Application of a Deep Learning System in Pterygium Grading and Further Prediction of Recurrence with Slit Lamp Photographs.

BACKGROUND: The aim of this study was to evaluate the efficacy of a deep learning system in pterygium grading and recurrence prediction. METHODS: This was a single center, retrospective study. Slit-lamp photographs, from patients with or without pterygium, were collected to develop an algorithm. Demographic data, including age, gender, laterality, grading, and pterygium area, recurrence, and surgical methods were recorded. Complex ocular surface diseases and pseudopterygium were excluded. Performance of the algorithm was evaluated by sensitivity, specificity, F1 score, accuracy, and area under the receiver operating characteristic curve. Confusion matrices and heatmaps were created to help explain the results. RESULTS: A total of 237 eyes were enrolled, of which 176 eyes had pterygium and 61 were non-pterygium eyes. The training set and testing set were comprised of 189 and 48 photographs, respectively. In pterygium grading, sensitivity, specificity, F1 score, and accuracy were 80% to 91.67%, 91.67% to 100%, 81.82% to 94.34%, and 86.67% to 91.67%, respectively. In the prediction model, our results showed sensitivity, specificity, positive predictive value, and negative predictive values were 66.67%, 81.82%, 33.33%, and 94.74%, respectively. CONCLUSIONS: Deep learning systems can be useful in pterygium grading based on slit lamp photographs. When clinical parameters involved in the prediction of pterygium recurrence were included, the algorithm showed higher specificity and negative predictive value in prediction.

The Usage Behavior and Intention Stability of Nurses: An Empirical Study of a Nursing Information System.

BACKGROUND: Many prior studies of technology adoption treat user intention as the single predictor of actual usage behavior. However, as many researchers of behavioral science have pointed out, multiple factors mediate the relationship between user intention and usage behavior. PURPOSE: The present article explores the factors that mediate the relationship between intention and actual behavior. We develop a conceptual framework that is based on the Technology Acceptance Model III and behavior theory to further elicit system usage behavior and to confirm "intention stability" and "past experience" as two significant mediating factors in this relationship. METHODS: The target system was a nursing information system that had been recently adopted by a medical center in central Taiwan. Data were collected using a questionnaire survey conducted in two rounds. Two hundred forty-five valid questionnaires were returned (response rate: 49%). Mediated moderation was analyzed to explore the presence of mediators or moderators between intention and behavior. RESULTS: The results support that intention stability is a mediated moderator and that prior experience is a moderator of the relationship between intention and behavior. These two factors increased by over 13.6% the explanatory power of intention on actual behavior. Furthermore, this study expanded the scope of prior research by confirming intention stability as a moderating variable between intention and behavior. Finally, this study identified the moderating effect of past experience on the intention-behavior relationship, indicating that past experience enhances the predictive power of intention on behavior. CONCLUSIONS/IMPLICATIONS FOR PRACTICE: The findings of this study may assist hospital managers to better understand the nursing information system usage behaviors of nursing staff and to develop ways to enhance the intention stability of these staff. Managers may improve the familiarity of nursing staff with the system by increasing their system-related practice time. More experience should enhance staff system skills and resolve problems such as the need for extra work hours or overtime because of initial system unfamiliarity. Improved work efficiency should then allow nurses to divert more time from administrative work to patient care and training. This positive circle of support is expected to increase the willingness of nurses to accept and take advantage of the system.

The application of data mining techniques to oral cancer prognosis.

This study adopted an integrated procedure that combines the clustering and classification features of data mining technology to determine the differences between the symptoms shown in past cases where patients died from or survived oral cancer. Two data mining tools, namely decision tree and artificial neural network, were used to analyze the historical cases of oral cancer, and their performance was compared with that of logistic regression, the popular statistical analysis tool. Both decision tree and artificial neural network models showed superiority to the traditional statistical model. However, as to clinician, the trees created by the decision tree models are relatively easier to interpret compared to that of the artificial neural network models. Cluster analysis also discovers that those stage 4 patients whose also possess the following four characteristics are having an extremely low survival rate: pN is N2b, level of RLNM is level I-III, AJCC-T is T4, and cells mutate situation (G) is moderate.

Barriers to physicians' adoption of healthcare information technology: an empirical study on multiple hospitals.

Prior research on technology usage had largely overlooked the issue of user resistance or barriers to technology acceptance. Prior research on the Electronic Medical Records had largely focused on technical issues but rarely on managerial issues. Such oversight prevented a better understanding of users' resistance to new technologies and the antecedents of technology rejection. Incorporating the enablers and the inhibitors of technology usage intention, this study explores physicians' reactions towards the electronic medical record. The main focus is on the barriers, perceived threat and perceived inequity. 115 physicians from 6 hospitals participated in the questionnaire survey. Structural Equation Modeling was employed to verify the measurement scale and research hypotheses. According to the results, perceived threat shows a direct and negative effect on perceived usefulness and behavioral intentions, as well as an indirect effect on behavioral intentions via perceived usefulness. Perceived inequity reveals a direct and positive effect on perceived threat, and it also shows a direct and negative effect on perceived usefulness. Besides, perceived inequity reveals an indirect effect on behavioral intentions via perceived usefulness with perceived threat as the inhibitor. The research finding presents a better insight into physicians' rejection and the antecedents of such outcome. For the healthcare industry understanding the factors contributing to physicians' technology acceptance is important as to ensure a smooth implementation of any new technology. The results of this study can also provide change managers reference to a smooth IT introduction into an organization. In addition, our proposed measurement scale can be applied as a diagnostic tool for them to better understand the status quo within their organizations and users' reactions to technology acceptance. By doing so, barriers to physicians' acceptance can be identified earlier and more effectively before leading to technology rejection.

Critical factors influencing hospitals' adoption of HL7 version 2 standards: an empirical investigation.

Industry predictions focus on future e-hospitals that will integrate all stakeholders into a seamless network, allowing data to be shared. The Health Level Seven (HL7) is a standard for the interchange of data within the healthcare industry. It simplifies communication interfaces and allows the interoperability among heterogeneous applications. Although the benefits of adopting HL7 are well known, only a few hospitals in Taiwan have actually adopted it. What are the reasons behind the hospitals' lack of intention to adopt HL7? Most prior studies on HL7 have focused on technical issues and general overlooked the managerial side. This has caused a lack of understanding of factors influencing hospitals' decision on HL7 adoption. In fact, main reasons behind a hospital's decision on whether to adopt an innovative technology are more often related to organizational than purely technical issues. Hence, we pay our attention to these organizational considerations over HL7 adoption. Based on the Innovation Diffusion Theory, we proposed a research model to explore the critical factors influencing Taiwan hospitals' adoption intention of HL7. 472 questionnaires were distributed to all accredited hospitals in Taiwan and 122 were returned. The valid response rate was 25.21% (119). Factor analysis, logistic regression and Pearson Chi-square test were conducted to verify the research model. The results showed that environmental pressure, top management attitude towards HL7, staff's technology capability, system integrity, and hospital's scale were critical factors influencing hospitals' intention on whether to adopt HL7. The research findings provided the government, the healthcare industry, the hospital administrators and the academia with practical and theoretical references. These factors should be considered in planning promotion plan to encourage hospital adoption of HL7. This study also opens up a new research direction as well as a new viewpoint, and consequentially improves the completeness of related researches in the medical informatics discipline.