Predicting Medical Event Occurrence Using Medical Insurance Claims Big Data.

Medical events are often infrequent, thus becomes hard to predict. In this paper, we focus on predictor that forecasts whether a medical event would occur in the next year, and analyzes the impact of event's frequency and data size via predictor's performance. In the experiment, we made 1572 predictors for medical events using Medical Insurance Claims (MICs) data from 800,000 participants and 205.8 million claims over 8 years. The result revealed that (a) forecasting error will be increased when predicting low-frequency events, and (b) increasing the number of training dataset reduces errors. This result suggests that increasing data size is a key to solve low frequency problems. However, we still need additional methods to cope with sparse and imbalanced data.

Analyzing Patient-Sharing Network Using an Administrative Claim Database in Japan.

We analyzed the behavior of patient with a focus on patient-sharing based on the methodology of network analysis. We used an administrative healthcare claims database from September of the years 2008-2020 to identify shared patients with hypertension. The patients' behavior of visiting multiple medical facilities was extracted as graphical data, and we calculated density and centrality as indicators to evaluate the structure of the patient sharing network. Our findings indicate that density, reciprocity, and transitivity increased over time, and that centrality and PageRank were correlated.

Changes in Demand Volume and Patient/Health Care Provider Characteristics of First-Time Telehealth Users: A Comparative Analysis Before and After the COVID-19 Policy Response Using the Administrative Claims Database.

Introduction: The COVID-19 pandemic has led to a decrease in demand for medical services in Japan, but the utilization of telehealth, which the Japanese government has recently promoted, has seen a temporary increase. This study aims to analyze the trend of telehealth utilization and changes in patient characteristics following the policy response to COVID-19. Methods: This retrospective study analyzed data from 26,152 adult patients who used telehealth for the first time between April 2019 and April 2021 in Mie Prefecture, Japan. An interrupted time series analysis was conducted to evaluate changes in the number of first-time patients before and after April 2020. Results: The number of telehealth users increased by 111.87% after April 2020, but the trend showed a declining slope thereafter. Patient characteristics and disease types showed different trends. The percentage of patients choosing a hospital over a clinic increased for the first time. Conclusions: After the policy response to COVID-19, the number of first-time telehealth users overall increased immediately, but gradually showed a declining trend. However, some diseases have shown both an immediate increase and a continued upward trend in telehealth utilization. Patients with these diseases may be candidates for adopting telehealth services in clinical settings.

The five-year trends in antibiotic prescription by dentists and antibiotic prophylaxis for tooth extraction: a region-wide claims study in Japan.

BACKGROUND: Antimicrobial stewardship in dentistry and antibiotic prophylaxis for tooth extraction have been areas of concern in Japan, with limited research available. METHODS: This cross-sectional study utilized the regional health insurance claims database in Japan to examine antibiotic prescription trends by dentists, including antibiotic regimens, timing of prescription, and days of supply for prophylactic antibiotic use during tooth extraction. Antibiotic prophylaxis for patients with prosthetic heart valves was also investigated. FINDINGS: Antibiotic prescriptions by dentists decreased by 7% in 2019 compared to those in 2015, with third-generation cephalosporins still accounting for 48.5% in 2019. Amoxicillin prescription increased 3.9 times in 2019, although it only accounted for 8.4% of all antibiotic prescriptions. In 2019, amoxicillin was prescribed for 17.1% of all prophylactic antibiotics associated with tooth extraction, and 80% of prophylactic antibiotics were prescribed for 3 days or more, with 85% prescribed on the day of the procedure. However, only 60-70% of patients with prosthetic heart valves received antibiotic prophylaxis. INTERPRETATION: Despite the increasing trend after the implementation of the National Action Plan on antimicrobial resistance, the proportion of amoxicillin prescriptions in dentistry remains low. Antimicrobial stewardship issues related to long-term prescription and timing of administration of prophylactic antibiotics for tooth extraction should be addressed. Dentists must recognize the risks associated with high-risk patients with prosthetic heart valves who require antibiotic prophylaxis, and physicians providing valve replacement therapy should inform patients of the requirement for prophylaxis before invasive dental procedures.

Virtual patient identifier (vPID): Improving patient traceability using anonymized identifiers in Japanese healthcare insurance claims database.

Objective: Japan's national-level healthcare insurance claims database (NDB) is a collective database that contains the entire information on healthcare services being provided to all citizens. However, existing anonymized identifiers (ID1 and ID2) have a poor capability of tracing patients' claims in the database, hindering longitudinal analyses. This study presents a virtual patient identifier (vPID), which we have developed on top of these existing identifiers, to improve the patient traceability. Methods: vPID is a new composite identifier that intensively consolidates ID1 and ID2 co-occurring in an identical claim to allow to collect claims of each patient even though its ID1 or ID2 may change due to life events or clerical errors. We conducted a verification test with prefecture-level datasets of healthcare insurance claims and enrollee history records, which allowed us to compare vPID with the ground truth, in terms of an identifiability score (indicating a capability of distinguishing a patient's claims from another patient's claims) and a traceability score (indicating a capability of collecting claims of an identical patient). Results: The verification test has clarified that vPID offers significantly higher traceability scores (0.994, Mie; 0.997, Gifu) than ID1 (0.863, Mie; 0.884, Gifu) and ID2 (0.602, Mie; 0.839, Gifu), and comparable (0.996, Mie) and lower (0.979, Gifu) identifiability scores. Discussion: vPID is seemingly useful for a wide spectrum of analytic studies unless they focus on sensitive cases to the design limitation of vPID, such as patients experiencing marriage and job change, simultaneously, and same-sex twin children. Conclusion: vPID successfully improves patient traceability, providing an opportunity for longitudinal analyses that used to be practically impossible for NDB. Further exploration is also necessary, in particular, for mitigating identification errors.

Predicting demand for long-term care using Japanese healthcare insurance claims data.

BACKGROUND: Driven by the rapid aging of the population, Japan introduced public long-term care insurance to reinforce healthcare services for the elderly in 2000. Precisely predicting future demand for long-term care services helps authorities to plan and manage their healthcare resources and citizens to prevent their health status deterioration. METHODS: This paper presents our novel study for developing an effective model to predict individual-level future long-term care demand using previous healthcare insurance claims data. We designed two discriminative models and subsequently trained and validated the models using three learning algorithms with medical and long-term care insurance claims and enrollment records, which were provided by 170 regional public insurers in Gifu, Japan. RESULTS: The prediction model based on multiclass classification and gradient-boosting decision tree achieved practically high accuracy (weighted average of Precision, 0.872; Recall, 0.878; and F-measure, 0.873) for up to 12 months after the previous claims. The top important feature variables were indicators of current health status (e.g., current eligibility levels and age), risk factors to worsen future healthcare status (e.g., dementia), and preventive care services for improving future healthcare status (e.g., training and rehabilitation). CONCLUSIONS: The intensive validation tests have indicated that the developed prediction method holds high robustness, even though it yields relatively lower accuracy for specific patient groups with health conditions that are hard to distinguish.

The Association Between Telehealth Utilization and Policy Responses on COVID-19 in Japan: Interrupted Time-Series Analysis.

BACKGROUND: Telehealth using telephones or online communication is being promoted as a policy initiative in several countries. However, there is a lack of research on telehealth utilization in a country such as Japan that offers free access to medical care and regulates telehealth provision-particularly with respect to COVID-19. OBJECTIVE: The present study aimed to clarify telehealth utilization, the characteristics of patients and medical institutions using telehealth, and the changes to telehealth in Japan in order to support the formulation of policy strategies for telehealth provision. METHODS: Using a medical administrative claim database of the National Health Insurance and Advanced Elderly Medical Service System in Mie Prefecture, we investigated patients who used telehealth from January 2017 to September 2021. We examined telehealth utilization with respect to both patients and medical institutions, and we determined their characteristics. Using April 2020 as the reference time point for COVID-19, we conducted an interrupted time-series analysis (ITSA) to assess changes in the monthly proportion of telehealth users to beneficiaries. RESULTS: The number of telehealth users before the reference time point was 13,618, and after the reference time point, it was 28,853. Several diseases and conditions were associated with an increase in telehealth utilization. Telehealth consultations were mostly conducted by telephone and for prescriptions. The ITSA results showed a sharp increase in the proportion of telehealth use to beneficiaries after the reference time point (rate ratio 2.97; 95% CI 2.14-2.31). However, no apparent change in the trend of increasing or decreasing telehealth use was evident after the reference time point (rate ratio 1.00; 95% CI 1.00-1.01). CONCLUSIONS: We observed a sharp increase in telehealth utilization after April 2020, but no change in the trend of telehealth use was evident. We identified changes in the characteristics of patients and providers using telehealth.

Prevalence of hypertensive diseases and treated hypertensive patients in Japan: A nationwide administrative claims database study.

We investigated the prevalence of hypertensive patients and treated hypertensive patients using a Japanese nationwide administrative claims database. We analyzed national database data from 2014, including all claims data, provided by the Ministry of Health, Labour and Welfare of Japan. Hypertensive diseases were identified using Japanese standardized disease codes. Among hypertensive patients, treated hypertensive patients were defined by the prescription of any antihypertensive medication, identified using national health insurance price listing codes. We calculated and compared the number and age-adjusted prevalence of hypertensive patients and treated hypertensive patients by prefecture and the proportion of these patients by the size of medical facilities. In 2014, approximately 27 million Japanese people were identified as hypertensive, among which 89.6% were treated. The age-adjusted prevalence of hypertensive patients (per 100,000 persons) among women and men was 21,414 and 21,084, respectively. The age-adjusted prevalence of treated hypertensive patients (per 100,000 persons) among women and men was 19,118 and 18,974, respectively. While the prevalence of hypertensive and treated hypertensive patients varied geographically, the prevalence remained similar between the sexes. Approximately 59% of hypertensive patients visited clinics (0 to 19 beds) in Japan. In Japan, 27 million people were diagnosed with hypertensive diseases, and approximately 90% of these patients were treated with any antihypertensive medication in 2014. The distribution of hypertensive patients varied geographically throughout Japan.

Projecting prevalence of frailty and dementia and the economic cost of care in Japan from 2016 to 2043: a microsimulation modelling study.

BACKGROUND: Dementia and frailty often accompany one another in older age, requiring complex care and resources. Available projections provide little information on their joint impact on future health-care need from different segments of society and the associated costs. Using a newly developed microsimulation model, we forecast this situation in Japan as its population ages and decreases in size. METHODS: In this microsimulation modelling study, we built a model that simulates an individual's status transition across 11 chronic diseases (including diabetes, coronary heart disease, and stroke) as well as depression, functional status, and self-reported health, by age, sex, and educational strata (less than high school, high school, and college and higher), on the basis of nationally representative health surveys and existing cohort studies. Using the simulation results, we projected the prevalence of dementia and frailty, life expectancy with these conditions, and the economic cost for formal and informal care over the period 2016-43 in the population of Japan aged 60 years and older. FINDINGS: Between 2016 and 2043, life expectancy at age 65 years will increase from 23·7 years to 24·9 years in women and from 18·7 years to 19·9 years in men. Years spent with dementia will decrease from 4·7 to 3·9 years in women and 2·2 to 1·4 years in men. By contrast, years spent with frailty will increase from 3·7 to 4·0 years for women and 1·9 to 2·1 for men, and across all educational groups. By 2043, approximately 29% of women aged 75 years and older with a less than high school education are estimated to have both dementia and frailty, and so will require complex care. The expected need for health care and formal long-term care is anticipated to reach costs of US$125 billion for dementia and $97 billion for frailty per annum in 2043 for the country. INTERPRETATION: Japan's Government and policy makers should consider the potential social challenges in caring for a sizable population of older people with frailty and dementia, and a widening disparity in the burden of those conditions by sex and by educational status. The future burden of dementia and frailty should be countered not only by curative and preventive technology innovation, but also by social policies to mitigate the health gap. FUNDING: Japan Society for the Promotion of Science, Hitachi - the University of Tokyo Laboratory for a sustainable society, and the National Institute of Ageing.

Monthly trends and seasonality of hemodialysis treatment and outcomes of newly initiated patients from the national database (NDB) of Japan.

BACKGROUND: The numbers of patients treated with hemodialysis (HD) in Japan are currently quantified by manual survey. As this method requires much effort from medical institutions and cannot achieve 100% response, a more practical method is required. We aimed to establish a novel method for determining the static and dynamic numbers of patients treated with HD. METHODS: This observational study used the national medical billing database (termed NDB) of Japan, based on the records of the universal healthcare insurance system. Medical billing data registered in the NDB between April 2011 and March 2015 were analyzed. From 130 billion records, we extracted and analyzed records of patients who had undergone HD at least once per month. Patients' monthly condition was classified as newly initiated HD, chronic HD, or presumed death, using conditional expressions. We also investigated renal outcome and presumed survival in newly initiated HD patients. RESULTS: In the last month of the study period, 274,100 patients were identified as receiving chronic HD, which is estimated as > 95% of the number of these patients identified in the manual survey so far. The monthly data showed clear seasonality in the incidence of transient HD, which increased in winter and decreased in summer. CONCLUSION: Analysis of a large national database revealed a significant increase in transient HD in winter and decrease in summer. Applied to additional epidemiological exploratory studies or clinical research, this analytical technique would enable collection of the dynamics of almost all HD patients nationwide.

A Rare Case of Brain Metastasis of Thymic Carcinoma.

BACKGROUND: Thymic carcinoma is a rare cancer that often metastasizes to the liver and kidneys but rarely to the brain. CASE REPORT: We present a rare case of an 81-year-old woman with multiple cerebellar metastases of thymic carcinoma. She was initially diagnosed with stage IVb thymic carcinoma based on biopsy examination of a lesion in the anterior mediastinum. The patient refused to undergo treatment at the time. Six months later, she presented with gait disturbance and nausea. Contrast-enhanced magnetic resonance imaging revealed multiple cerebellar metastases. She underwent craniotomy and resection of the left cerebellar metastasis. Postoperative histological examination confirmed metastasis of the original thymic carcinoma. The patient underwent additional stereotactic radiotherapy for the cavity of the cerebellar metastasis and the small cerebellar metastatic lesions. Seven months after radiotherapy, she died due to progression of the thymic carcinoma. CONCLUSION: We believe that these findings add important information to the literature on this rare entity.

Retrieving and Analyzing Hospital Service Suspensions from Regional Healthcare Insurance Claims Data.

The geographical imbalance of the healthcare workforce is a social problem in Japan. Except for big cities, hospitals have difficulties in securing a sufficient workforce to offer healthcare services stably. For local government, hospital service suspensions are potentially an essential indicator to figure out the capacity of the regional healthcare supply. This paper proposes an algorithm that automatically identifies and classifies hospital service suspensions from insurance claims data, based on periodicity and similarity. To verify the effectiveness, we have applied the algorithm to the insurance claim dataset, which has been provided 91 regional public insurers in Japan. The case studies have confirmed that the proposed algorithm has presented an evidential picture of hospital service suspensions, which is potentially useful to understand the actual capacity of healthcare service supply in regions.

Indications and classes of outpatient antibiotic prescriptions in Japan: A descriptive study using the national database of electronic health insurance claims, 2012-2015.

OBJECTIVES: To evaluate condition-specific antibiotic prescription rates and the appropriateness of antibiotic use in outpatient settings in Japan. METHODS: Using Japan's national administrative claims database, all outpatient visits with infectious disease diagnoses were linked to reimbursed oral antibiotic prescriptions. Prescription rates stratified by age, sex, prefecture, and antibiotic category were determined for each infectious disease diagnosis. The proportions of any antibiotic prescription to all infectious disease visits and the proportions of first-line antibiotic prescriptions to all antibiotic prescriptions were calculated for each infectious disease diagnosis. RESULTS: Of the 659 million infectious disease visits between April 2012 and March 2015, antibiotics were prescribed in 266 million visits (704 prescriptions per 1000 population per year). Third-generation cephalosporins, macrolides, and quinolones accounted for 85.9% of all antibiotic prescriptions. Fifty-six percent of antibiotic prescriptions were directed toward infections for which antibiotics are generally not indicated. The diagnoses with frequent antibiotic prescription were bronchitis (184 prescriptions per 1000 population per year), viral upper respiratory infections (166), pharyngitis (104), sinusitis (52), and gastrointestinal infection (41), for which 58.3%, 40.6%, 58.9%, 53.9%, and 26.1% of visits antibiotics were prescribed, respectively. First-line antibiotics were rarely prescribed for pharyngitis (8.8%) and sinusitis (9.8%). More antibiotics were prescribed for children aged 0-9 years, adult women, and patients living in western Japan. CONCLUSIONS: Antibiotic prescription rates are high in Japan. Acute respiratory or gastrointestinal infections, which received the majority of the antibiotics generally not indicated, should be the main targets of antimicrobial stewardship intervention.

Novel Analytics Framework for Universal Healthcare Insurance Claims Database.

Medical insurance claims are useful data to offer a big-picture view and insight of a nation-wide healthcare system. Yet, formal description of the logic to analyze the claims has not been established. So far, we proposed a description scheme of analytics logic over claims database. In this paper, we propose a novel analytics framework based on the description scheme. By showing a case study, we demonstrate the effectiveness of the framework.

Enabling Patient Traceability Using Anonymized Personal Identifiers in Japanese Universal Health Insurance Claims Database.

Anonymization of medical data helps protect patient identities. However, with conventional anonymized personal identifiers it is difficult to trace patients, which hinders longitudinal analyses in insurance claim database. Herein, we describe the development of a method to identify unique patients by using partial equivalence relationships of multiple anonymized personal identifiers. By using two conventional anonymized personal identifiers, we have developed virtual patient identifiers (vPIDs) to indicate unique patients. To verify the effectiveness of the developed identifiers, we have applied vPIDs to a six-year dataset of national-level Japanese insurance claims dataset and a prefectural-level insurance claims dataset with enrollee master data. In addition, we have applied vPIDs to practical analyses of medical expenditures and doctor consultations. vPID has enabled the continued tracing of patients throughout the six-year study period, and demonstrated the validity of our method. Therefore, the proposed method can be used to improve patient traceability in insurance claims database.

Novel Analytics Framework for Universal Healthcare Insurance Database.

Medical insurance claims data is one of the most useful data sources that can offer a big-picture view of a nation-wide healthcare system. Form the viewpoint of medical policy planning, Japan's Ministry of Health, Labour and Welfare has been continuously collecting claims data. However, claims data in Japan has an ordered nested tuple format, and a method for describing the logic to analyze this form in a simple and clear manner has not been established yet. In the present work, we construct a novel analytics framework based on previous analyses that we conducted with medical researchers and design a UI that facilitates the construction of the processing logic in a simple and clear manner. By showing the execution result of typical analyses of claim data, we demonstrate the effectiveness of the developed tool.

[Case of hydrocephalus after cervical laminoplasty for cervical ossification of the posterior longitudinal ligament].

We report a rare complication of cervical laminoplasty in cervical ossification of the posterior longitudinal ligament (OPLL). A 69-year-old man suffered from gait disturbance and numbness of the bilateral hand for 6 months. He underwent C3-7 partial laminoplasty at the department of orthopedic surgery. After the operation, his symptoms immeadiately disappeared. However 1 month later, he presented with memory disturbance and gait disturbance. A computed tomography (CT) scan of head showed hydrocephalus, and cervical magnetic resonance imaging (MRI) showed fluid collection in the epidural and subcutaneous spaces. A ventriculoperitoneal shunt was performed, and it resolved the memory and gait disturbance. This is the second case report of hydrocephalus after laminoplasty for cervical OPLL.

Upper plexus thoracic outlet syndrome--case report.

A 47-year-old right-handed female became aware of proximal ache and muscle weakness in the right shoulder and elbow in 1997. Atrophy of the right biceps muscle was recognized and the right deltoid, triceps, supraspinatus, and infraspinatus muscles were weak. The Morley test and elevated arm stress test were positive. Neurolysis of the brachial plexus and anterior scalenectomy were performed via a right supraclavicular approach. An abnormal fibromuscular band was identified passing between the upper and middle trunks and constricting the middle trunk. Another scalene muscle anomaly was found passing between the C-5 and C-6 nerve roots and connecting the anterior and middle scalene muscles. These muscles were resected, and thorough neurolysis was performed around all nerves and the trunks. Postoperatively, all symptoms completely resolved and the patient was discharged 5 days after surgery. Thoracic outlet syndrome (TOS) manifests as symptoms of lower cervical nerve involvements with hypesthesia and paresthesia. However, upper plexus TOS manifests as symptoms due to the involvement of the C-5 to C-7 nerve roots, and is relatively rare. Transaxillary first rib resection is performed as the primary operation for TOS, but supraclavicular scalenectomy is effective for upper plexus TOS.