Camelia Delcea and Ioana-Alexandra Bradea
This study aims to analyze the major risk categories that could be encountered in hospitals and other medical facilities and attempts to determine which are more important from…
Abstract
Purpose
This study aims to analyze the major risk categories that could be encountered in hospitals and other medical facilities and attempts to determine which are more important from the patients’ perspective for the purpose of improving to the hospital–patient relationship improvement. For this, five main risk categories are identified along with an overall perceived risk.
Design/methodology/approach
To extract the patients’ opinion over the considered types of risks in terms of importance and exposure to these risks when using the medical services, a questionnaire has been created and validated using AMOS 22.0.0. Due to the validation process, a series of variables have been excluded, while the selected ones have been used for calculating the overall perceived risk. Having the values of this risk for the entire set of respondents (N = 304), the grey incidence analysis has been applied to determine whether there is a correlation between the overall perceived risk and the frequency of medical services usage, the disease gravity, the hospitalisation period or the healing degree.
Findings
The human resources and the hospital conditions risk has been mentioned as the main risk category encountered by the respondents when accessing the medical services both in term of importance and exposure, shortly followed by the technological and hospital conditions risk. The overall perceived risk has a moderate to high average value on the entire set of respondents and it is mostly related to the frequency to which the respondents are utilising the medical services.
Originality/value
In this paper, the hospital’s risks are analysed from the patients’ point of view to see both their perception over these risks and the importance they are giving to these risks. More, an overall perceived risk has been determined, with a moderate to high value on the Likert scale (on this data set), which can be useful if extended to each hospital (and not calculated as a general indicator), as it can provide a landmark for patients when choosing a hospital.
Details
Keywords
Camelia Delcea and Bradea Ioana-Alexandra
The identification of the main risk triggers is essential for the hospital’s survival and performance with direct effects on its patients’ health and well-being. For this reason…
Abstract
Purpose
The identification of the main risk triggers is essential for the hospital’s survival and performance with direct effects on its patients’ health and well-being. For this reason, in this paper some of the most important risk categories have been determined. While in a previous research a qualitative analysis has been done for determining which are the most important risks felt by the patient that are believed to affect their health through the usage of a questionnaire and through conducting a confirmatory factor analysis, the purpose of this paper is to analyze the quantitative side of these risks’ presence in a hospital.
Design/methodology/approach
On this purpose, four main categories of risks have been considered (the same as in the qualitative research) and they have been analyzed from the hospital’s point of view – through the usage of the hospital financial and internal documents. Therefore, a series of indicators have been determined for each risk category. After that, a representative indicator has been selected and the grey incidence analysis has been conducted.
Findings
By comparing the results gathered form this study with the qualitative analysis conducted among the patients (Delcea et al., 2016) it can be said that there can be seen a difference among the way a hospital and a patient perceive the risks within a medical activity. While for the hospital, the most affecting risk is the technological and hospital conditions risk, for the patients the most affecting risk seems to be the human resources and clinical risk. The mismanagement risk and inability to treat patients is the second in intensity for both the hospital and patients, with a smaller value in the patients’ case.
Practical implications
From here, the research can be extended for capturing the risks that are considered to be important for the medical stuff, which will permit us to have a global image over the healthcare risks. After that, a comparative analysis among the hospitals with different financial performance can be conducted in order to see how these risks are affecting their performance and to determine which can be the decisions that can fostering the reduction of these risks.
Originality/value
The present paper offers a quantitative analysis from the hospital’s point of view using the advantages offered by the grey systems theory. Combining this analysis with a qualitative one conducted on the patients, the managers of the hospital can a have a more adequate view over the risks that they are facing with. In this context, grey systems theory offers the needed methods for dealing with such situations.
Details
Keywords
Nor Hamizah Miswan, Chee Seng Chan and Chong Guan Ng
This paper develops a robust hospital readmission prediction framework by combining the feature selection algorithm and machine learning (ML) classifiers. The improved feature…
Abstract
Purpose
This paper develops a robust hospital readmission prediction framework by combining the feature selection algorithm and machine learning (ML) classifiers. The improved feature selection is proposed by considering the uncertainty in patient's attributes that leads to the output variable.
Design/methodology/approach
First, data preprocessing is conducted which includes how raw data is managed. Second, the impactful features are selected through feature selection process. It started with calculating the relational grade of each patient towards readmission using grey relational analysis (GRA) and the grade is used as the target values for feature selection. Then, the influenced features are selected using the Least Absolute Shrinkage and Selection Operator (LASSO) method. This proposed method is termed as Grey-LASSO feature selection. The final task is the readmission prediction using ML classifiers.
Findings
The proposed method offered good performances with a minimum feature subset up to 54–65% discarded features. Multi-Layer Perceptron with Grey-LASSO gave the best performance.
Research limitations/implications
The performance of Grey-LASSO is justified in two readmission datasets. Further research is required to examine the generalisability to other datasets.
Originality/value
In designing the feature selection algorithm, the selection on influenced input variables was based on the integration of GRA and LASSO. Specifically, GRA is a part of the grey system theory, which was employed to analyse the relation between systems under uncertain conditions. The LASSO approach was adopted due to its ability for sparse data representation.