Digital pathology (DP) is no longer an unfamiliar term for pathologists, but it is still difficult for many pathologists to understand the engineering and mathematics concepts involved in DP. Computer-aided pathology (CAP) aids pathologists in diagnosis. However, some consider CAP a threat to the existence of pathologists and are skeptical of its clinical utility. Implementation of DP is very burdensome for pathologists because technical factors, impact on workflow, and information technology infrastructure must be considered. In this paper, various terms related to DP and computer-aided pathologic diagnosis are defined, current applications of DP are discussed, and various issues related to implementation of DP are outlined. The development of computer-aided pathologic diagnostic tools and their limitations are also discussed.

Objective Smartphones have become common, and problematic smartphone use (PSU) is increasing. Predictors of PSU should be identified to prevent it. Little is known about the role of content types of smartphone use as predictors of PSU. Therefore, we aimed to evaluate the predictors of two proposed concepts of PSU, namely habitual smartphone behavior (SB) and addictive SB, within the context of the application (app) categories.Methods We studied 1,039 smartphone users using online surveys conducted between January 2 and 31, 2019. We employed multiple regression analysis to identify the predictors of habitual and addictive SB. We controlled for sex and age (mean=39.20).Results Common predictors of habitual and addictive SB were the use of social networking services, games, entertainment apps, and average weekend smartphone usage time. The predictors of habitual SB were the use of web and lifestyle apps, weekly usage frequency, and sex (female) and the predictors of addictive SB were the use of shopping apps and sleep duration.Conclusion This study revealed the need to consider habitual and addictive SB in evaluating PSU. The predictors in terms of the content types of smartphone usage can be used to develop monitoring and prevention services for PSU.

Prostate cancer has a low mortality rate and requires persistent treatment; however, treatment decisions are challenging. Because prostate cancer is complex, the outcomes warrant thorough follow-up evaluation for appropriate treatment. Electronic health records (EHRs) do not present intuitive information. This study aimed to develop a Clinical Decision Support System (CDSS) for prognosis management of radical prostatectomy. We used data from 5,199 prostate cancer patients from three hospitals’ EHRs in South Korea, comprising laboratory results, surgery, medication, and radiation therapy. We used open source R for data preprocessing and development of web-based visualization system. We also used R for automatic calculation functionalities of two factors to visualize the data, e.g., Prostate-Specific Antigen Doubling Time (PSADT), and four Biochemical Recurrence (BCR) definitions: American Society of Therapeutic Radiology and Oncology (ASTRO), Phoenix, consecutive PSA > 0.2 ng/mL, and PSA > 0.2 ng/mL. We developed the Prostate Cancer Trajectory Map (PCT-Map) as a CDSS for intuitive visualization of serial data of PSA, testosterone, surgery, medication, radiation therapy, BCR, and PSADT. The PCT-Map comprises functionalities for BCR and PSADT and calculates and visualizes the newly added patient data automatically in a PCT-Map data format, thus optimizing the visualization of patient data and allowing clinicians to promptly access patient data to decide the appropriate treatment.

It is particularly desirable to predict castration-resistant prostate cancer (CRPC) in prostate cancer (PCa) patients, and this study aims to predict patients’ likely outcomes to support physicians’ decision-making. Serial data is collected from 1592 PCa patients, and a phased long short-term memory (phased-LSTM) model with a special module called a “time-gate” is used to process the irregularly sampled data sets. A synthetic minority oversampling technique is used to overcome the data imbalance between two patient groups: those with and without CRPC treatment. The phased-LSTM model is able to predict the CRPC outcome with an accuracy of 88.6% (precision-recall: 91.6%) using 120 days of data or 94.8% (precision-recall: 96.9%) using 360 days of data. The validation loss converged slowly with 120 days of data and quickly with 360 days of data. In both cases, the prediction model takes four epochs to build. The overall CPRC outcome prediction model using irregularly sampled serial medical data is accurate and can be used to support physicians’ decision-making, which saves time compared to cumbersome serial data reviews. This study can be extended to realize clinically meaningful prediction models.

Background: Since the COVID-19 outbreak, South Korea has been engaged in various efforts to overcome the pandemic. One of them is to provide app-based COVID-19–related services to the public. As the pandemic continues, a need for various apps has emerged, including COVID-19 apps that can support activities aimed at overcoming the COVID-19 pandemic. Objective: We aimed to determine which apps were considered the most necessary according to users and evaluate the current status of the development of COVID-19–related apps in South Korea. We also aimed to determine users’ acceptance and concerns related to using apps to support activities to combat COVID-19. Methods: We collected data from 1148 users from a web-based survey conducted between November 11 and December 6, 2020. Basic statistical analysis, multiple response analysis, and the Wilcoxon rank sum test were performed using R software. We then manually classified the current status of the development of COVID-19–related apps. Results: In total, 68.4% (785/1148) of the respondents showed high willingness to protect themselves from COVID-19 by using related apps. Users considered the epidemiological investigation app to be the most necessary app (709/1148, 61.8%) overall, followed by the self-management app for self-isolation (613/1148, 53.4%), self-route management app (605/1148, 52.7%), COVID-19 symptom management app (483/1148, 42.1%), COVID-19–related information provision app (339/1148, 29.5%), and mental health management app (270/1148, 23.5%). Despite the high intention to use these apps, users were also concerned about privacy issues and media exposure. Those who had an underlying disease and had experience using COVID-19–related apps showed significantly higher intentions to use those apps (P=.05 and P=.01, respectively). Conclusions: Targeting users is very important in order to design and develop the most necessary apps. Furthermore, to gain the public’s trust and make the apps available to as many people as possible, it is vital to develop diverse apps in which privacy protection is maximized.

There are many medical demands that still need to be resolved for prostate cancer (PCa), including better diagnosis and predictive medicine. For this to be accomplished, diverse medical data need to be integrated with the development of intelligent software (SW) based on various types of medical data. Various types of information technology have been used to address these medical demands of PCa. We initiated the PROstate Medical Intelligence System Enterprise-Clinical, Imaging, and Pathology (PROMISE CLIP) and a multicenter, big data study to develop PCa SW for patients with PCa and clinicians. We integrated the clinical data of 7257 patients, 610 patients’ imaging data, and 39,000 cores of pathology digital scanning data from four tertiary hospitals in South Korea. We developed the PROMISE CLIP registry based on integrated clinical, imaging, and pathology data. Related intelligent SW has been developed for helping patients and clinicians decide on the best treatment option. The PROMISE CLIP study directs guidelines for intelligent SW development to solve medical demands for PCa. The PROMISE CLIP registry plays an important role in advancing PCa research and care.