Diagnostic Assessment of Deep Learning Algorithms for Frozen Tissue Section Analysis in Women with Breast Cancer / Journal of the Korean Cancer Association, 대한암학회지

Purpose@#Assessing the metastasis status of the sentinel lymph nodes (SLNs) for hematoxylin and eosin–stained frozen tissue sections by pathologists is an essential but tedious and time-consuming task that contributes to accurate breast cancer staging. This study aimed to review a challenge competition (HeLP 2019) for the development of automated solutions for classifying the metastasis status of breast cancer patients. @*Materials and Methods@#A total of 524 digital slides were obtained from frozen SLN sections: 297 (56.7%) from Asan Medical Center (AMC) and 227 (43.4%) from Seoul National University Bundang Hospital (SNUBH), South Korea. The slides were divided into training, development, and validation sets, where the development set comprised slides from both institutions and training and validation set included slides from only AMC and SNUBH, respectively. The algorithms were assessed for area under the receiver operating characteristic curve (AUC) and measurement of the longest metastatic tumor diameter. The final total scores were calculated as the mean of the two metrics, and the three teams with AUC values greater than 0.500 were selected for review and analysis in this study. @*Results@#The top three teams showed AUC values of 0.891, 0.809, and 0.736 and major axis prediction scores of 0.525, 0.459, and 0.387 for the validation set. The major factor that lowered the diagnostic accuracy was micro-metastasis. @*Conclusion@#In this challenge competition, accurate deep learning algorithms were developed that can be helpful for making a diagnosis on intraoperative SLN biopsy. The clinical utility of this approach was evaluated by including an external validation set from SNUBH.

Exploring the Category and Use Cases on Digital Therapeutic Methodologies / 대한의료정보학회지

Objectives@#As the Fourth Industrial Revolution advances, there is a growing interest in digital technology. In particular, the use of digital therapeutics (DTx) in healthcare is anticipated to reduce medical expenses. However, analytical research on DTx is still insufficient to fuel momentum for future DTx development. The purpose of this article is to analyze representative cases of different types of DTx from around the world and to propose a classification system. @*Methods@#In this exploratory study examining DTx interaction types and representative cases, we conducted a literature review and selected seven interaction types that were utilized in a large number of cases. Then, we evaluated the specific characteristics of each DTx mechanism by reviewing the relevant literature, analyzing their indications and treatment components. A representative case for each mechanism was provided. @*Results@#Cognitive behavioral therapy, distraction therapy, graded exposure therapy, reminiscence therapy, art therapy, therapeutic exercise, and gamification are the seven categories of DTx interaction types. Illustrative examples of each variety are provided. @*Conclusions@#Efforts from both the government and private sector are crucial for success, as standardization can decrease both the expense and the time required for government-led DTx development. The private sector should partner with medical facilities to stimulate potential demand, carry out clinical research, and produce scholarly evidence.

Review of Smart Hospital Services in Real Healthcare Environments / 대한의료정보학회지

Objectives@#Smart hospitals involve the application of recent information and communications technology (ICT) innovations to medical services; however, the concept of a smart hospital has not been rigorously defined. In this study, we aimed to derive the definition and service types of smart hospitals and investigate cases of each type. @*Methods@#A literature review was conducted regarding the background and technical characteristics of smart hospitals. On this basis, we conducted a focus group interview with experts in hospital information systems, and ultimately derived eight smart hospital service types. @*Results@#Smart hospital services can be classified into the following types: services based on location recognition and tracking technology that measures and monitors the location information of an object based on short-range communication technology; high-speed communication network-based services based on new wireless communication technology; Internet of Things-based services that connect objects embedded with sensors and communication functions to the internet; mobile health services such as mobile phones, tablets, and wearables; artificial intelligence-based services for the diagnosis and prediction of diseases; robot services provided on behalf of humans in various medical fields; extended reality services that apply hyper-realistic immersive technology to medical practice; and telehealth using ICT. @*Conclusions@#Smart hospitals can influence health and medical policies and create new medical value by defining and quantitatively measuring detailed indicators based on data collected from existing hospitals. Simultaneously, appropriate government incentives, consolidated interdisciplinary research, and active participation by industry are required to foster and facilitate smart hospitals.

Prediction of Neurological Outcomes in Out-of-hospital Cardiac Arrest Survivors Immediately after Return of Spontaneous Circulation: Ensemble Technique with Four Machine Learning Models

Background@#We performed this study to establish a prediction model for 1-year neurological outcomes in out-of-hospital cardiac arrest (OHCA) patients who achieved return of spontaneous circulation (ROSC) immediately after ROSC using machine learning methods. @*Methods@#We performed a retrospective analysis of an OHCA survivor registry. Patients aged ≥ 18 years were included. Study participants who had registered between March 31, 2013 and December 31, 2018 were divided into a develop dataset (80% of total) and an internal validation dataset (20% of total), and those who had registered between January 1, 2019 and December 31, 2019 were assigned to an external validation dataset. Four machine learning methods, including random forest, support vector machine, ElasticNet and extreme gradient boost, were implemented to establish prediction models with the develop dataset, and the ensemble technique was used to build the final prediction model. The prediction performance of the model in the internal validation and the external validation dataset was described with accuracy, area under the receiver-operating characteristic curve, area under the precision-recall curve, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Futhermore, we established multivariable logistic regression models with the develop set and compared prediction performance with the ensemble models. The primary outcome was an unfavorable 1-year neurological outcome. @*Results@#A total of 1,207 patients were included in the study. Among them, 631, 139, and 153were assigned to the develop, the internal validation and the external validation datasets, respectively. Prediction performance metrics for the ensemble prediction model in the internal validation dataset were as follows: accuracy, 0.9620 (95% confidence interval [CI],0.9352–0.9889); area under receiver-operator characteristics curve, 0.9800 (95% CI, 0.9612– 0.9988); area under precision-recall curve, 0.9950 (95% CI, 0.9860–1.0000); sensitivity, 0.9594 (95% CI, 0.9245–0.9943); specificity, 0.9714 (95% CI, 0.9162–1.0000); PPV, 0.9916 (95% CI, 0.9752–1.0000); NPV, 0.8718 (95% CI, 0.7669–0.9767). Prediction performance metrics for the model in the external validation dataset were as follows: accuracy, 0.8509 (95% CI, 0.7825–0.9192); area under receiver-operator characteristics curve, 0.9301 (95% CI, 0.8845–0.9756); area under precision-recall curve, 0.9476 (95% CI, 0.9087–0.9867); sensitivity, 0.9595 (95% CI, 0.9145–1.0000); specificity, 0.6500 (95% CI, 0.5022–0.7978); PPV, 0.8353 (95% CI, 0.7564–0.9142); NPV, 0.8966 (95% CI, 0.7857–1.0000). All the prediction metrics were higher in the ensemble models, except NPVs in both the internal and the external validation datasets. @*Conclusion@#We established an ensemble prediction model for prediction of unfavorable 1-year neurological outcomes in OHCA survivors using four machine learning methods. The prediction performance of the ensemble model was higher than the multivariable logistic regression model, while its performance was slightly decreased in the external validation dataset.

Prediction of Neurological Outcomes in Out-of-hospital Cardiac Arrest Survivors Immediately after Return of Spontaneous Circulation: Ensemble Technique with Four Machine Learning Models

Background@#We performed this study to establish a prediction model for 1-year neurological outcomes in out-of-hospital cardiac arrest (OHCA) patients who achieved return of spontaneous circulation (ROSC) immediately after ROSC using machine learning methods. @*Methods@#We performed a retrospective analysis of an OHCA survivor registry. Patients aged ≥ 18 years were included. Study participants who had registered between March 31, 2013 and December 31, 2018 were divided into a develop dataset (80% of total) and an internal validation dataset (20% of total), and those who had registered between January 1, 2019 and December 31, 2019 were assigned to an external validation dataset. Four machine learning methods, including random forest, support vector machine, ElasticNet and extreme gradient boost, were implemented to establish prediction models with the develop dataset, and the ensemble technique was used to build the final prediction model. The prediction performance of the model in the internal validation and the external validation dataset was described with accuracy, area under the receiver-operating characteristic curve, area under the precision-recall curve, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Futhermore, we established multivariable logistic regression models with the develop set and compared prediction performance with the ensemble models. The primary outcome was an unfavorable 1-year neurological outcome. @*Results@#A total of 1,207 patients were included in the study. Among them, 631, 139, and 153were assigned to the develop, the internal validation and the external validation datasets, respectively. Prediction performance metrics for the ensemble prediction model in the internal validation dataset were as follows: accuracy, 0.9620 (95% confidence interval [CI],0.9352–0.9889); area under receiver-operator characteristics curve, 0.9800 (95% CI, 0.9612– 0.9988); area under precision-recall curve, 0.9950 (95% CI, 0.9860–1.0000); sensitivity, 0.9594 (95% CI, 0.9245–0.9943); specificity, 0.9714 (95% CI, 0.9162–1.0000); PPV, 0.9916 (95% CI, 0.9752–1.0000); NPV, 0.8718 (95% CI, 0.7669–0.9767). Prediction performance metrics for the model in the external validation dataset were as follows: accuracy, 0.8509 (95% CI, 0.7825–0.9192); area under receiver-operator characteristics curve, 0.9301 (95% CI, 0.8845–0.9756); area under precision-recall curve, 0.9476 (95% CI, 0.9087–0.9867); sensitivity, 0.9595 (95% CI, 0.9145–1.0000); specificity, 0.6500 (95% CI, 0.5022–0.7978); PPV, 0.8353 (95% CI, 0.7564–0.9142); NPV, 0.8966 (95% CI, 0.7857–1.0000). All the prediction metrics were higher in the ensemble models, except NPVs in both the internal and the external validation datasets. @*Conclusion@#We established an ensemble prediction model for prediction of unfavorable 1-year neurological outcomes in OHCA survivors using four machine learning methods. The prediction performance of the ensemble model was higher than the multivariable logistic regression model, while its performance was slightly decreased in the external validation dataset.

Codeless Deep Learning of COVID-19 Chest X-Ray Image Dataset with KNIME Analytics Platform / 대한의료정보학회지

Objectives@#This paper proposes a method for computer-assisted diagnosis of coronavirus disease 2019 (COVID-19) through chest X-ray imaging using a deep learning model without writing a single line of code using the Konstanz Information Miner (KNIME) analytics platform. @*Methods@#We obtained 155 samples of posteroanterior chest X-ray images from COVID-19 open dataset repositories to develop a classification model using a simple convolutional neural network (CNN). All of the images contained diagnostic information for COVID-19 and other diseases. The model would classify whether a patient was infected with COVID-19 or not. Eighty percent of the images were used for model training, and the rest were used for testing. The graphic user interface-based programming in the KNIME enabled class label annotation, data preprocessing, CNN model training and testing, performance evaluation, and so on. @*Results@#1,000 epochs training were performed to test the simple CNN model. The lower and upper bounds of positive predictive value (precision), sensitivity (recall), specificity, and f-measure are 92.3% and 94.4%. Both bounds of the model’s accuracies were equal to 93.5% and 96.6% of the area under the receiver operating characteristic curve for the test set. @*Conclusions@#In this study, a researcher who does not have basic knowledge of python programming successfully performed deep learning analysis of chest x-ray image dataset using the KNIME independently. The KNIME will reduce the time spent and lower the threshold for deep learning research applied to healthcare.

Recovery of Proprioception in the Upper Extremity by Robotic Mirror Therapy: a Clinical Pilot Study for Proof of Concept

A novel robotic mirror therapy system was recently developed to provide proprioceptive stimulus to the hemiplegic arm during a mirror therapy. Validation of the robotic mirror therapy system was performed to confirm its synchronicity prior to the clinical study. The mean error angle range between the intact arm and the robot was 1.97 to 4.59 degrees. A 56-year-old male who had right middle cerebral artery infarction 11 months ago received the robotic mirror therapy for ten 30-minute sessions during 2 weeks. Clinical evaluation and functional magnetic resonance imaging (fMRI) studies were performed before and after the intervention. At the follow-up evaluation, the thumb finding test score improved from 2 to 1 for eye level and from 3 to 1 for overhead level. The Albert's test score on the left side improved from 6 to 11. Improvements were sustained at 2-month follow-up. The fMRI during the passive motion revealed a considerable increase in brain activity at the lower part of the right superior parietal lobule, suggesting the possibility of proprioception enhancement. The robotic mirror therapy system may serve as a useful treatment method for patients with supratentorial stroke to facilitate recovery of proprioceptive deficit and hemineglect.

In-Silico Trials for Glucose Control in Hospitalized Patients with Type 2 Diabetes

Although various basal-bolus insulin therapy (BBIT) protocols have been used in the clinical environment, safer and more effective BBIT protocols are required for glucose control in hospitalized patients with type 2 diabetes (T2D). Modeling approaches could provide an evaluation environment for developing the optimal BBIT protocol prior to clinical trials at low cost and without risk of danger. In this study, an in-silico model was proposed to evaluate subcutaneous BBIT protocols in hospitalized patients with T2D. The proposed model was validated by comparing the BBIT protocol and sliding-scale insulin therapy (SSIT) protocol. The model was utilized for in-silico trials to compare the protocols of adjusting basal-insulin dose (BBIT1) versus adjusting total-daily-insulin dose (BBIT2). The model was also used to evaluate two different initial total-daily-insulin doses for various levels of renal function. The BBIT outcomes were superior to those of SSIT, which is consistent with earlier studies. BBIT2 also outperformed BBIT1, producing a decreased daily mean glucose level and longer time-in-target-range. Moreover, with a standard dose, the overall daily mean glucose levels reached the target range faster than with a reduced-dose for all degrees of renal function. The in-silico studies demonstrated several significant findings, including that the adjustment of total-daily-insulin dose is more effective than changes to basal-insulin dose alone. This research represents a first step toward the eventual development of an advanced model for evaluating various BBIT protocols.

Application of the Oral Minimal Model to Korean Subjects with Normal Glucose Tolerance and Type 2 Diabetes Mellitus

BACKGROUND: The oral minimal model is a simple, useful tool for the assessment of β-cell function and insulin sensitivity across the spectrum of glucose tolerance, including normal glucose tolerance (NGT), prediabetes, and type 2 diabetes mellitus (T2DM) in humans. METHODS: Plasma glucose, insulin, and C-peptide levels were measured during a 180-minute, 75-g oral glucose tolerance test in 24 Korean subjects with NGT (n=10) and T2DM (n=14). The parameters in the computational model were estimated, and the indexes for insulin sensitivity and β-cell function were compared between the NGT and T2DM groups. RESULTS: The insulin sensitivity index was lower in the T2DM group than the NGT group. The basal index of β-cell responsivity, basal hepatic insulin extraction ratio, and post-glucose challenge hepatic insulin extraction ratio were not different between the NGT and T2DM groups. The dynamic, static, and total β-cell responsivity indexes were significantly lower in the T2DM group than the NGT group. The dynamic, static, and total disposition indexes were also significantly lower in the T2DM group than the NGT group. CONCLUSION: The oral minimal model can be reproducibly applied to evaluate β-cell function and insulin sensitivity in Koreans.

Computational Discrimination of Breast Cancer for Korean Women Based on Epidemiologic Data Only

Breast cancer is the second leading cancer for Korean women and its incidence rate has been increasing annually. If early diagnosis were implemented with epidemiologic data, the women could easily assess breast cancer risk using internet. National Cancer Institute in the United States has released a Web-based Breast Cancer Risk Assessment Tool based on Gail model. However, it is inapplicable directly to Korean women since breast cancer risk is dependent on race. Also, it shows low accuracy (58%-59%). In this study, breast cancer discrimination models for Korean women are developed using only epidemiological case-control data (n = 4,574). The models are configured by different classification techniques: support vector machine, artificial neural network, and Bayesian network. A 1,000-time repeated random sub-sampling validation is performed for diverse parameter conditions, respectively. The performance is evaluated and compared as an area under the receiver operating characteristic curve (AUC). According to age group and classification techniques, AUC, accuracy, sensitivity, specificity, and calculation time of all models were calculated and compared. Although the support vector machine took the longest calculation time, the highest classification performance has been achieved in the case of women older than 50 yr (AUC = 64%). The proposed model is dependent on demographic characteristics, reproductive factors, and lifestyle habits without using any clinical or genetic test. It is expected that the model could be implemented as a web-based discrimination tool for breast cancer. This tool can encourage potential breast cancer prone women to go the hospital for diagnostic tests.

Simulation of Oral Glucose Tolerance Tests and the Corresponding Isoglycemic Intravenous Glucose Infusion Studies for Calculation of the Incretin Effect

The incretin effect, which is a unique stimulus of insulin secretion in response to oral ingestion of nutrients, is calculated by the difference in insulin secretory responses from an oral glucose tolerance test (OGTT) and a corresponding isoglycemic intravenous glucose infusion (IIGI) study. The OGTT model of this study, which is individualized by fitting the glucose profiles during an OGTT, was developed to predict the glucose profile during an IIGI study in the same subject. Also, the model predicts the insulin and incretin profiles during both studies. The incretin effect, estimated by simulation, was compared with that measured by physiologic studies from eight human subjects with normal glucose tolerance, and the result exhibited a good correlation (r > 0.8); the incretin effect from the simulation was 56.5% +/- 10.6% while the one from the measured data was 52.5% +/- 19.6%. In conclusion, the parameters of the OGTT model have been successfully estimated to predict the profiles of both OGTTs and IIGI studies. Therefore, with glucose data from the OGTT alone, this model could control and predict the physiologic responses, including insulin secretion during OGTTs and IIGI studies, which could eventually eliminate the need for complex and cumbersome IIGI studies in incretin research.

The role of scientific evidence in the management of high-risk groups using genetic information

Genetic factors are important host factors that play a role in the development of all diseases through their interaction with environmental factors. Most genetic disorders are the direct result of a mutation in a single gene. However, one of the most difficult challenges currently faced by researchers is the identification of ways in which genes contribute to diseases with complex inheritance patterns, such as cancer, diabetes, asthma, and mental illness. In all of these cases, no single gene determines whether a person will develop a disease. Several genes may contribute to an individual's susceptibility to a disease; genes may also affect how an individual reacts to environmental factors. In this study, we attempted to classify high-risk groups using up-to-date genetic knowledge. We also briefly discuss the role of scientific evidence in the identification (through genetic screening) and management of high-risk subgroups in the population.