithm, constructed based on these factors, demonstrated the most outstanding performance.

show abstract

Development and validation of a spontaneous preterm birth risk prediction algorithm based on maternal bioinformatics: A single-center retrospective study

Chen,

Shi,

Wang

et al. 2024

BMC Pregnancy Childbirth

View full text Add to dashboard Cite

show abstract

The Impact of Big Data Analytics on Health Care: A Systematic Review

Akour,

Salloum

2024

Preprint

View full text Add to dashboard Cite

The extension of Big Data analytics to healthcare has radically altered how healthcare-related data is managed and used, presenting unequalled chances of augmenting patient experiences, boosting operational effectiveness, and customising treatment regimens. The prospective advantages of Big Data in medical fields have been ameliorated to a larger extent due to recent technological breakthroughs. Regardless of the noteworthy progress, an in-depth comprehension of the exact manner in which Big Data analytics improves numerous healthcare applications is lacking. The abrupt advancement of these technological innovations and their utilisation in the healthcare sector demands a revised amalgamation of the existing research patterns, approaches, and outcomes. In order to answer six particular research questions on Big Data analytics in healthcare, this comprehensive analysis examined 127 research articles that were released between 2015 and 2024. The evaluation used a methodically organised approach that included determining the parameters for inclusion and exclusion, data sources, search tactics, quality evaluation, and data coding and analysis. To facilitate a thorough and honest review procedure, the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) standards were applied. According to the research, the fields with the highest representation in the literary works include sleep apnoea monitoring, digital health records, and BDA healthcare applications and platforms. The machine learning algorithms that are most commonly used are supervised learning approaches, including Linear Regression and Support Vector Machines. A geographic study showed that China, India, and the United States have made substantial contributions. The temporal study revealed a substantial spike in research endeavours between 2020 and 2023, indicating heightened interest in the fusion of Big Data with the healthcare industry. The year 2024 witnessed an abrupt reduction in publications, indicating either a level of saturation or a shift in the focus of the study. The results highlight how Big Data analytics may redefine healthcare by improving operational effectiveness, individualised treatment regimens, and diagnostic accuracy. The report also emphasises the significance of having strong ethical standards and legal frameworks in place in order to cope with data security and privacy issues. Future studies should concentrate on investigating upcoming technologies, multidisciplinary approaches, flawless integration with current systems, and the lasting effects of these technologies. Furthermore, encouraging international cooperation can improve the exchange of resources and ideal practices, expanding the scope of Big Data healthcare analytics globally.

show abstract

Analysis of Hospital Length of Stay in Each Diagnostic -Related Groups (DRGs) Carried Out Using the Smart Hospital Research Application

Kozera,

Pikala,

Burzyńska

2024

Journal of Health Study and Medicine

View full text Add to dashboard Cite

Background The application of business intelligence (BI) tools in hospitals can enhance the quality and efficiency of care by providing insights into diagnostic, therapeutic, and business processes. BI tools aid in infection monitoring, clinical decision -making, and analysis of hospitalisation durations within Diagnostic-Related Groups (DRGs), identifying inefficiencies and optimizing resource use. Objectives This study aims to analyse hospital length of stay and identify the DRGs with the most inefficient hospitalization times using the BI -driven Smart Hospital application. Materials and methods The Smart Hospital application, developed on the Qlik Sense BI platform, analysed data from the National Health Fund (NFZ), Statistics Poland, e -health Centre (CEZ), and hospitalisations billed by DRG sections. The dataset included 20,376,405 hospitalisations from 2017–2019. Results The average length of stay (ALOS) was 6.2 days, with an effective length of stay (ELOS) of 4.33 days. Ineffective hospitalisation days totalled 30,307,086, accounting for 28.99% of all hospitalizations. The most inefficient DRGs were E53G (Cardiovascular failure), A48 (Complex stroke treatment), N01 (Childbirth), T07 (Trauma conservative treatment), and D28 (Respiratory and thoracic malignancies), contributing to about 14% of all ineffective hospital days. Conclusions Understanding the factors influencing hospitalisation durations in DRGs can improve patient flow management. Future research should compare treatment effectiveness concerning hospitalisation duration to develop optimal strategies for specific patient groups.

show abstract

Challenges and opportunities of big data analytics in healthcare

Cited by 5 publications

References 73 publications

Development and validation of a spontaneous preterm birth risk prediction algorithm based on maternal bioinformatics: A single-center retrospective study

Development and validation of a spontaneous preterm birth risk prediction algorithm based on maternal bioinformatics: A single-center retrospective study

The Impact of Big Data Analytics on Health Care: A Systematic Review

Analysis of Hospital Length of Stay in Each Diagnostic -Related Groups (DRGs) Carried Out Using the Smart Hospital Research Application

Contact Info

Product

Resources

About