Medical card data imputation and patient psychological and behavioral profile construction

Федушко, Соломія; ml., Michal Greguš; Ustyianovych, Taras

doi:10.1016/j.procs.2019.11.080

Cited by 11 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methods and systems for medical data analysis are given in [5][6][7][8][9]. The usage of artificial intelligence in the management of financial risks will enable economically wear time and money and save the health of patients.…”

Section: Literature Reviewmentioning

confidence: 99%

An Ensemble Methods for Medical Insurance Costs Prediction Task

Shakhovska¹,

Melnykova²,

Chopiyak³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

The paper reports three new ensembles of supervised learning predictors for managing medical insurance costs. The open dataset is used for data analysis methods development. The usage of artificial intelligence in the management of financial risks will facilitate economic wear time and money and protect patients' health. Machine learning is associated with many expectations, but its quality is determined by choosing a good algorithm and the proper steps to plan, develop, and implement the model. The paper aims to develop three new ensembles for individual insurance costs prediction to provide high prediction accuracy. Pierson coefficient and Boruta algorithm are used for feature selection. The boosting, stacking, and bagging ensembles are built. A comparison with existing machine learning algorithms is given. Boosting modes based on regression tree and stochastic gradient descent is built. Bagged CART and Random Forest algorithms are proposed. The boosting and stacking ensembles shown better accuracy than bagging. The tuning parameters for boosting do not allow to decrease the RMSE too. So, bagging shows its weakness in generalizing the prediction. The stacking is developed using K Nearest Neighbors (KNN), Support Vector Machine (SVM), Regression Tree, Linear Regression, Stochastic Gradient Boosting. The random forest (RF) algorithm is used to combine the predictions. One hundred trees are built for RF. Root Mean Square Error (RMSE) has lifted the to 3173.213 in comparison with other predictors. The quality of the developed ensemble for Root Mean Squared Error metric is 1.47 better than for the best weak predictor (SVR).

show abstract

Section: Literature Reviewmentioning

confidence: 99%

An Ensemble Methods for Medical Insurance Costs Prediction Task

Shakhovska¹,

Melnykova²,

Chopiyak³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…Therefore, perceived preparedness to implement a screening program in various cultures and settings (e.g., rural and urban), while comparing various healthcare providers (e.g., OB/GYNs, nurses, GPs) and forms of screening implementation (e.g., filling out an electronic screening measure vs. face-to-face screening) could shed light on differences in perceived preparedness to screen, intervene and refer in cases of PPD, as well as on differences in factors associated with such preparedness. In addition, as healthcare systems are increasingly implementing the use of new and innovative technologies (e.g., artificial intelligence), which could assist healthcare staff in their work, especially when dealing with large numbers of clients [ 53 , 54 ], and which could be used for PPD screening [ 55 ], examining the perceived preparedness of healthcare providers (e.g., PHNs) to use such techniques in the PPD screening process is of importance. These studies could contribute to gaining a more in-depth understanding of ways to enhance PHNs’ preparedness to implement a PPD screening program, and ultimately to achieving the most optimal program.…”

Section: Discussionmentioning

confidence: 99%

The Role of Organizational Factors in Nurses’ Perceived Preparedness to Screen, Intervene and Refer in Cases of Suspected Postpartum Depression

Bina

Glasser

Honovich

et al. 2022

IJERPH

View full text Add to dashboard Cite

Routine screening for postpartum depression (PPD) is widespread, yet little attention has been given to the perceived preparedness of health providers to perform screening procedures, or to the role of organizational factors in their preparedness, although these are crucial elements for optimal implementation. The aim of this study was to examine organizational factors associated with public health nurses’ (PHNs) perceived preparedness to screen women for PPD, intervene, and refer them in cases of suspected PPD. Two hundred and nineteen PHNs completed a self-report survey regarding their perceived preparedness to carry out a screening program (including screening, intervening, and referring women), and their perceived organizational support, supervisor’s support, colleagues’ support, and colleagues’ preparedness. A path analysis model was used to analyze the data. The results showed that perceived colleagues’ preparedness was significantly associated with the three perceived preparedness constructs (screen, intervene, and refer). Perceived supervisor’s support was positively associated with perceived preparedness to screen, and perceived organizational support was positively associated with perceived preparedness to intervene. This paper highlights the manner in which formal and informal organizational factors play an important role in the perceived preparedness of PHNs to carry out a PPD screening program, and how these factors impact the three different aspects of the screening program. Organizations implementing PPD screening should support PHNs in all aspects of the implementation process, provide guidance, and enhance peer-group continued learning through which PHNs could share knowledge, discuss barriers, and foster professional development.

show abstract

“…In parallel, the processes of building an Operational Intelligence solution must occur. This is required in order to provide data workflow monitoring, avoiding missing data and gaps [23], service reliability monitoring, and predict service downtime, information security, data privacy, quality and integrity checking; compute application performance specific metrics; implement system reliability engineering practices; and to prevent data and infrastructure issues. The next step after completing data engineering is analytics, data science, especially exploratory data analysis, statistical models' development and selecting the most accurate one that will be used.…”

Section: Operational Intelligence Analytics and Engineering In A Technology Data-based Projectmentioning

confidence: 99%

Real-Time High-Load Infrastructure Transaction Status Output Prediction Using Operational Intelligence and Big Data Technologies

2020

Self Cite

View full text Add to dashboard Cite

An approach to use Operational Intelligence with mathematical modeling and Machine Learning to solve industrial technology projects problems are very crucial for today’s IT (information technology) processes and operations, taking into account the exponential growth of information and the growing trend of Big Data-based projects. Monitoring and managing high-load data projects require new approaches to infrastructure, risk management, and data-driven decision support. Key difficulties that might arise when performing IT Operations are high error rates, unplanned downtimes, poor infrastructure KPIs and metrics. The methods used in the study include machine learning models, data preprocessing, missing data imputation, SRE (site reliability engineering) indicators computation, quantitative research, and a qualitative study of data project demands. A requirements analysis for the implementation of an Operational Intelligence solution with Machine learning capabilities has been conducted and represented in the study. A model based on machine learning algorithms for transaction status code and output predictions, in order to execute system load testing, risks identification and, to avoid downtimes, is developed. Metrics and indicators for determining infrastructure load are given in the paper to obtain Operational intelligence and Site reliability insights. It turned out that data mining among the set of Operational Big Data simplifies the task of getting an understanding of what is happening with requests within the data acquisition pipeline and helps identify errors before a user faces them. Transaction tracing in a distributed environment has been enhanced using machine learning and mathematical modelling. Additionally, a step-by-step algorithm for applying the application monitoring solution in a data-based project, especially when it is dealing with Big Data is described and proposed within the study.

show abstract

Medical card data imputation and patient psychological and behavioral profile construction

Cited by 11 publications

References 12 publications

An Ensemble Methods for Medical Insurance Costs Prediction Task

An Ensemble Methods for Medical Insurance Costs Prediction Task

The Role of Organizational Factors in Nurses’ Perceived Preparedness to Screen, Intervene and Refer in Cases of Suspected Postpartum Depression

Real-Time High-Load Infrastructure Transaction Status Output Prediction Using Operational Intelligence and Big Data Technologies

Contact Info

Product

Resources

About