Intelligent healthcare informatics in big data era

Yang, Christopher C.; Veltri, Pierangelo

doi:10.1016/j.artmed.2015.08.002

Cited by 35 publications

(13 citation statements)

References 8 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, black box machine learning methods are typically more accurate for numerous applications because they do not make the assumptions that other methods, such as logistic regression, make when analyzing data. 9,12,42 Further, comparisons of different methodologies in predicting health outcomes have often revealed that black box learning methods outperform more traditional statistical techniques such as regression. 33,39 Consequently, machine learning methods are becoming increasingly useful and relevant across the healthcare industry and will likely become an important part of risk management, diagnosis, and the management of the everyday practice of medicine going forward.…”

Section: Discussionmentioning

confidence: 99%

Machine learning modeling for predicting hospital readmission following lumbar laminectomy

Kalagara¹,

Eltorai²,

Durand³

et al. 2019

Journal of Neurosurgery: Spine

View full text Add to dashboard Cite

OBJECTIVEHospital readmission contributes substantial costs to the healthcare system. The purpose of this investigation was to create a predictive machine learning model to identify lumbar laminectomy patients at risk for postoperative hospital readmission.METHODSPatients who had undergone a lumbar laminectomy procedure in the period from 2011 to 2014 were isolated from the American College of Surgeons National Surgical Quality Improvement Program (ACS NSQIP) database. Demographic characteristics and clinical factors, including complications, comorbidities, length of stay, age, and body mass index, were analyzed in relation to whether or not the patients had been readmitted to the hospital within 30 days after their procedure by utilizing independent-samples t-tests. Supervised gradient boosting machine learning was then used to create two models to predict readmission—one with all collected patient variables and one with only the variables known prior to hospital discharge.RESULTSA total of 26,869 patients were evaluated, 5.59% (1501 patients) of whom had an unplanned readmission to the hospital within 30 days of their procedure. Readmitted patients were older and had a greater number of complications and comorbidities, longer operative time, longer hospital stay, higher BMI, and higher work relative value unit (RVU) operation score (p < 0.01). They also had a worse health status prior to surgery (p < 0.01) and were more likely to be sent to a skilled discharge destination postoperatively (p < 0.01). The model with all patient variables accurately identified 49.6% of readmissions with an overall accuracy of 95.33% (area under the curve [AUC] = 0.8059), with postdischarge complications and comorbidities as the most important predictors. The predictive model built with only clinical information known predischarge identified 40.5% of readmitted patients with an accuracy of 79.55% (AUC = 0.6901), with discharge destination, comorbidities, and American Society of Anesthesiologists (ASA) classification as the most influential factors in identifying readmitted patients.CONCLUSIONSIn this study, the authors analyzed hospital readmissions following laminectomy and developed predictive models to identify readmitted patients with an accuracy of over 95% using all variables and over 79% when using only predischarge variables. Using only the variables available predischarge, the authors created a model capable of predicting 40% of the readmitted patients. This study provides data that will assist in the development of predictive models for readmission and the creation of interventions to prevent readmission in high-risk patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning modeling for predicting hospital readmission following lumbar laminectomy

Kalagara¹,

Eltorai²,

Durand³

et al. 2019

Journal of Neurosurgery: Spine

View full text Add to dashboard Cite

show abstract

“…erefore, developing big data-driven intelligent algorithms that automatically learn massive information from medical record pathological sections and image data to provide guidance for diagnosis and disease treatment and establish different disease models have become more crucial in the era of intelligent healthcare than in the past [28][29][30]. By extracting and structuring ICD-11-coded data and utilizing expert knowledge, such as ICD-11 and SNOMED CT, the algorithm with the use of ICD-11 could hold potential value for solving critical healthcare problems that cannot be solved by traditional ICD-10.…”

Section: Discussionmentioning

confidence: 99%

A Bibliometric Analysis of the Development of ICD-11 in Medical Informatics

Chen

Zhang

Zhao

et al. 2019

Journal of Healthcare Engineering

View full text Add to dashboard Cite

The International Classification of Diseases (ICD), which is used to group and report health conditions and factors, provides a basis for healthcare statistics. The 11th revision of the ICD (ICD-11) released by the World Health Organization provides stakeholders with novel perspectives on solving the complexity of critical problems in medical informatics. This study conducts a bibliometric analysis of research published over the period of 1989–2018 to examine the development of ICD-related research and its trends. First, over 4000 ICD-related papers spanning the 30-year period are retrieved from the Web of Science database. Then, based on the meta data of the selected papers, time trend analysis is performed to examine the development of different ICD revisions. Finally, the keywords and topics of these papers are analyzed and visualized using VOSViewer and CiteSpace. Our findings indicate that ICD-11-related research has grown rapidly in recent years compared with studies on ICD-9 and ICD-10. Moreover, the most popular research directions of ICD-11 include the topics psychiatry, psychology, information science, library science, and behavioral science. In terms of perspectives, information system-related research is more common than big data- and knowledge discovery-related work. However, the popularity of big data- and knowledge discovery-related developments has grown in recent years. The use of ICD-11 facilitates the development of medical informatics from the perspectives of information systems, big data, and knowledge discovery.

show abstract

“…The current situation of healthcare as an industry makes it no different. Electronic medical records are a source of big data which provide a tremendous amount of information extracted via various deep mining and deep learning techniques (33,35). Through predictive analysis, AI is expected to pave the path towards precision medicine.…”

Section: Predictive Analysismentioning

confidence: 99%

Artificial intelligence in service of medicine

El-Hassoun¹,

Maruscakova²,

Valaskova³

et al. 2019

BLL

View full text Add to dashboard Cite

The race to make the dream of artifi cial intelligence a reality comes parallel with the increasing struggle of health care systems to cope with information overload and translational pressure. It is clear that a shift in the way data is generated requires a shift in the way they are processed. This is where AI comes with great promises to solve the problem of volume versus applicability of information in science. In medicine, AI is showing exponential progress in the fi elds of predictive analysis and image recognition. These promises however, come with an intricate package of ethico-social, scientifi c and economic implications, towards which a reductionist approach leads to distorted and dramatic predictions. All this, in a time when the growing pressure on healthcare systems towards defensive medicine begs the question of the true need for AI for good medical practice. This article examines the concept and achievements of AI and attempts to offer a complex view on the realistic expectations from it in medicine, in the context of current practice (Ref. 38).

show abstract

Intelligent healthcare informatics in big data era

Cited by 35 publications

References 8 publications

Machine learning modeling for predicting hospital readmission following lumbar laminectomy

Machine learning modeling for predicting hospital readmission following lumbar laminectomy

A Bibliometric Analysis of the Development of ICD-11 in Medical Informatics

Artificial intelligence in service of medicine

Contact Info

Product

Resources

About