Development of Mobile System for Medical Recommendations

Shakhovska, Nataliya; Федушко, Соломія; ml., Michal Greguš; Shvorob, Iryna; Syerov, Yuriy

doi:10.1016/j.procs.2019.08.010

Cited by 11 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the accuracy of the prediction results for these methods is not so high. Deep learning models allow to find hidden patterns too, but training time does not allow to use of these models in the real time [5].…”

Section: Introductionmentioning

confidence: 99%

An Ensemble Methods for Medical Insurance Costs Prediction Task

Shakhovska¹,

Melnykova²,

Chopiyak³

et al. 2022

Computers, Materials &Amp; Continua

Self Cite

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: Introductionmentioning

confidence: 99%

An Ensemble Methods for Medical Insurance Costs Prediction Task

Shakhovska¹,

Melnykova²,

Chopiyak³

et al. 2022

Computers, Materials &Amp; Continua

Self Cite

View full text Add to dashboard Cite

show abstract

“…Unfortunately, there are few published studies on the evaluation of M-medical APPs, let alone that of China. The previous research around M-medical APP focuses on the following areas: (a) the development or improvement of M-medical APP [2,4,[8][9][10]; (b) the attitudes of different groups to mobile medical technology or APP, including technical and medical students, working staff and healthcare professor [2]; (c) classification of M-medical APP and macro analysis of mobile medical industry [11,12]; (d) design or development of specific M-medical APP, such as in oncology [13], in Neurosurgery [14] and in chronic diseases [15]. Therefore, there is a pressing need for devising ways to evaluate the available M-medical APPs effectively.…”

Section: Int J Environ Res Public Health 2020 17 X 2 Of 29mentioning

confidence: 99%

“…; end for v end for i end for j end for k 4. According to Equation (7), w is calculated by dd 2 /(dd 1 ) T ; 5. for k, from 1 to h According to Equation (9), we get H k (X v ) of any alternative X v and give ranking T k ; end for k 6. for v, from 2 to n for i, from 1 to v-1 for k, from 1 to h taking Table 1 and T k to Equation (10) and calculating x iv end for k end for i end for v Output: group compromise ranking T From Table 2, it can be seen that the algorithm is composed of three loops, and correspondingly basic operation execution times are O(h × m × n 2 ), O(h × n 2 ) and O(h × n 2 ), respectively. Therefore, the time complexity of the algorithm is O(h × m × n 2 ).…”

Section: Umldm Algorithmmentioning

confidence: 99%

“…In this section, we calculate the ranking of 10 M-medical APPs for each expert based on from definitions 14 to 16, shown in Figure 7. The comprehensive deviation from attribute vector of each APPs to positive ideal point and negative ideal point, and alternative's closeness to positive ideal point are given in Appendix C. Finally, according to Equation (10) and Table 2, the group compromise ranking of 10 M-medical APPs is obtained:…”

Section: Comparison Analysismentioning

confidence: 99%

See 1 more Smart Citation

Uncertain Multiplicative Language Decision Method Based on Group Compromise Framework for Evaluation of Mobile Medical APPs in China

Zhang

Ding

2020

IJERPH

View full text Add to dashboard Cite

The mobile medical application (M-medical APP) can optimize medical service process and reduce health management costs for users, which has become an important complementary form of traditional medical services. To assist users including patients choose the ideal M-medical APP, we proposed a novel multiple attribute group decision making algorithm based on group compromise framework, which need not determine the weight of decision-maker. The algorithm utilized an uncertain multiplicative linguistic variable to measure the individual original preference to express the real evaluation information as much as possible. The attribute weight was calculated by maximizing the differences among alternatives. It determined the individual alternatives ranking according to the net flow of each alternative. By solved the 0–1 optimal model with the objective of minimizing the differences between individual ranking, the ultimate group compromise ranking was obtained. Then we took 10 well-known M-medical APPs in Chinese as an example, we summarized service categories provided for users and constructed the assessment system consisting of 8 indexes considering the service quality users are concerned with. Finally, the effectiveness and superiority of the proposed method and the consistency of ranking results were verified, through comparing the group ranking results of 3 similar algorithms. The experiments show that group compromise ranking is sensitive to attribute weight.

show abstract

“…Another drawback of CF technology is that it does not make full use of the available context information. In other words, context information, such as item attributes [1] or user profiles, is not considered when making recommendations.…”

Section: Introductionmentioning

confidence: 99%

A Joint Summarization and Pre-Trained Model for Review-Based Recommendation

Bai

Wang

2021

Information

View full text Add to dashboard Cite

Currently, reviews on the Internet contain abundant information about users and products, and this information is of great value to recommendation systems. As a result, review-based recommendations have begun to show their effectiveness and research value. Due to the accumulation of a large number of reviews, it has become very important to extract useful information from reviews. Automatic summarization can capture important information from a set of documents and present it in the form of a brief summary. Therefore, integrating automatic summarization into recommendation systems is a potential approach for solving this problem. Based on this idea, we propose a joint summarization and pre-trained recommendation model for review-based rate prediction. Through automatic summarization and a pre-trained language model, the overall recommendation model learns a fine-grained summary representation of the key content as well as the relationships between words and sentences in each review. The review summary representations of users and items are finally incorporated into a neural collaborative filtering (CF) framework with interactive attention mechanisms to predict the rating scores. We perform experiments on the Amazon dataset and compare our method with several competitive baselines. Experimental results show that the performance of the proposed model is obviously better than that of the baselines. Relative to the current best results, the average improvements obtained on four sub-datasets randomly selected from the Amazon dataset are approximately 3.29%.

show abstract

Development of Mobile System for Medical Recommendations

Cited by 11 publications

References 13 publications

An Ensemble Methods for Medical Insurance Costs Prediction Task

An Ensemble Methods for Medical Insurance Costs Prediction Task

Uncertain Multiplicative Language Decision Method Based on Group Compromise Framework for Evaluation of Mobile Medical APPs in China

A Joint Summarization and Pre-Trained Model for Review-Based Recommendation

Contact Info

Product

Resources

About