Use of explainable AI on slit-lamp images of anterior surface of eyes to diagnose allergic conjunctival diseases.

BACKGROUND: Artificial intelligence (AI) is a promising new technology that has the potential of diagnosing allergic conjunctival diseases (ACDs). However, its development is slowed by the absence of a tailored image database and explainable AI models. Thus, the purpose of this study was to develop an explainable AI model that can not only diagnose ACDs but also present the basis for the diagnosis. METHODS: A dataset of 4942 slit-lamp images from 10 ophthalmological institutions across Japan were used as the image database. A sequential pipeline of segmentation AI was constructed to identify 12 clinical findings in 1038 images of seasonal and perennial allergic conjunctivitis (AC), atopic keratoconjunctivitis (AKC), vernal keratoconjunctivitis (VKC), giant papillary conjunctivitis (GPC), and normal subjects. The performance of the pipeline was evaluated by determining its ability to obtain explainable results through the extraction of the findings. Its diagnostic accuracy was determined for 4 severity-based diagnosis classification of AC, AKC/VKC, GPC, and normal. RESULTS: Segmentation AI pipeline efficiently extracted crucial ACD indicators including conjunctival hyperemia, giant papillae, and shield ulcer, and offered interpretable insights. The AI pipeline diagnosis had a high diagnostic accuracy of 86.2%, and that of the board-certified ophthalmologists was 60.0%. The pipeline had a high classification performance, and the area under the curve (AUC) was 0.959 for AC, 0.905 for normal subjects, 0.847 for GPC, 0.829 for VKC, and 0.790 for AKC. CONCLUSIONS: An explainable AI model created by a comprehensive image database can be used for diagnosing ACDs with high degree of accuracy.

[STATE-OF-THE-ART OF GLOBAL START-UP INVESTMENT FOR ALLERGY AND IMMUNOLOGY 2022].

BACKGROUND: In 2022, the "New Capitalism Grand Design and Implementation Plan" was adopted in Japan, emphasizing the promotion and environmental development of startups. Given this context, an investigation into the startup and investment landscape in the allergy sector, both domestically and internationally, becomes imperative. METHODS: We analyzed 156 allergy-related startups from Japan, the US, and Europe from 2010 to 2021. Data on corporate information and investment trends were extracted from databases and VC websites. RESULTS: The total investment reached approximately 7.2 billion USD, with a ratio of 20:6:1 for the US, Europe, and Japan, respectively. The US showed a decline post its peak from 2016-2018, while Europe and Japan experienced growth. Notably, the US primarily invested in biopharmaceuticals for atopic dermatitis and food allergies, Europe in asthma-related apps, and Japan in healthcare apps and cross-border startups. DISCUSSION AND CONCLUSION: While Japan's investment environment in the allergy sector remains in its nascent stages and has room for development, the US and Europe are evidently ahead. Considering the rise of startups and funding limitations in Japan, external funding from regions like the US becomes a potential avenue. These findings are anticipated to contribute to the strategic activation of startups in allergy research and development.

[RECURRENT AND VIRTUAL EDUCATION FOR ALL DISCIPLINES AND OCCUPATIONS IN THE ALLERGY REALM : A SURVEY OF THE PARTICIPANTS FROM THE INITIATIVE 'OUTREACH LECTURES' TO CREATE EDUCATIONAL OPPORTUNITIES].

BACKGROUND: In the enhancement of allergy care involving multidisciplinary and multiple medical departments, there is a perceived need for education that targets not only specialists but also non-specialists. However, research on the need for and methods of such education remains inadequate. OBJECTIVE: To design a remote allergy care education program for all medical practitioners and to validate its necessity and utility. METHODS: The Empowering Next Generation Allergist/immunologist toward Global Excellence Task Force (ENGAGE-TF), supported by the Japanese Society of Allergology, initiated a virtual educational program called 'Outreach Lectures' in collaboration with Keio University and Fukui University. This initiative was widely promoted through social media and various institutions, and a survey was conducted through its mailing list. RESULTS: 1139 responses were obtained. More than half were physicians from non-allergy specialties, representing a diverse range of healthcare professions. Over 70% expressed being 'very satisfied,' and over 60% found the difficulty level 'appropriate.' Free-form feedback revealed differences in learning focus based on profession and learning approach based on years of experience. CONCLUSION: The high participation rate (90%) of non-specialist physicians underscores the demand for addressing allergic conditions in primary care. The effectiveness of virtual / recurrent education, particularly for healthcare professionals with over 11 years of experience, was implied. Further follow-up investigation focusing on quantitative and objective assessment of educational effectiveness is indispensable.

Smartphone App-Based and Paper-Based Patient-Reported Outcomes Using a Disease-Specific Questionnaire for Dry Eye Disease: Randomized Crossover Equivalence Study.

BACKGROUND: Using traditional patient-reported outcomes (PROs), such as paper-based questionnaires, is cumbersome in the era of web-based medical consultation and telemedicine. Electronic PROs may reduce the burden on patients if implemented widely. Considering promising reports of DryEyeRhythm, our in-house mHealth smartphone app for investigating dry eye disease (DED) and the electronic and paper-based Ocular Surface Disease Index (OSDI) should be evaluated and compared to determine their equivalency. OBJECTIVE: The purpose of this study is to assess the equivalence between smartphone app-based and paper-based questionnaires for DED. METHODS: This prospective, nonblinded, randomized crossover study enrolled 34 participants between April 2022 and June 2022 at a university hospital in Japan. The participants were allocated randomly into 2 groups in a 1:1 ratio. The paper-app group initially responded to the paper-based Japanese version of the OSDI (J-OSDI), followed by the app-based J-OSDI. The app-paper group responded to similar questionnaires but in reverse order. We performed an equivalence test based on minimal clinically important differences to assess the equivalence of the J-OSDI total scores between the 2 platforms (paper-based vs app-based). A 95% CI of the mean difference between the J-OSDI total scores within the ±7.0 range between the 2 platforms indicated equivalence. The internal consistency and agreement of the app-based J-OSDI were assessed with Cronbach α coefficients and intraclass correlation coefficient values. RESULTS: A total of 33 participants were included in this study. The total scores for the app- and paper-based J-OSDI indicated satisfactory equivalence per our study definition (mean difference 1.8, 95% CI -1.4 to 5.0). Moreover, the app-based J-OSDI total score demonstrated good internal consistency and agreement (Cronbach α=.958; intraclass correlation=0.919; 95% CI 0.842 to 0.959) and was significantly correlated with its paper-based counterpart (Pearson correlation=0.932, P<.001). CONCLUSIONS: This study demonstrated the equivalence of PROs between the app- and paper-based J-OSDI. Implementing the app-based J-OSDI in various scenarios, including telehealth, may have implications for the early diagnosis of DED and longitudinal monitoring of PROs.

Using the AllerSearch Smartphone App to Assess the Association Between Dry Eye and Hay Fever: mHealth-Based Cross-Sectional Study.

BACKGROUND: Dry eye (DE) and hay fever (HF) show synergistic exacerbation of each other's pathology through inflammatory pathways. OBJECTIVE: This study aimed to investigate the association between DE and HF comorbidity and the related risk factors. METHODS: A cross-sectional observational study was conducted using crowdsourced multidimensional data from individuals who downloaded the AllerSearch smartphone app in Japan between February 2018 and May 2020. AllerSearch collected the demographics, medical history, lifestyle and residential information, HF status, DE symptoms, and HF-related quality of life. HF symptoms were evaluated using the nasal symptom score (0-15 points) and nonnasal symptom score (0-12 points). HF was defined by the participants' responses to the questionnaire as HF, non-HF, or unknown. Symptomatic DE was defined as an Ocular Surface Disease Index total score (0-100 points), with a threshold score of 13 points. HF-related quality of life was assessed using the Japanese Allergic Conjunctival Disease Standard Quality of Life Questionnaire (0-68 points). We conducted a multivariable linear regression analysis to examine the association between the severity of DE and HF symptoms. We subsequently conducted a multivariable logistic regression analysis to identify the factors associated with symptomatic DE (vs nonsymptomatic DE) among individuals with HF. Dimension reduction via Uniform Manifold Approximation and Projection stratified the comorbid DE and HF symptoms. The symptom profiles in each cluster were identified using hierarchical heat maps. RESULTS: This study included 11,284 participants, classified into experiencing HF (9041 participants), non-HF (720 participants), and unknown (1523 participants) groups. The prevalence of symptomatic DE among individuals with HF was 49.99% (4429/9041). Severe DE symptoms were significantly associated with severe HF symptoms: coefficient 1.33 (95% CI 1.10-1.57; P<.001) for mild DE, coefficient 2.16 (95% CI 1.84-2.48; P<.001) for moderate DE, and coefficient 3.80 (95% CI 3.50-4.11; P<.001) for severe DE. The risk factors for comorbid symptomatic DE among individuals with HF were identified as female sex; lower BMI; medicated hypertension; history of hematologic, collagen, heart, liver, respiratory, or atopic disease; tomato allergy; current and previous mental illness; pet ownership; living room and bedrooms furnished with materials other than hardwood, carpet, tatami, and vinyl; discontinuation of contact lens use during the HF season; current contact lens use; smoking habits; and sleep duration of <6 hours per day. Uniform Manifold Approximation and Projection stratified the heterogeneous comorbid DE and HF symptoms into 14 clusters. In the hierarchical heat map, cluster 9 was comorbid with the most severe HF and DE symptoms, and cluster 1 showed severe HF symptoms with minimal DE-related symptoms. CONCLUSIONS: This crowdsourced study suggested a significant association between severe DE and HF symptoms. Detecting DE among individuals with HF could allow effective prevention and interventions through concurrent treatment for ocular surface management along with HF treatment.

Individual multidisciplinary clinical phenotypes of nasal and ocular symptoms in hay fever: Crowdsourced cross-sectional study using AllerSearch.

BACKGROUND: Multidisciplinary efforts to prospectively collect and analyze symptoms of hay fever are limited. We aimed to identify the characteristics of nasal and ocular symptoms of hay fever, using the AllerSearch smartphone application. METHODS: This mobile health-based prospective observational study using the AllerSearch smartphone application was conducted between February 1, 2018, and May 1, 2020. Individuals who downloaded AllerSearch from Japan and provided comprehensive self-assessments (including 17 items related to quality of life [QoL]-related items) were included. The characteristics and risk factors for allergic rhinitis (AR) and allergic conjunctivitis (AC) were identified using hierarchical heat maps and multivariate logistic regression. RESULTS: Of the 9041 participants with hay fever, 58.8% had AR and AC, 22.2% had AR, and 5.7% had AC. The AR-AC comorbid cohort showed worse symptoms of hay fever and QoL scores than the other cohorts. Factors (odds ratio, 95% confidence interval) associated with AR-AC included a lower age (0.98, 0.97-0.98), female sex (1.31, 1.19-1.45), liver disease (1.58, 1.26-2.35), dry eye disease (1.45, 1.30-1.63), unknown dry eye disease status (1.46, 1.31-1.62), contact lens use discontinuation during the hay fever season (1.69, 1.28-2.23), and bedroom flooring material other than hardwood, carpet, tatami, or vinyl (1.91, 1.16-3.14). CONCLUSIONS: Analysis of medical big data for hay fever performed using a mobile health app helped identify risk factors and characteristics of AC, AR, and AR-AC. Phenotyping of highly variable symptoms of hay fever, such as nasal and ocular symptoms, can facilitate better-quality clinical care.

Individual characteristics and associated factors of hay fever: A large-scale mHealth study using AllerSearch.

BACKGROUND: The prevalence of hay fever, a multifactorial allergic disease, is increasing. Identifying individual characteristics and associated factors of hay fever is essential for predictive, preventive, personalized, and participatory (P4) medicine. This study aimed to identify individual characteristics and associated factors of hay fever using an iPhone application AllerSearch. METHODS: This large-scale mobile health-based cross-sectional study was conducted between February 2018 and May 2020. Individuals who downloaded AllerSearch in Japan and provided a comprehensive self-assessment (general characteristics, medical history, lifestyle habits, and hay fever symptoms [score range 0-36]) were included. Associated factors of hay fever (vs. non-hay fever) and severe hay fever symptoms were identified using multivariate logistic and linear regression analyses, respectively. RESULTS: Of the included 11,284 individuals, 9041 had hay fever. Factors associated with hay fever (odds ratio) included age (0.98), female sex (1.33), atopic dermatitis (1.40), history of dry eye diagnosis (1.36), discontinuation of contact lens use during hay fever season (3.34), frequent bowel movements (1.03), and less sleep duration (0.91). The factors associated with severe hay fever symptoms among individuals with hay fever (coefficient) included age (-0.104), female sex (1.329), history of respiratory disease (1.539), history of dry eye diagnosis (0.824), tomato allergy (1.346), discontinuation of contact lens use during hay fever season (1.479), smoking habit (0.614), and having a pet (0.303). CONCLUSIONS: Our large-scale mobile health-based study using AllerSearch elucidated distinct hay fever presentation patterns, characteristics, and factors associated with hay fever. Our study establishes the groundwork for effective individualized interventions for P4 medicine.

Evaluation of adrenaline auto-injector prescription profiles: A population-based, retrospective cohort study within the National Insurance Claims Database of Japan.

BACKGROUND: Adrenaline is the first-line medication for managing anaphylaxis. A better understanding of prescription trends for adrenaline auto-injectors (AAIs) is important to improving patient care as well as information on health education interventions and medical guidelines. However, it has been difficult to gather comprehensive data in a sustainable manner. Thus, we aimed to investigate trends in AAI prescriptions in Japan. METHODS: We searched the National Database of Health Insurance Claims and Specific Health Checkups of Japan (NDB), a unique and comprehensive database of health insurance claims, and investigated prescriptions for AAIs for all ages (April 2017 to March 2018). We assessed the annual number of prescriptions per person as well as prescription rates per 100,000 population per year by age, sex, and geographic region. RESULTS: A total of 88,039 subjects (56,109 males, 31,930 female) and 116,758 devices (1.33 AAIs per patient per year) were prescribed AAIs at least once a year for all ages. The prescription rate for AAIs was 69.5 per 100,000 population-years. Patients aged 0-9 years were prescribed AAIs at the rate of 278.9 per 100,000 population-years. Patients aged 0-19 years were 6.4 times more likely to be prescribed AAIs than those over 20 years of age. Males were more frequently prescribed AAIs than females in all age groups, except for those aged 20-24 years. We also evaluated differences in prescription rates by geographic region. CONCLUSIONS: This comprehensive evaluation revealed trends in AAI prescriptions, thus helping develop preventive strategies with respect to anaphylaxis in Japan.

Stratification of Individual Symptoms of Contact Lens-Associated Dry Eye Using the iPhone App DryEyeRhythm: Crowdsourced Cross-Sectional Study.

BACKGROUND: Discontinuation of contact lens use is mainly caused by contact lens-associated dry eye. It is crucial to delineate contact lens-associated dry eye's multifaceted nature to tailor treatment to each patient's individual needs for future personalized medicine. OBJECTIVE: This paper aims to quantify and stratify individual subjective symptoms of contact lens-associated dry eye and clarify its risk factors for future personalized medicine using the smartphone app DryEyeRhythm (Juntendo University). METHODS: This cross-sectional study included iPhone (Apple Inc) users in Japan who downloaded DryEyeRhythm. DryEyeRhythm was used to collect medical big data related to contact lens-associated dry eye between November 2016 and January 2018. The main outcome measure was the incidence of contact lens-associated dry eye. Univariate and multivariate adjusted odds ratios of risk factors for contact lens-associated dry eye were determined by logistic regression analyses. The t-distributed Stochastic Neighbor Embedding algorithm was used to depict the stratification of subjective symptoms of contact lens-associated dry eye. RESULTS: The records of 4454 individuals (median age 27.9 years, SD 12.6), including 2972 female participants (66.73%), who completed all surveys were included in this study. Among the included participants, 1844 (41.40%) were using contact lenses, and among those who used contact lenses, 1447 (78.47%) had contact lens-associated dry eye. Multivariate adjusted odds ratios of risk factors for contact lens-associated dry eye were as follows: younger age, 0.98 (95% CI 0.96-0.99); female sex, 1.53 (95% CI 1.05-2.24); hay fever, 1.38 (95% CI 1.10-1.74); mental illness other than depression or schizophrenia, 2.51 (95% CI 1.13-5.57); past diagnosis of dry eye, 2.21 (95% CI 1.63-2.99); extended screen exposure time >8 hours, 1.61 (95% CI 1.13-2.28); and smoking, 2.07 (95% CI 1.49-2.88). The t-distributed Stochastic Neighbor Embedding analysis visualized and stratified 14 groups based on the subjective symptoms of contact lens-associated dry eye. CONCLUSIONS: This study identified and stratified individuals with contact lens-associated dry eye and its risk factors. Data on subjective symptoms of contact lens-associated dry eye could be used for prospective prevention of contact lens-associated dry eye progression.

New medical big data for P4 medicine on allergic conjunctivitis.

Allergic conjunctivitis affects approximately 15-20% of the global population and can permanently deteriorate one's quality of life (QoL) and work productivity, leading to societal work force costs. Although not fully understood, allergic conjunctivitis is a multifactorial disease with a complex network of environmental, lifestyle, and host contributory risk factors. To effectively enhance the quality of treatment for patients with allergic conjunctivitis, as well as other allergic diseases, the field must first comprehend the pathology underlying various individualized subjective symptoms and stratify the disease according to risk factors and presentations. Such competent stratification and societal reconstruction that targets the alleviation of the damage due to allergic diseases would greatly help ramify personalized treatments and prevent the projected increase in societal costs imposed by allergic diseases. Owing to the rapid advancements in the information and technology sector, medical big data are greatly accessible and useful to decipher the pathophysiology of many diseases. Such data collected through multi-omics and mobile health have been effective for research on chronic diseases including allergic and immune-mediated diseases. Novel big data containing vast and continuous information on individuals with allergic conjunctivitis and other allergic symptoms are being used to search for causative genes of diseases, gain insights into new biomarkers, prevent disease progression, and, ultimately, improve QoL. The individualized and holistic data accrued from new angles using technological innovations are helping the field realize the principles of P4 medicine: predictive, preventive, personalized, and participatory medicine.

IFN-γ-Expressing Th17 Cells Are Required for Development of Severe Ocular Surface Autoimmunity.

Th17 cells are critical effectors mediating the ocular surface autoimmunity in dry eye disease (DED). Increased IFN-γ has also been implicated in DED; however, it remains unclear to what extent Th1 cells contribute to DED pathogenesis. In this study, we investigated the cellular source of IFN-γ and assessed its contribution to corneal epitheliopathy in DED mice. We discovered a significant IL-17A+IFN-γ+ (Th17/1) population and determined that these cells are derived from Th17 precursors. Adoptive transfer of Th17/1, but not Th1, cells confers the disease to naive recipients as effectively as do Th17 cells alone. DED-induced IL-12 and IL-23 are required for in vivo transition of pathogenic Th17 cells to IFN-γ producers. Furthermore, using IFN-γ-deficient Th17 cells, we demonstrate the disease-amplifying role of Th17-derived IFN-γ in DED pathogenesis. These results clearly demonstrate that Th17 cells mediate ocular surface autoimmunity through both IL-17A and IFN-γ.

Donor characteristics and risk factors for methicillin-resistant Staphylococcus aureus contamination in storage medium for corneal transplantation: A 10-year retrospective study.

PURPOSE: This study investigated the donor characteristics of methicillin-resistant Staphylococcus aureus (MRSA) contamination in storage medium before transfer of corneas to preservation medium for corneal transplantation, in order to identify donor characteristic risk factors for MRSA contamination. METHODS: This retrospective, cross-sectional study was performed using Juntendo Eye Bank records for all corneal transplantation procedures. Storage medium (EP-II® ) cultures for right eyes were included for the period between July 2008 and December 2017. The following donor characteristics were collected: age, sex, cause of death, history of cataract surgery, death-to-enucleation interval, death-to-preservation interval, and endothelial cell density (ECD). Donor characteristics were compared between MRSA and non-MRSA contamination groups. Odds ratios (ORs) for donor-related risk factors for MRSA contamination were determined using logistic regression. RESULTS: In total, 370 storage medium samples were examined; 222 were positive for bacterial cultures (60.0%) and 36 were MRSA-positive (9.7%). Donor age was significantly higher in the MRSA contamination group than in the non-MRSA contamination group (86.1 ± 9.5 years vs 75.9 ± 15.9 years, P < 0.001). Univariate logistic regression analysis showed that MRSA contamination risk factors were older age (OR = 1.07; 95% confidence interval [95% CI]: 1.03-1.11) and decreased ECD (OR = 0.9993; 95% CI: 0.9986-0.9992). The fully adjusted OR for every year of age as a risk factor for MRSA contamination was 1.07 (95% CI: 1.03-1.11). CONCLUSIONS: Aging was a risk factor for MRSA contamination in storage medium. Careful pre-banking assessment of elderly donor corneas is needed to prevent intractable postoperative MRSA infection.

Fundus changes in type III membranoproliferative glomerulonephritis: a case report.

BACKGROUND: Membranoproliferative glomerulonephritis (MPGN) is characterized by mesangial cell proliferation and is classified into types I, II and III based on structural changes in the glomerular capillary walls. The drusen-like deposits of MPGN type II have been studied, but the fundus changes in MPGN type III have yet to be clarified. We report a case of MPGN type III with multiple deposits in the retinal pigment epithelium (RPE). CASE PRESENTATION: A 40-year-old Japanese woman with MPGN type III developed numerous yellow-white patches in the central macula of both eyes. Optical coherence tomography (OCT) showed deposits between the RPE and Bruch's membrane. Fluorescein angiography showed choroidal neovascularization (CNV) and OCT confirmed it as type 1 (sub RPE) CNV with fibrin tissue and subretinal fluid in the right eye. After 12 months, the CNV and subretinal fluid resolved spontaneously but the RPE deposits remained in both eyes. Her final visual acuity was 20/20 in the right eye and 20/16 in the left eye. CONCLUSION: We report a case of MPGN type III with multiple deposits in the RPE and CNV, suggesting that various fundus changes occur in MPGN type III and careful fundus follow-up is necessary to prevent vision loss.

Relationship between dry eye disease and myopia: A systematic review and meta-analysis.

Background/objectives: Dry eye disease (DED) and myopia are common ocular disorders. This systematic review and meta-analysis investigated the association between DED and myopia. Methods: PubMed and EMBASE were searched for articles published between 1984 and 2022. Study quality was assessed using the Joanna Briggs Institute Critical Appraisal Checklist, and analysis was conducted using the DerSimonian-Laird random-effects model. Results: Of the 1,313 studies identified, 15 studies on DED and myopia were included. The meta-analysis revealed that the overall prevalence of subjective DED symptoms in the myopia population was 45.1 % (95 % confidence interval: 0.287-0.616). There was a significant association between DED and myopia. The myopia population had higher Ocular Surface Disease Index scores and shorter tear film breakup times than the non-myopia population. Additionally, the meta-regression analysis showed that spherical equivalent was significantly associated with the prevalence of DED symptoms in adults with myopia. Conclusion: Interventions to prevent DED are required in the myopia population. Enhancing patient awareness and self-management for DED, in addition to early screening and detection, is especially critical for younger populations who are at a higher risk of developing myopia.

Human ocular thelaziasis with genetic analysis in Niigata Prefecture, Japan: A case report on an emerging zoonosis.

Purpose: We report the clinical findings and molecular identification of ocular Thelazia callipaeda from Niigata Prefecture in the Hokuriku area of Japan during winter. Observations: A 77-year-old male visited an ophthalmology clinic in Niigata Prefecture in January 2022 after a 2-week-duration of a conjunctival injection in the left eye and foreign body sensation. Slit-lamp microscopy revealed 11 active nematodes in the left conjunctival sac. Morphological characteristics included longer female body length than male, buccal cavity lacking teeth and lips, and serrated striations along the body surface. The specimens were determined to be T. callipaeda. Genetic analysis of the mitochondrial cytochrome c oxidase subunit 1 (cox1) gene revealed an h9 haplotype. Conclusions and Importance: T. callipaeda infection, especially the h9 haplotype, commonly occurs in western Japan owing to its higher incidence in warmer climates, suggesting the origin of the case. Here, we report a human case of Thelaziasis diagnosed in a cold region of Japan (the Hokuriku area) during winter. This human case of T. callipaeda infection from a cold, previously unassociated region, raises concerns about the potential geographical widening of its distribution, and further investigation may be warranted to prevent its spread.

Impact of the Coronavirus Disease 2019 Pandemic on Outpatient Visits for Diabetic Retinopathy in Japan: A Retrospective Cohort Study.

Purpose: Long-term ramifications of the coronavirus disease 2019 pandemic on various care-seeking characteristics of patients with diabetic retinopathy remain unclear. This study aimed to identify risk factors for dropout from regular fundus examinations (RFEs) in patients with diabetic retinopathy in Japan. Methods: We extracted demographic and health checkup data (April 2018 to March 2021) from the JMDC database. Patients with diabetes identified using diagnosis-related and medication codes were included. The dropout and continuation groups included patients who discontinued and continued to undergo RFEs during the coronavirus disease 2019 pandemic, respectively. Results: The number of RFEs was significantly lower during the mild lockdown period (April and May 2020) than during the prepandemic period. Of the 14,845 patients with diabetes, 2333 (15.7%) dropped out of RFEs during the pandemic, whereas before the pandemic, of the 11,536 patients with diabetes, 1666 (14.4%) dropped out of RFEs (P = 0.004). Factors associated with dropout in the multivariate logistic regression analysis included younger age, male sex, high triglyceride levels, high γ-glutamyl transpeptidase levels, smoking habit, alcohol consumption, weight gain of more than 10 kg since the age of 20 years, and certain stages of lifestyle improvement. Factors associated with continuation included low body mass index and high glycosylated hemoglobin levels. Conclusions: Our findings can assist in identifying patients with diabetes at risk of dropout. Translational Relevance: These results have implications for public health and identifying patients with diabetes at risk of dropout. Education and tailored monitoring regimens could be pivotal role in fostering adherence.