Yi-Ju Tseng

A multiple measurements case-based reasoning method for predicting recurrent status of liver cancer patients

Abstract In general, the studies introducing the medical predictive models which frequently handle time series data by direct matching between pairs of features within sequences during calculation of similarity may have following limitations: (1) direct matching may not be a suitable matching because these paired cases by a fixed order may not be with the most similar temporal information, and (2) when two patients have different numbers of multiple cases, some cases may be ignored. For example, one patient with four cases and another one with five cases, only first four cases of these two patients are paired and the left one case may be ignored. In this paper, in order to dynamically determine matching pairs among cases and pair all cases between two patients, we propose a multiple measurements case-based reasoning (MMCBR) to be used for building liver cancer recurrence predictive models. MMCBR and single measurement case-based reasoning (SingleCBR) are evaluated and compared. According to experiment results in this study, the performance of MMCBR models is better than that of SingleCBR models. Multiple measurements accumulated during a period of time do have benefits for building predictive models with improved performance based on this proposed MMCBR method.

A Reliable User Authentication and Key Agreement Scheme for Web-Based Hospital-Acquired Infection Surveillance Information System

With the rapid development of the Internet, both digitization and electronic orientation are required on various applications in the daily life. For hospital-acquired infection control, a Web-based Hospital-acquired Infection Surveillance System was implemented. Clinical data from different hospitals and systems were collected and analyzed. The hospital-acquired infection screening rules in this system utilized this information to detect different patterns of defined hospital-acquired infection. Moreover, these data were integrated into the user interface of a signal entry point to assist physicians and healthcare providers in making decisions. Based on Service-Oriented Architecture, web-service techniques which were suitable for integrating heterogeneous platforms, protocols, and applications, were used. In summary, this system simplifies the workflow of hospital infection control and improves the healthcare quality. However, it is probable for attackers to intercept the process of data transmission or access to the user interface. To tackle the illegal access and to prevent the information from being stolen during transmission over the insecure Internet, a password-based user authentication scheme is proposed for information integrity.

Recurrence predictive models for patients with hepatocellular carcinoma after radiofrequency ablation using support vector machines with feature selection methods

BACKGROUND AND OBJECTIVE Recurrence of hepatocellular carcinoma (HCC) is an important issue despite effective treatments with tumor eradication. Identification of patients who are at high risk for recurrence may provide more efficacious screening and detection of tumor recurrence. The aim of this study was to develop recurrence predictive models for HCC patients who received radiofrequency ablation (RFA) treatment. METHODS From January 2007 to December 2009, 83 newly diagnosed HCC patients receiving RFA as their first treatment were enrolled. Five feature selection methods including genetic algorithm (GA), simulated annealing (SA) algorithm, random forests (RF) and hybrid methods (GA+RF and SA+RF) were utilized for selecting an important subset of features from a total of 16 clinical features. These feature selection methods were combined with support vector machine (SVM) for developing predictive models with better performance. Five-fold cross-validation was used to train and test SVM models. RESULTS The developed SVM-based predictive models with hybrid feature selection methods and 5-fold cross-validation had averages of the sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and area under the ROC curve as 67%, 86%, 82%, 69%, 90%, and 0.69, respectively. CONCLUSIONS The SVM derived predictive model can provide suggestive high-risk recurrent patients, who should be closely followed up after complete RFA treatment.

Multiple-Time-Series Clinical Data Processing for Classification With Merging Algorithm and Statistical Measures

A description of patient conditions should consist of the changes in and combination of clinical measures. Traditional data-processing method and classification algorithms might cause clinical information to disappear and reduce prediction performance. To improve the accuracy of clinical-outcome prediction by using multiple measurements, a new multiple-time-series data-processing algorithm with period merging is proposed. Clinical data from 83 hepatocellular carcinoma (HCC) patients were used in this research. Their clinical reports from a defined period were merged using the proposed merging algorithm, and statistical measures were also calculated. After data processing, multiple measurements support vector machine (MMSVM) with radial basis function (RBF) kernels was used as a classification method to predict HCC recurrence. A multiple measurements random forest regression (MMRF) was also used as an additional evaluation/classification method. To evaluate the data-merging algorithm, the performance of prediction using processed multiple measurements was compared to prediction using single measurements. The results of recurrence prediction by MMSVM with RBF using multiple measurements and a period of 120 days (accuracy 0.771, balanced accuracy 0.603) were optimal, and their superiority to the results obtained using single measurements was statistically significant (accuracy 0.626, balanced accuracy 0.459, P <; 0.01). In the cases of MMRF, the prediction results obtained after applying the proposed merging algorithm were also better than single-measurement results (P <; 0.05). The results show that the performance of HCC-recurrence prediction was significantly improved when the proposed data-processing algorithm was used, and that multiple measurements could be of greater value than single

Web-based newborn screening system for metabolic diseases: machine learning versus clinicians.

Background A hospital information system (HIS) that integrates screening data and interpretation of the data is routinely requested by hospitals and parents. However, the accuracy of disease classification may be low because of the disease characteristics and the analytes used for classification. Objective The objective of this study is to describe a system that enhanced the neonatal screening system of the Newborn Screening Center at the National Taiwan University Hospital. The system was designed and deployed according to a service-oriented architecture (SOA) framework under the Web services .NET environment. The system consists of sample collection, testing, diagnosis, evaluation, treatment, and follow-up services among collaborating hospitals. To improve the accuracy of newborn screening, machine learning and optimal feature selection mechanisms were investigated for screening newborns for inborn errors of metabolism. Methods The framework of the Newborn Screening Hospital Information System (NSHIS) used the embedded Health Level Seven (HL7) standards for data exchanges among heterogeneous platforms integrated by Web services in the C# language. In this study, machine learning classification was used to predict phenylketonuria (PKU), hypermethioninemia, and 3-methylcrotonyl-CoA-carboxylase (3-MCC) deficiency. The classification methods used 347,312 newborn dried blood samples collected at the Center between 2006 and 2011. Of these, 220 newborns had values over the diagnostic cutoffs (positive cases) and 1557 had values that were over the screening cutoffs but did not meet the diagnostic cutoffs (suspected cases). The original 35 analytes and the manifested features were ranked based on F score, then combinations of the top 20 ranked features were selected as input features to support vector machine (SVM) classifiers to obtain optimal feature sets. These feature sets were tested using 5-fold cross-validation and optimal models were generated. The datasets collected in year 2011 were used as predicting cases. Results The feature selection strategies were implemented and the optimal markers for PKU, hypermethioninemia, and 3-MCC deficiency were obtained. The results of the machine learning approach were compared with the cutoff scheme. The number of the false positive cases were reduced from 21 to 2 for PKU, from 30 to 10 for hypermethioninemia, and 209 to 46 for 3-MCC deficiency. Conclusions This SOA Web service–based newborn screening system can accelerate screening procedures effectively and efficiently. An SVM learning methodology for PKU, hypermethioninemia, and 3-MCC deficiency metabolic diseases classification, including optimal feature selection strategies, is presented. By adopting the results of this study, the number of suspected cases could be reduced dramatically.

A Web-Based Data-Querying Tool Based on Ontology-Driven Methodology and Flowchart-Based Model

Background Because of the increased adoption rate of electronic medical record (EMR) systems, more health care records have been increasingly accumulating in clinical data repositories. Therefore, querying the data stored in these repositories is crucial for retrieving the knowledge from such large volumes of clinical data. Objective The aim of this study is to develop a Web-based approach for enriching the capabilities of the data-querying system along the three following considerations: (1) the interface design used for query formulation, (2) the representation of query results, and (3) the models used for formulating query criteria. Methods The Guideline Interchange Format version 3.5 (GLIF3.5), an ontology-driven clinical guideline representation language, was used for formulating the query tasks based on the GLIF3.5 flowchart in the Protégé environment. The flowchart-based data-querying model (FBDQM) query execution engine was developed and implemented for executing queries and presenting the results through a visual and graphical interface. To examine a broad variety of patient data, the clinical data generator was implemented to automatically generate the clinical data in the repository, and the generated data, thereby, were employed to evaluate the system. The accuracy and time performance of the system for three medical query tasks relevant to liver cancer were evaluated based on the clinical data generator in the experiments with varying numbers of patients. Results In this study, a prototype system was developed to test the feasibility of applying a methodology for building a query execution engine using FBDQMs by formulating query tasks using the existing GLIF. The FBDQM-based query execution engine was used to successfully retrieve the clinical data based on the query tasks formatted using the GLIF3.5 in the experiments with varying numbers of patients. The accuracy of the three queries (ie, “degree of liver damage,” “degree of liver damage when applying a mutually exclusive setting,” and “treatments for liver cancer”) was 100% for all four experiments (10 patients, 100 patients, 1000 patients, and 10,000 patients). Among the three measured query phases, (1) structured query language operations, (2) criteria verification, and (3) other, the first two had the longest execution time. Conclusions The ontology-driven FBDQM-based approach enriched the capabilities of the data-querying system. The adoption of the GLIF3.5 increased the potential for interoperability, shareability, and reusability of the query tasks.

A Web-Based Multidrug-Resistant Organisms Surveillance and Outbreak Detection System with Rule-Based Classification and Clustering

Background The emergence and spread of multidrug-resistant organisms (MDROs) are causing a global crisis. Combating antimicrobial resistance requires prevention of transmission of resistant organisms and improved use of antimicrobials. Objectives To develop a Web-based information system for automatic integration, analysis, and interpretation of the antimicrobial susceptibility of all clinical isolates that incorporates rule-based classification and cluster analysis of MDROs and implements control chart analysis to facilitate outbreak detection. Methods Electronic microbiological data from a 2200-bed teaching hospital in Taiwan were classified according to predefined criteria of MDROs. The numbers of organisms, patients, and incident patients in each MDRO pattern were presented graphically to describe spatial and time information in a Web-based user interface. Hierarchical clustering with 7 upper control limits (UCL) was used to detect suspicious outbreaks. The system’s performance in outbreak detection was evaluated based on vancomycin-resistant enterococcal outbreaks determined by a hospital-wide prospective active surveillance database compiled by infection control personnel. Results The optimal UCL for MDRO outbreak detection was the upper 90% confidence interval (CI) using germ criterion with clustering (area under ROC curve (AUC) 0.93, 95% CI 0.91 to 0.95), upper 85% CI using patient criterion (AUC 0.87, 95% CI 0.80 to 0.93), and one standard deviation using incident patient criterion (AUC 0.84, 95% CI 0.75 to 0.92). The performance indicators of each UCL were statistically significantly higher with clustering than those without clustering in germ criterion (P < .001), patient criterion (P = .04), and incident patient criterion (P < .001). Conclusion This system automatically identifies MDROs and accurately detects suspicious outbreaks of MDROs based on the antimicrobial susceptibility of all clinical isolates.

Incidence and Patterns of Extended-Course Antibiotic Therapy in Patients Evaluated for Lyme Disease

BACKGROUND Most patients with Lyme disease (LD) can be treated effectively with 2-4 weeks of antibiotics. The Infectious Disease Society of America guidelines do not currently recommend extended treatment even in patients with persistent symptoms. METHODS To estimate the incidence of extended use of antibiotics in patients evaluated for LD, we retrospectively analyzed claims from a nationwide US health insurance plan in 14 high-prevalence states over 2 periods: 2004-2006 and 2010-2012. RESULTS As measured by payer claims, the incidence of extended antibiotic therapy among patients evaluated for LD was higher in 2010-2012 (14.72 per 100 000 person-years; n = 684) than in 2004-2006 (9.94 per 100 000 person-years; n = 394) (P < .001). Among these patients, 48.8% were treated with ≥2 antibiotics in 2010-2012 and 29.9% in 2004-2006 (P < .001). In each study period, a distinct small group of providers (roughly 3%-4%) made the diagnosis in >20% of the patients who were evaluated for LD and prescribed extended antibiotic treatment. CONCLUSIONS Insurance claims data suggest that the use of extended courses of antibiotics and multiple antibiotics in the treatment of LD has increased in recent years.

A web-based hospital-acquired infection surveillance information system

A web-based hospital-acquired infection surveillance system (WHISS) was implemented in a 2200-beds medical center in Taiwan. Clinical data from hospital information system, laboratory information system and others were collected and analyzed. The hospital-acquired infection decision guidelines of WHISS utilize this information to detect 9 patterns of defined hospital-acquired urinary tract infection. Moreover, these data were integrated into a signal entry point user interface to assist physicians and healthcare providers in making decision. We use web services techniques based on Service-Oriented Architecture (SOA), which are suitable for integrating heterogeneous platforms, protocols, and applications. The WHISS detects 81.9% candidates of hospital-acquired infection event in real time and provides user-friendly interface to infection control nurses. In conclusion, the WHISS simplifies the workflow of hospital infection control, and improves the healthcare quality.

A new scheme for strain typing of methicillin-resistant Staphylococcus aureus on the basis of matrix-assisted laser desorption ionization time-of-flight mass spectrometry by using machine learning approach

Methicillin-resistant Staphylococcus aureus (MRSA), one of the most important clinical pathogens, conducts an increasing number of morbidity and mortality in the world. Rapid and accurate strain typing of bacteria would facilitate epidemiological investigation and infection control in near real time. Matrix-assisted laser desorption ionization-time of flight (MALDI-TOF) mass spectrometry is a rapid and cost-effective tool for presumptive strain typing. To develop robust method for strain typing based on MALDI-TOF spectrum, machine learning (ML) is a promising algorithm for the construction of predictive model. In this study, a strategy of building templates of specific types was used to facilitate generating predictive models of methicillin-resistant Staphylococcus aureus (MRSA) strain typing through various ML methods. The strain types of the isolates were determined through multilocus sequence typing (MLST). The area under the receiver operating characteristic curve (AUC) and the predictive accuracy of the models were compared. ST5, ST59, and ST239 were the major MLST types, and ST45 was the minor type. For binary classification, the AUC values of various ML methods ranged from 0.76 to 0.99 for ST5, ST59, and ST239 types. In multiclass classification, the predictive accuracy of all generated models was more than 0.83. This study has demonstrated that ML methods can serve as a cost-effective and promising tool that provides preliminary strain typing information about major MRSA lineages on the basis of MALDI-TOF spectra.