Abstract:
BACKGROUND:Accumulating evidence has linked environmental exposure, such as ambient air pollution and meteorological factors, to the development and severity of cardiovascular diseases (CVDs), resulting in increased healthcare demand. Effective prediction of demand for healthcare services, particularly those associated with peak events of CVDs, can be useful in optimizing the allocation of medical resources. However, few studies have attempted to adopt machine learning approaches with excellent predictive abilities to forecast the healthcare demand for CVDs. This study aims to develop and compare several machine learning models in predicting the peak demand days of CVDs admissions using the hospital admissions data, air quality data and meteorological data in Chengdu, China from 2015 to 2017. METHODS:Six machine learning algorithms, including logistic regression (LR), support vector machine (SVM), artificial neural network (ANN), random forest (RF), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM) were applied to build the predictive models with a unique feature set. The area under a receiver operating characteristic curve (AUC), logarithmic loss function, accuracy, sensitivity, specificity, precision, and F1 score were used to evaluate the predictive performances of the six models. RESULTS:The LightGBM model exhibited the highest AUC (0.940, 95% CI: 0.900-0.980), which was significantly higher than that of LR (0.842, 95% CI: 0.783-0.901), SVM (0.834, 95% CI: 0.774-0.894) and ANN (0.890, 95% CI: 0.836-0.944), but did not differ significantly from that of RF (0.926, 95% CI: 0.879-0.974) and XGBoost (0.930, 95% CI: 0.878-0.982). In addition, the LightGBM has the optimal logarithmic loss function (0.218), accuracy (91.3%), specificity (94.1%), precision (0.695), and F1 score (0.725). Feature importance identification indicated that the contribution rate of meteorological conditions and air pollutants for the prediction was 32 and 43%, respectively. CONCLUSION:This study suggests that ensemble learning models, especially the LightGBM model, can be used to effectively predict the peak events of CVDs admissions, and therefore could be a very useful decision-making tool for medical resource management.
journal_name
BMC Med Inform Decis Makjournal_title
BMC medical informatics and decision makingauthors
Qiu H,Luo L,Su Z,Zhou L,Wang L,Chen Ydoi
10.1186/s12911-020-1101-8subject
Has Abstractpub_date
2020-05-01 00:00:00pages
83issue
1issn
1472-6947pii
10.1186/s12911-020-1101-8journal_volume
20pub_type
杂志文章abstract:BACKGROUND:Approximately 20% of deaths in the US each year are attributable to smoking, yet current practices in the recording of this health risk in electronic health records (EHRs) have not led to discernable changes in health outcomes. Several groups have developed algorithms for extracting smoking behaviors from cl...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-019-0864-2
更新日期:2019-07-25 00:00:00
abstract:BACKGROUND:Although regulatory compliance in academic research is enforced by law to ensure high quality and safety to participants, its implementation is frequently hindered by cost and logistical barriers. In order to decrease these barriers, we have developed a Web-based application, Duke Surgery Research Central (D...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/1472-6947-6-32
更新日期:2006-07-27 00:00:00
abstract:BACKGROUND:The Kentucky Cancer Registry (KCR) is a central cancer registry for the state of Kentucky that receives data about incident cancer cases from all healthcare facilities in the state within 6 months of diagnosis. Similar to all other U.S. and Canadian cancer registries, KCR uses a data dictionary provided by t...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-020-01288-7
更新日期:2020-12-15 00:00:00
abstract:BACKGROUND:Electronic patient portals are increasingly being implemented, also in (haemato) oncology. However, portal usage is low and depends on user and provider engagement. We explored wishes, expectations and thoughts of patients with a haematologic malignancy and their physicians with regard to the electronic pati...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-019-0868-y
更新日期:2019-07-11 00:00:00
abstract:BACKGROUND:The storage and distribution of electrocardiogram data is based on different formats. There is a need to promote the development of standards for their exchange and analysis. Such models should be platform-/ system- and application-independent, flexible and open to every member of the scientific community. ...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/1472-6947-3-4
更新日期:2003-05-07 00:00:00
abstract:BACKGROUND:Quantitative electroencephalogram (EEG) is one neuroimaging technique that has been shown to differentiate patients with major depressive disorder (MDD) and non-depressed healthy volunteers (HV) at the group-level, but its diagnostic potential for detecting differences at the individual level has yet to be r...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-015-0227-6
更新日期:2015-12-23 00:00:00
abstract:BACKGROUND:The global age-adjusted mortality rate related to atrial fibrillation (AF) registered a rapid growth in the last four decades, i.e., from 0.8 to 1.6 and 0.9 to 1.7 per 100,000 for men and women during 1990-2010, respectively. In this context, this study uses convolutional neural networks for classifying (dia...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-019-0946-1
更新日期:2019-10-29 00:00:00
abstract:BACKGROUND:Efficient planning of hospital bed usage is a necessary condition to minimize the hospital costs. In the presented work we deal with the problem of occupancy forecasting in the scale of several months, with a focus on personnel's holiday planning. METHODS:We construct a model based on a set of recursive neu...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-019-0776-1
更新日期:2019-03-07 00:00:00
abstract:BACKGROUND:Preconception care may be an efficacious tool to reduce risk factors for adverse pregnancy outcomes that are associated with lifestyles and health status before pregnancy. We conducted a web-based cohort study in Italian women planning a pregnancy to assess whether a tailored web intervention may change know...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/1472-6947-14-33
更新日期:2014-04-15 00:00:00
abstract:BACKGROUND:Increased digitalization of healthcare comes along with the cost of cybercrime proliferation. This results to patients' and healthcare providers' skepticism to adopt Health Information Technologies (HIT). In Europe, this shortcoming hampers efficient cross-border health data exchange, which requires a holist...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-018-0664-0
更新日期:2018-10-16 00:00:00
abstract:BACKGROUND:Text mining and natural language processing of clinical text, such as notes from electronic health records, requires specific consideration of the specialized characteristics of these texts. Deep learning methods could potentially mitigate domain specific challenges such as limited access to in-domain tools ...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-019-0981-y
更新日期:2019-12-23 00:00:00
abstract:BACKGROUND:Emergency room reports pose specific challenges to natural language processing techniques. In this setting, violence episodes on women, elderly and children are often under-reported. Categorizing textual descriptions as containing violence-related injuries (V) vs. non-violence-related injuries (NV) is thus a...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-020-01237-4
更新日期:2020-10-15 00:00:00
abstract:BACKGROUND:Recent telehealth studies have demonstrated minor impact on patients affected by long-term conditions. The use of technology does not guarantee the compliance required for sustained collection of high-quality symptom and physiological data. Remote monitoring alone is not sufficient for successful disease man...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章,随机对照试验
doi:10.1186/s12911-017-0414-8
更新日期:2017-02-20 00:00:00
abstract:BACKGROUND:Medication events in clinical settings are significant threats to patient safety. Analyzing and learning from the medication event reports is an important way to prevent the recurrence of these events. Currently, the analysis of medication event reports is ineffective and requires heavy workloads for clinici...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-018-0687-6
更新日期:2018-12-07 00:00:00
abstract:BACKGROUND:We have carried out an extensive qualitative research program focused on the barriers and facilitators to successful adoption and use of various features of advanced, state-of-the-art electronic health records (EHRs) within large, academic, teaching facilities with long-standing EHR research and development ...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/1472-6947-11-13
更新日期:2011-02-17 00:00:00
abstract:BACKGROUND:Problems may arise during the approval process of treatment after a compensable work injury, which include excess paperwork, delays in approving services, disputes, and allegations of over-servicing. This is perceived as undesirable for injured people, health care professionals and claims managers, and costl...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-017-0460-2
更新日期:2017-05-22 00:00:00
abstract:BACKGROUND:The widespread use of electronic health records (EHRs) has generated massive clinical data storage. Association rules mining is a feasible technique to convert this large amount of data into usable knowledge for clinical decision making, research or billing. We present a data driven method to create a knowle...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-015-0151-9
更新日期:2015-04-15 00:00:00
abstract:BACKGROUND:Although a number of studies have evaluated the effectiveness of computerized decision-support systems (CDSS), there is lack of data on user perspectives, barriers, and facilitators to the implementation of CDSSs in real-life surroundings. The aim of this study was to assess individually perceived barriers, ...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-016-0245-z
更新日期:2016-01-22 00:00:00
abstract:BACKGROUND:Patient-reported Outcomes (PROs) capturing e.g., quality of life, fatigue, depression, medication side-effects or disease symptoms, have become important outcome parameters in medical research and daily clinical practice. Electronic PRO data capture (ePRO) with software packages to administer questionnaires,...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/1472-6947-12-126
更新日期:2012-11-09 00:00:00
abstract:BACKGROUND:A large body of work in the clinical guidelines field has identified requirements for guideline systems, but there are formidable challenges in translating such requirements into production-quality systems that can be used in routine patient care. Detailed analysis of requirements from an implementation pers...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/1472-6947-12-16
更新日期:2012-03-09 00:00:00
abstract:BACKGROUND:The purpose of this study was to assess the impact of accessing primary care records on unscheduled care. Unscheduled care is typically delivered in hospital Emergency Departments. Studies published to December 2014 reporting on primary care record access during unscheduled care were retrieved. RESULTS:Twen...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章,评审
doi:10.1186/s12911-017-0523-4
更新日期:2017-09-22 00:00:00
abstract:BACKGROUND:Biofuels produced from biomass are considered to be promising sustainable alternatives to fossil fuels. The conversion of lignocellulose into fermentable sugars for biofuels production requires the use of enzyme cocktails that can efficiently and economically hydrolyze lignocellulosic biomass. As many fungi ...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/1472-6947-12-S1-S5
更新日期:2012-04-30 00:00:00
abstract:BACKGROUND:Simulation applications on operations management in hospitals are frequently published and claim to support decision-making on operations management subjects. However, the reported implementation rates of recommendations are low and the actual impact of the changes recommended by the modeler has hardly been ...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章,评审
doi:10.1186/1472-6947-12-18
更新日期:2012-03-14 00:00:00
abstract:BACKGROUND:In 2006, we were funded by the US National Institutes of Health to implement a study of tuberculosis epidemiology in Peru. The study required a secure information system to manage data from a target goal of 16,000 subjects who needed to be followed for at least one year. With previous experience in the devel...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/1472-6947-12-125
更新日期:2012-11-07 00:00:00
abstract:BACKGROUND:Microcontact datasets gathered automatically by electronic devices have the potential augment the study of the spread of contagious disease by providing detailed representations of the study population's contact dynamics. However, the impact of data collection experimental design on the subsequent simulation...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/1472-6947-12-132
更新日期:2012-11-15 00:00:00
abstract:BACKGROUND:This study implemented and evaluated a point-of-care, wireless Internet access using smart phones for information retrieval during daily clinical rounds and academic activities of internal medicine residents in a community hospital. We did the project to assess the feasibility of using smart phones as an alt...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/1472-6947-7-5
更新日期:2007-02-21 00:00:00
abstract:BACKGROUND:Cognitive aids are increasingly recommended in clinical practice, yet little is known about the attitudes of physicians towards these tools. METHODS:We employed a qualitative, descriptive design to explore physician attitudes towards cognitive aids in pediatric intensive care units (PICUs). Semi-structured ...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-016-0291-6
更新日期:2016-05-21 00:00:00
abstract:BACKGROUND:Plain language search tools for MEDLINE/PubMed are few. We wanted to develop a search tool that would allow anyone using a free-text, natural language query and without knowing specialized vocabularies that an expert searcher might use, to find relevant citations in MEDLINE/PubMed. This tool would translate ...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/1472-6947-5-5
更新日期:2005-03-10 00:00:00
abstract:BACKGROUND:Clear communication about the possible outcomes of proposed medical interventions is an integral part of medical care. Despite its importance, there have been few studies comparing different formats for presenting probabilistic information to patients, especially when small probabilities are involved. The pu...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/1472-6947-8-14
更新日期:2008-04-10 00:00:00
abstract:BACKGROUND:Transient ischemic attack (TIA) is a brief episode of neurological dysfunction resulting from cerebral ischemia not associated with permanent cerebral infarction. TIA is associated with high diagnostic errors because of the subjective nature of findings and the lack of clinical and imaging biomarkers. The go...
journal_title:BMC medical informatics and decision making
pub_type: 杂志文章
doi:10.1186/s12911-020-01154-6
更新日期:2020-06-18 00:00:00