Min-Huei Hsu

Building a National Electronic Medical Record Exchange System - Experiences in Taiwan

There are currently 501 hospitals and about 20,000 clinics in Taiwan. The National Health Insurance (NHI) system, which is operated by the NHI Administration, uses a single-payer system and covers 99.9% of the nations total population of 23,000,000. Taiwans NHI provides people with a high degree of freedom in choosing their medical care options. However, there is the potential concern that the available medical resources will be overused. The number of doctor consultations per person per year is about 15. Duplication of laboratory tests and prescriptions are not rare either. Building an electronic medical record exchange system is a good method of solving these problems and of improving continuity in health care. In November 2009, Taiwans Executive Yuan passed the Plan for accelerating the implementation of electronic medical record systems in medical institutions (2010-2012; a 3-year plan). According to this plan, a patient can, at any hospital in Taiwan, by using his/her health insurance IC card and physicians medical professional IC card, upon signing a written agreement, retrieve all important medical records for the past 6 months from other participating hospitals. The focus of this plan is to establish the National Electronic Medical Record Exchange Centre (EEC). A hospitals information system will be connected to the EEC through an electronic medical record (EMR) gateway. The hospital will convert the medical records for the past 6 months in its EMR system into standardized files and save them on the EMR gateway. The most important functions of the EEC are to generate an index of all the XML files on the EMR gateways of all hospitals, and to provide search and retrieval services for hospitals and clinics. The EEC provides four standard inter-institution EMR retrieval services covering medical imaging reports, laboratory test reports, discharge summaries, and outpatient records. In this system, we adopted the Health Level 7 (HL7) Clinical Document Architecture (CDA) standards to generate clinical documents and Integrating the Healthcare Enterprise (IHE) Cross-enterprise Document Sharing (XDS) profile for the communication infrastructure. By December of 2014, the number of hospitals that provide an inter-institution EMR exchange service had reached 321. Hospitals that had not joined the service were all smaller ones with less than 100 beds. Inter-institution EMR exchange can make it much easier for people to access their own medical records, reduce the waste of medical resources, and improve the quality of medical care. The implementation of an inter-institution EMR exchange system faces many challenges. This article provides Taiwans experiences as a reference.

Cancer-disease associations

OBJECTIVEnCancer is the primary disease responsible for death and disability worldwide. Currently, prevention and early detection represents the best hope for cure. Knowing the expected diseases that occur with a particular cancer in advance could lead to physicians being able to better tailor their treatment for cancer. The aim of this study was to build an animated visualization tool called as Cancer Associations Map Animation (CAMA), to chart the association of cancers with other disease over time.nnnMETHODSnThe study population was collected from the Taiwan National Health Insurance Database during the period January 2000 to December 2002, 782 million outpatient visits were used to compute the associations of nine major cancers with other diseases. A motion chart was used to quantify and visualize the associations between diseases and cancers.nnnRESULTSnThe CAMA motion chart that was built successfully facilitated the observation of cancer-disease associations across ages and genders. The CAMA system can be accessed online at http://203.71.86.98/web/runq16.html.nnnCONCLUSIONnThe CAMA animation system is an animated medical data visualization tool which provides a dynamic, time-lapse, animated view of cancer-disease associations across different age groups and gender. Derived from a large, nationwide healthcare dataset, this exploratory data analysis tool can detect cancer comorbidities earlier than is possible by manual inspection. Taking into account the trajectory of cancer-specific comorbidity development may facilitate clinicians and healthcare researchers to more efficiently explore early stage hypotheses, develop new cancer treatment approaches, and identify potential effect modifiers or new risk factors associated with specific cancers.

A Probabilistic Model for Reducing Medication Errors

Background Medication errors are common, life threatening, costly but preventable. Information technology and automated systems are highly efficient for preventing medication errors and therefore widely employed in hospital settings. The aim of this study was to construct a probabilistic model that can reduce medication errors by identifying uncommon or rare associations between medications and diseases. Methods and Finding(s) Association rules of mining techniques are utilized for 103.5 million prescriptions from Taiwan’s National Health Insurance database. The dataset included 204.5 million diagnoses with ICD9-CM codes and 347.7 million medications by using ATC codes. Disease-Medication (DM) and Medication-Medication (MM) associations were computed by their co-occurrence and associations’ strength were measured by the interestingness or lift values which were being referred as Q values. The DMQs and MMQs were used to develop the AOP model to predict the appropriateness of a given prescription. Validation of this model was done by comparing the results of evaluation performed by the AOP model and verified by human experts. The results showed 96% accuracy for appropriate and 45% accuracy for inappropriate prescriptions, with a sensitivity and specificity of 75.9% and 89.5%, respectively. Conclusions We successfully developed the AOP model as an efficient tool for automatic identification of uncommon or rare associations between disease-medication and medication-medication in prescriptions. The AOP model helps to reduce medication errors by alerting physicians, improving the patients’ safety and the overall quality of care.

The incidence rate and mortality of malignant brain tumors after 10 years of intensive cell phone use in Taiwan.

The issue of whether cell phone usage can contribute toward the development of brain tumors has recently been reignited with the International Agency for Research on Cancer classifying radiofrequency electromagnetic fields as ‘possibly’ carcinogenic to humans in a WHO report. To our knowledge, this is the largest study reporting on the incidence and mortality of malignant brain tumors after long-term use of the cell phone by more than 23 million users. A population-based study was carried out the numbers of cell phone users were collected from the official statistics provided by the National Communication Commission. According to National Cancer Registry, there were 4 incidences and 4 deaths due to malignant neoplasms in Taiwan during the period 2000–2009. The 10 years of observational data show that the intensive user rate of cell phones has had no significant effect on the incidence rate or on the mortality of malignant brain tumors in Taiwan. In conclusion, we do not detect any correlation between the morbidity/mortality of malignant brain tumors and cell phone use in Taiwan. We thus urge international agencies to publish only confirmatory reports with more applicable conclusions in public. This will help spare the public from unnecessary worries.

Outcome prediction after moderate and severe head injury using an artificial neural network.

Many studies have constructed predictive models for outcome after traumatic brain injury. Most of these attempts focused on dichotomous result, such as alive vs dead or good outcome vs poor outcome. If we want to predict more specific levels of outcome, we need more sophisticated models. We conducted this study to determine if artificial neural network modeling would predict outcome in five levels of Glasgow Outcome Scale (death, persistent vegetative state, severe disability, moderate disability, and good recovery) after moderate to severe head injury. The database was collected from a nation-wide epidemiological study of traumatic brain injury in Taiwan from July 1, 1995 to June 30, 1998. There were total 18583 records in this database and each record had thirty-two parameters. After pruning the records with minor cases (GCS 13) and missing data in the 132 variables, the number of cases decreased from 18583 to 4460. A step-wise logistic regression was applied to the remaining data set and 10 variables were selected as being statically significant in predicting outcome. These 10 variables were used as the input neurons for constructing neural network. Overall, 75.8% of predictions of this model were correct, 14.6% were pessimistic, and 9.6% optimistic. This neural network model demonstrated a significant difference of performance between different levels of Glasgow Outcome Scale. The prediction performance of dead or good recovery is best and the prediction of vegetative state is worst. An artificial neural network may provide a useful second opinion to assist neurosurgeon to predict outcome after traumatic brain injury.