Search

Objective Tsushima mamushi (Gloydius tsushimaensis) is an endemic species of snake inhabiting only Tsushima Island, a remote Japanese island. We conducted a multicenter, retrospective study of G. tsushimaensis bites for the first time and developed a treatment algorithm that unified treatment on the island and is still in use today. Methods This is a multicenter, retrospective study comparing 72 cases from January 2005 to December 2018, before the introduction of the algorithm, and 12 cases from January 2019 to December 2020, after its introduction. Results There was no significant decrease in the maximum grade of symptoms after the introduction of the algorithm, but there was a decreasing trend (p=0.057). Conversely, the median of the maximum creatinine kinase levels was 343.5 IU/L (interquartile range: 115.5-4,745.5) before the algorithm's introduction and significantly lower (142.5; interquartile range: 111.3-163) after the algorithm's introduction (p=0.042). After the algorithm's introduction, the disseminated intravascular coagulation merger rate and the acute kidney injury incidence both dropped to 0%, from 9.7% and 6.9%, respectively, before the algorithm's introduction. There was no significant difference in the length of hospital stay before versus after the algorithm's introduction. Conclusion This study showed that the treatment algorithm can be safely and quickly applied. The algorithm's effectiveness is expected to be strengthened by the accumulation of more cases in the future.

This study aimed to investigate the relationship between transient return of spontaneous circulation (ROSC) before extracorporeal membrane oxygenation (ECMO) initiation and outcomes in out-of-hospital cardiac arrest (OHCA) patients, who were resuscitated with extracorporeal cardiopulmonary resuscitation (ECPR).This study was a secondary analysis of the SAVE-J II study, which was a retrospective multicentre registry study involving 36 participating institutions in Japan. We classified patients into two groups according to the presence or absence of transient ROSC before ECMO initiation. Transient ROSC was defined as any palpable pulse of ≥1 min before ECMO initiation. The primary outcome was favourable neurological outcomes (cerebral performance categories 1-2).Of 2,157 patients registered in the SAVE-J II study, 1,501 met the study inclusion criteria; 328 (22%) experienced transient ROSC before ECMO initiation. Patients with transient ROSC had better outcomes than those without ROSC (favourable neurological outcome, 26% vs 12%,In OHCA patients resuscitated with ECPR, transient ROSC before ECMO initiation was associated with favourable outcomes. Hence, transient ROSC is a predictor of improved outcomes after ECPR.

The purpose of our study is to identify the patterns of vectors in similar/dissimilar pairs of definition sentence created by Word2vec and doec2vec for elaboration of the terminology for Japanese Medical Device Adverse Events. 2-dimension vector space created by t-SNE showed that the pair with true positive located closer in a vector space, especially Doc2vec had a strong tendency. Comparing with Word2vec, Similar vectors in Doc2vec were close and tended to form clusters.

The purpose of our study is to identify the patterns of vectors in similar/dissimilar pairs of definition sentence created by Word2vec and doec2vec for elaboration of the terminology for Japanese Medical Device Adverse Events. 2-dimension vector space created by t-SNE showed that the pair with true positive located closer in a vector space, especially Doc2vec had a strong tendency. Comparing with Word2vec, Similar vectors in Doc2vec were close and tended to form clusters.

Gloydius tsushimaensis is an endemic species inhabiting only Tsushima, a remote Japanese island, and is a distinct species from Gloydius blomhoffii widely distributed throughout mainland Japan and Gloydius brevicaudus and Gloydius ussuriensis which are geographically distributed in South Korea. This is the first multicenter retrospective study of G. tsushimaensis bites in Japan. A study of seventy-two patients who visited the former Izuhara Hospital, the former Naka Tsushima Hospital, Tsushima Hospital, and Kamitsushima Hospital during the fourteen years from January 1, 2005, to December 31, 2018, revealed the typical clinical characteristics of G. tsushimaensis bites. Five out of seventy-two cases (6.9%) showed severe hypofibrinogenemia, in which fibrinogen levels were below 100 mg/dl, which is an unreported clinical finding for G. blomhoffii bites. Generally, when fibrinogen levels are lower than 100 mg/dl, the bleeding risk increases, and it is perilous. Severe hypofibrinogenemia cases did not improve after G. blomhoffii antivenom administration. Additionally, all five cases had disseminated intravascular coagulation, and there were two cases of acute kidney injury and one death. five cases had a median maximum creatine kinase level of 5171 IU/l (Interquartile range: 4992–41,310). Although the mechanism is not precise, coagulation tests showed that the G. tsushimaensis venom contains a thrombin-like enzyme. Based on this research, we created an algorithm for the treatment of G. tsushimaensis bites and unified the treatment methods used on the island.

Background The prevalence of extracorporeal cardiopulmonary resuscitation (ECPR) in patients with out-of-hospital cardiac arrest (OHCA) has been increasing rapidly worldwide. However, guidelines or clinical studies do not provide sufficient data on ECPR practice. The aim of this study was to provide real-world data on ECPR for patients with OHCA, including details of complications. Methods We did a retrospective database analysis of observational multicenter cohort study in Japan. Adult patients with OHCA of presumed cardiac etiology who received ECPR between 2013 and 2018 were included. The primary outcome was favorable neurological outcome at hospital discharge, defined as a cerebral performance category of 1 or 2. Results A total of 1644 patients with OHCA were included in this study. The patient age was 18–93 years (median: 60 years). Shockable rhythm in the initial cardiac rhythm at the scene was 69.4%. The median estimated low flow time was 55 min (interquartile range: 45–66 min). Favorable neurological outcome at hospital discharge was observed in 14.1% of patients, and the rate of survival to hospital discharge was 27.2%. The proportions of favorable neurological outcome at hospital discharge in terms of shockable rhythm, pulseless electrical activity, and asystole were 16.7%, 9.2%, and 3.9%, respectively. Complications were observed during ECPR in 32.7% of patients, and the most common complication was bleeding, with the rates of cannulation site bleeding and other types of hemorrhage at 16.4% and 8.5%, respectively. Conclusions In this large cohort, data on the ECPR of 1644 patients with OHCA show that the proportion of favorable neurological outcomes at hospital discharge was 14.1%, survival rate at hospital discharge was 27.2%, and complications were observed during ECPR in 32.7%.

D-Allulose is a rare sugar that exists in nature. It is a food ingredient with nearly zero calories (

We aimed to develop a reliable identification algorithm combining diagnostic codes with several treatment factors for inpatients with acute ischemic stroke (AIS) to conduct pharmacoepidemiological studies using the administrative database MID-NET® in Japan.We validated 11 identification algorithms based on 56 different diagnostic codes (International Classification of Diseases, Tenth Revision; ICD-10) using Diagnosis Procedure Combination (DPC) data combined with information on AIS therapeutic procedures added as "AND" condition or "OR" condition. The target population for this study was 366 randomly selected hospitalized patients with possible cases of AIS, defined as relevant ICD-10 codes and diagnostic imaging and prescription or surgical procedure, in three institutions between April 1, 2015 and March 31, 2017. We determined the positive predictive values (PPVs) of these identification algorithms based on comparisons with a gold standard consisting of chart reviews by experienced specialist physicians. Additionally, the sensitivities of them among 166 patients with the possible cases of AIS at a single institution were evaluated.The PPVs were 0.618 (95% confidence interval [CI]: 0.566-0.667) to 0.909 (95% CI: 0.708-0.989) and progressively increased with adding or limiting information on AIS therapeutic procedures as "AND" condition in the identification algorithms. The PPVs for identification algorithms based on diagnostic codes I63.x were 0.8. However, the sensitivities progressively decreased to a maximum of ~0.2 after adding information on AIS therapeutic procedures as "AND" condition.The identification algorithms based on the combination of appropriate ICD-10 diagnostic codes in DPC data and other AIS treatment factors may be useful to studies for AIS at a national level using MID-NET®.

We provided COVID-19 outbreak trends in South Africa during the Omicron (B.1.1.529), Delta (B.1.617.2), and Beta (B.1.351) variants outbreak periods from November 2020 to March 2022.We used the time series summary data of the COVID-19 outbreak for South Africa available in the COVID-19 data repository created by the Center for System and Science and Engineering at Johns Hopkins University and the Our World in Data database by the University of Oxford from January 2020 to March 2022. We used the joinpoint regression model with a data-driven Bayesian information criterion method for analyzing the outbreak trends. In addition, we used density ellipses and partition modeling on the outbreak data.During the Omicron outbreak period, COVID-19 cases in South Africa significantly jumped by 4.7 times from December 01 to December 08, 2021. The average daily growth rate of incidence peaked at 23,000 cases/day until December 16, 2021, which was 18.6 % higher than the peak growth during the Delta outbreak period. South Africa experienced peak growth in COVID-19 cases with 18,611 cases/day (January 04 to January 14, 2021) during the Beta outbreak period and with 19,395 cases/day (July 01 to July 11, 2021) during the Delta outbreak period. Density ellipsoid showed a significant correlation between daily cases and daily death count during the Beta and Delta outbreak period which was not prominent in the Omicron outbreak period. Comparatively higher daily death tolls were reported in days with a recovery rate of less than 89.1 % and 91.9 % in the Beta and Delta outbreak period respectively. The backlog counts may be one of the reasons for the significant increase in daily death tolls during the Omicron period.During the Omicron period, COVID-19 cases peaked growth was 18.6 % higher than the peak growth during the Delta outbreak period. Despite that fact, growth in death trends in the Omicron outbreak period was found low which might be due to the low mortality rate and case fatality proportion. The emergence of the Omicron variant once again reminds us that- "no one is safe until everyone is safe".

PURPOSE To examine the potential role of Medical Information Database Network (MID-NET® ), a newly established Japanese medical information database network, in postmarketing drug safety assessments through the characterization of its advantages and limitations in five pilot studies. METHODS The pilot studies were designed to address three major objectives in postmarketing drug safety assessments, ie, the examination of actual drug utilization, the impact of safety-related regulatory actions, and drug-associated risks. The five studies were conducted on the following topics: (a) utilization of codeine-containing products and its relationship with respiratory depression, (b) impact of a Dear Healthcare Professional letter on hypocalcemia incidence associated with denosumab (Ranmark® ) use, (c) risk of acute myocardial infarction associated with antidiabetic drug use, (d) risk of glucose metabolism disorders associated with atypical antipsychotic drug use, and (e) prospective monitoring of abnormal laboratory test results during new drug prescriptions. RESULTS The pilot studies were successfully conducted and demonstrated the value of MID-NET® in postmarketing drug safety assessments. In particular, the ability to utilize laboratory test results as objective clinical indicators is a major advantage of this database. Potential limitations include a relatively small sample size and a lack of patient-level data linkages among hospitals. CONCLUSIONS MID-NET® was confirmed to be a valuable database for postmarketing drug safety assessments. The use of laboratory test results to define clinical outcomes may allow more objective and accurate analyses to be conducted. These studies furthered our understanding of the characteristics of MID-NET® , including its advantages and limitations.

Objective: In recent years, natural language processing (NLP) techniques have progressed, and their application in the medical field has been tested. However, the use of NLP to detect symptoms from medical progress notes written in Japanese, remains limited. We aimed to detect 2 gastrointestinal symptoms that interfere with the continuation of chemotherapy—nausea/vomiting and diarrhea—from progress notes using NLP, and then to analyze factors affecting NLP. Materials and methods: In this study, 200 patients were randomly selected from 5277 patients who received intravenous injections of cytotoxic anticancer drugs at Kagawa University Hospital, Japan, between January 2011 and December 2018. We aimed to detect the first occurrence of nausea/vomiting (Group A) and diarrhea (Group B) using NLP. The NLP performance was evaluated by the concordance with a review of the physicians’ progress notes used as the gold standard. Results: Both groups showed high concordance: 83.5% (95% confidence interval [CI] 74.1-90.1) in Group A and 97.7% (95% CI 91.3-99.9) in Group B. However, the concordance was significantly better in Group B ( P = .0027). There were significantly more misdetection cases in Group A than in Group B (15.3% in Group A; 1.2% in Group B, P = .0012) due to negative findings or past history. Conclusion: We detected occurrences of nausea/vomiting and diarrhea accurately using NLP. However, there were more misdetection cases in Group A due to negative findings or past history, which may have been influenced by the physicians’ more frequent documentation of nausea/vomiting.

The purpose of this study is to extract similar term definitions used in the terminology of Japanese medical device adverse events. We employed Levenshtein and Jaro-Winkler distances as edit distances and Skip-gram, continuous-bag of words, and fast text to produce distributed representations in Word2Vec. A comparison of the accuracies of the models showed that Levenshtein distance had higher specificity whereas Skip-gram had higher sensitivity as compared to the other models.

What is known and objective Since its introduction in April 2012, denosumab has been administered to approximately 7,300 patients as of August 2012, and 32 cases of serious hypocalcaemia after denosumab administration, including two deaths, have been reported in Japan. A Dear Healthcare Professional Letter of Rapid Safety Communication ('Blue letter') was released to warn about the risks of hypocalcaemia associated with denosumab. The goal of this study therefore was to measure the impact of regulatory action on denosumab-induced hypocalcaemia in Japan by using an electronic medical information database (MID). Methods We used two different aggregated data sets based on MIDs (data sets one and two). The patients studied were those who were newly prescribed denosumab or zoledronic acid between April 2012 and September 2014. We assessed four indicators: (a) the proportion of patients with calcium supplementation at the initial denosumab treatment, (b) the proportion of patients who underwent a serum calcium test, (c) the average number of serum calcium tests performed and (d) the prevalence of hypocalcaemia. All indices were aggregated by every 3 months. To evaluate the impact of regulatory action, we used difference in difference (DID) analysis. Results and discussion The proportion of patients with calcium supplementation at the initial denosumab treatment increased year by year in both data sets. The average number of serum calcium tests increased year by year in data set two. There was a significant difference in the prevalence of hypocalcaemia in data set two. This suggests that the estimate of impact of the regulatory action may vary according to the database. In DID analysis, however, significant influences of the regulatory action on combination use with a calcium supplement were detected in both data sets. What is new and conclusion There was a significant influence on combination use of denosumab with vitamin D and/or calcium supplement in both data sets. That there was no apparent increase in the prevalence of denosumab-induced hypocalcaemia, suggests that the regulatory action had an impact in the clinical setting studied. Such regulatory actions may play an important role in the promotion of drug safety.

To examine the potential role of Medical Information Database Network (MID-NETThe pilot studies were designed to address three major objectives in postmarketing drug safety assessments, ie, the examination of actual drug utilization, the impact of safety-related regulatory actions, and drug-associated risks. The five studies were conducted on the following topics: (a) utilization of codeine-containing products and its relationship with respiratory depression, (b) impact of a Dear Healthcare Professional letter on hypocalcemia incidence associated with denosumab (RanmarkThe pilot studies were successfully conducted and demonstrated the value of MID-NETMID-NET

Purpose The purpose of this study is to evaluate the accuracy of gastrointestinal (GI) perforation ICD-10 coding in the Diagnosis Procedure Combination (DPC) database and to examine drug exposure risk factors for GI perforation. Methods A total of 100 patients with GI perforation ICD-10 codes were selected randomly from Kagawa University Hospital's DPC database between April 2011 and December 2016. Two experienced specialist physicians independently reviewed the medical records and classified cases as "definite A," "definite B," "probable," or "no GI perforation." The positive predictive values (PPVs) of "definite A/B" cases were calculated after stratification by sex, age, ICD-10 code, and diagnostic information in the DPC data. The number of prescribed drugs with side effects of GI perforation according to historical data was compared between "definite A/B" and "no GI perforation" cases. Results The overall PPV was 47.0% (95% confidence interval [CI], 36.9-57.2). However, the PPVs for the three categories of diagnostic information in the DPC data ("main diagnosis," "diagnosis causing admission," and "most resource-intensive diagnosis") were each more than 70% after excluding inappropriate patients. Additionally, the PPV focused on these three categories was 76.3% (95% CI, 59.8-88.6). Prescribed drugs with side effects of GI perforation were more frequently detected in "definite A/B" cases (P = .028). Conclusions Although the overall PPV for GI perforation based on ICD-10 code was low, our results suggest that the PPV could be improved by appropriate selection of DPC diagnosis category and that use of multiple medications enhances the risk of GI perforation.

An 84-year-old man visited our hospital with epigastralgia.Levels of hepatic and biliary enzymes and CRP were elevated, as detected by a blood test.On a CT scan, a swollen gallbladder with stones was detected.The patient was admitted to the hospital with a diagnosis of Grade I acute cholecystitis.Conservative treatment was continued with antibiotic administration and the patient was discharged from the hospital with improvement on day 6 after admission.Three months later, the patient underwent laparoscopic cholecystectomy.In the gallbladder, a 45×45 mm tumor was found.Upon pathological examination, diffuse proliferation of lymphocyte-like heterotypic cells and subserosal invasion were observed.Immunohistochemistry results were negative for MUM1 and positive for CD10 and Bcl6 markers.A malignant diffuse large B-cell lymphoma was diagnosed.We experienced a case of malignant lymphoma of the gallbladder diagnosed after surgery for acute cholecystitis, which we herein report with literature consideration.

The aim of this study was to to estimate the sample size for the assumed feasibility study of the computer-assisted input support on a clinica trial. More than 1,500 observations were required for the feasibility study with assumed settings. Further study was required for more efficient research design.

A 75-year-old man admitted for left lateral abdominal pain was found to have advanced poorly differentiated gastric adenocarcinoma with abdominal para-aortic and Virchow's lymph node metastases, which was diagnosed to be clinical Stage IV (T3N3H0M1[LYM]). As curative surgery was not deemed possible, we started chemotherapy administration using S-1 (120mg/day)administered orally for 3 weeks and cisplatin(CDDP 100mg/body)administered intravenously on day 8. After 6 courses of chemotherapy, a CT scan showed that all lymph nodes metastases had disappeared, resulting in downstaging to clinical Stage II (T3[SE]N0H0P0M0). Thus, we performed total gastrectomy, lymph node dissection(D2), and splenectomy. Histological findings showed no residual tumor cells in any of the lymph nodes. However, cancer cells remained in the primary gastric lesion. The pathological response to chemotherapy was judged to be Grade 2. The patient has been recurrence-free for 5 years after surgery.

When therapy using interferon medication for chronic hepatitis patients, various conceptual knowledge/rules will benefit for giving a treatment. The paper describes our work on cooperatively using various data mining agents including GDT-RS, learning with ordered information (LOI), and peculiarity oriented mining (POM) in a spiral discovery process with the multi-phase such as pre-processing, rule mining, and post-processing, for multi-aspect analysis of the hepatitis data and meta learning. GDT-RS is an inductive learning system for discovering decision rules. LOI discovers ordering rules and important features. POM finds peculiarity data/rules. Our methodology and experimental results show that the perspective of medical doctors will be changed from a single type of experimental data analysis towards a holistic view, by using our multi-aspect mining approach.

近年，電子カルテが普及し，診療結果を電子的に記録することが一般的になってきた．電子データの共有・二次利用のためには，記録項目・用語の標準化が必要である．我々は腹部超音波検査に関する所見項目・用語について国内の種々の教科書から取材した結果と，診療施設で入力されたデータの検討を元に，コンピュータ用にオントロジーの性質を持った用語集案を作成した．この用語集は階層構造で用語同士の関係を表しており，多くの同義語を用語集の中で利用出来るように設計した．用語集の編集には専用のツールを作成し，このツールからはClaMLと呼ばれるXMLを用いた用語集の国際的表現方法で用語集を出力出来る．この機能により，用語集を多くのシステムで半自動的に取り込むことを目指している．

In this paper, we propose a method which removes exceptional patients in a spiral manner for obtaining a definition of a disease in the form of a table of conditional probabilities and we describe its application to chronic hepatitis data. The removal is based on a risk-ratio-based criterion and can be supported by our previously developed data mining methods and medical experts. A series of experiments in which two domain experts decided exceptional patients to be removed show that our proposed method is effective and promising from various viewpoints such as obtaining new hypotheses and improving skills of domain experts. Another series of experiments in which exceptional patients were removed automatically led us to a rediscovery of a piece of knowledge, which had been reported in an article of a medical journal as the main result of the article.

This article summarizes the consensus reached at the Summit on Color in Medical Imaging held at the Food and Drug Administration (FDA) on May 8–9, 2013, co-sponsored by the FDA and ICC (International Color Consortium). The purpose of the meeting was to gather information on how color is currently handled by medical imaging systems to identify areas where there is a need for improvement, to define objective requirements, and to facilitate consensus development of best practices. Participants were asked to identify areas of concern and unmet needs. This summary documents the topics that were discussed at the meeting and recommendations that were made by the participants. Key areas identified where improvements in color would provide immediate tangible benefits were those of digital microscopy, telemedicine, medical photography (particularly ophthalmic and dental photography), and display calibration. Work in these and other related areas has been started within several professional groups, including the creation of the ICC Medical Imaging Working Group.

Summary What is known and objective The implementation of appropriate epidemiological methodology using medical information databases (MIDs) to evaluate the effects of regulatory actions has been highly anticipated. To assess scientific methods for active pharmacovigilance using MIDs, we conducted a quantitative assessment of the impact of two regulatory actions by the Japanese government: (i) restriction of use of oseltamivir in teenagers in March 2007 and (ii) caution against the co-administration of omeprazole (OPZ) with clopidogrel (CPG) in April 2010. Methods Data were obtained from four hub hospitals in Japan. We measured the seasonal proportion of patients prescribed oseltamivir to those prescribed neuraminidase inhibitors for the 2002/2003 to 2010/2011 seasons. The monthly proportion of patients co-administered OPZ and CPG (OPZ+CPG) to those prescribed CPG was measured from May 2009 to April 2011. We evaluated the changes observed with implementation of the regulatory actions. To estimate the impact of the actions, we conducted segmented regression analysis using interrupted time series data. The impact was assessed by two parameter estimates of the regression model: the change in level for short-term effects and change in trend for long-term effects. Results and discussion The use of oseltamivir in the target 10–19 years age group showed a significant and large decline (63·16%) immediately after the intervention (P = 0·0008). No change was observed in OPZ+CPG, although there was a relative inhibitory trend for OPZ+CPG compared with co-administration of lansoprazole or rabeprazole with CPG as the control group. When restricted to new users of CPG, the stratified results were consistent with the overall results. What is new and conclusion The current analysis demonstrates the effectiveness of two regulatory actions. The results of the current study indicate that MID research can contribute to assessing and improving pharmacovigilance activities.

Many conventional studies have predicted the liver fibrosis stages in chronic hepatitis C at a certain time using the clinical test results on blood and urine obtained at the same time as inputs to classifiers. However, given the mechanism of liver fibrosis progress through time-varying inflammation, it is considered to be more effective to use the time series of test results obtained from the past to the present. This study aims to extract features on the dynamics of such time series and to examine how they are effective for the prediction of the stages of liver fibrosis. We propose the combination of the mean, standard deviation, and linear predictive coding cepstrum as a feature and conduct experiments on the prediction performance of this proposed feature and competitive ones, such as the waveform and other types of spectrum estimators. The experimental results suggest the effectiveness of the proposed feature, since it consistently achieves a performance that is better than those of the other features.

Conventional studies for predicting the stage of liver fibrosis in patients with hepatitis C used classifiers such as multivariate linear regression (MLR), logistic regression (LOGR), or kernel support vector machine (KSVM). However, the prediction performance of both MLR and LOGR was not high, and KSVM does not provide the posterior probabilities of classes, nor is it easily applicable to multiclass problems. This study proposes and evaluates the use of kernel logistic regression (KLOGR), which has the advantages of LOGR and KSVM. Our experimental results showed that KLOGR achieved a higher prediction performance than the other conventional classifiers. Additionally, KLOGR can provide posterior probabilities of classes and is easily applicable to multiclass problems. Therefore, the effectiveness of KLOGR was confirmed.

Context Predicting prognosis using noninvasive and objective tools may facilitate end-of-life decisions for terminal cancer patients, their families, and other health care professionals. Objectives To investigate if the shock index (SI), along with decreased level of consciousness (DLOC), is a reliable tool for predicting short-term survival time in terminal cancer patients. Methods A two-part retrospective cohort study was performed on 670 consecutive adult hospice patients. Part 1 of the study was performed to investigate the reliability of SI and DLOC on admission and to make a simple tool for predicting survival time. Part 2 of the study was to validate the tool's reproducibility and analyze the correlation between SI, DLOC, and survival time. Results In Part 1, multivariate Cox proportional hazards analyses for all study patients revealed that SI ≥ 1.0 in patients with DLOC was a significant risk factor of death (hazard ratio 3.08; 95% CI 1.72–5.53; P = 0.000). Generalized additive models confirmed that DLOC patients with SI = 1.0 had 9.58 days of mean survival time (MST). Receiver operating characteristic curve analyses of SI in patients with DLOC revealed that a survival time of less than three days was most reliably predicted. In Part 2, an increase in SI statistically decreased survival time. The upper 95% CIs of the calculated mean survival time for DLOC patients with SI ≥ 1.0 were less than one week. Bootstrap analyses revealed that the 95% CIs of the predicted survival time were 4.54–6.18 days in DLOC patients with SI = 1.0. Conclusion An SI ≥ 1.0 along with DLOC is a highly reliable tool for predicting short-term survival time in terminal cancer patients.

In this paper, we present an evaluation of learning costs of rule evaluation models based on objective indices for an iterative rule evaluation support method in data mining post-processing. Post-processing of mined results is one of the key processes in a data mining process. However, it is difficult for human experts to find out valuable knowledge from several thousands of rules obtained with a large dataset with noises. To reduce the costs in such rule evaluation task, we have developed the rule evaluation support method with rule evaluation models, which learn from objective indices for mined classification rules and evaluations by a human expert for each rule. To estimate learning costs for predicting human interests with objective rule evaluation indices, we have done the two case studies with actual data mining results, which include different phases of human interests. With regarding to these results, we discuss about the relationship between performances of learning algorithms and human hypothesis construction process.

In this paper a new method to judge the grade of normal form for relational database is proposed based on rough sets theory. First, some concepts about INF, 2NF, 3NF and BCNF are given and the principles of rough set theory are discussed. Second, the method to judge the grade of normal forms for a given relation is analyzed using rough sets theory, and some properties of a relation satisfying some grade of normal form are obtained. The study in this paper is a new application of rough sets theory.

To analyze the laboratory data by data mining, user-centered universal tools have not been available in medicine. We analyzed 1,565,877 laboratory data of 771 patients with viral hepatitis in order to find the difference of the temporal changes in laboratory test data between Hepatitis B and Hepatitis C by the combination of temporal abstraction and data mining. The data for one patient is temporal for more than 5 years. After pretreatment the data was converted to abstract patterns and then selected into sets of data combination and rules to identify Hepatitis B or C by D2MS and LUPC which were originally produced by ourselves. Not only data pattern, but also temporal relations were considered as a part of the rules. In the course of evaluating the results by domain experts, even though there were not so remarkable hypotheses, visualization tools made it easier for them to understand the relations of the complicated rules.

This paper presents a method to support the evaluation procedure of a data mining process using human-system interaction. The post-processing of mined results is one of the key factors for successful data mining process. However, it is difficult for human experts to completely evaluate several thousands of rules from a large dataset containing noise. We have designed a method based on objective rule evaluation indices to support the rule evaluation procedure; the indices are calculated to evaluate each if-then rule mathematically. We have evaluated five representative learning algorithms to construct rule evaluation models of the actual data mining results from a chronic hepatitis data set. Further, we discuss the relationship between the transitions of the subjective criterion of a medical expert and the performances of the rule evaluation models.

In this paper, we present an integrated time-series data mining environment for medical data mining. Medical time-series data mining is one of key issues to get useful clinical knowledge from medical databases. However, users often face difficulties during such medical time-series data mining process for data preprocessing method selection/construction, mining algorithm selection, and post-processing to refine the data mining process as shown in other data mining processes. To get more valuable rules for medical experts from a time-series data mining process, we have designed an environment which integrates time- series pattern extraction methods, rule induction methods and rule evaluation methods with visual human-system interface. After implementing this environment, we have done a case study to mine time- series rules from blood/urine biochemical test database on chronic hepatitis patients. The result shows the availability to find out valuable clinical course rules based on time-series pattern extraction. Furthermore, we compared the difference of time-series pattern extraction methods with objective rule evaluation results.

Recently researchers get more and more interested in personalizing wayfinding assistance based on the inte- gration of the individual prior knowledge. A promising approach is the analysis of trajectories recorded with everyday devices. Due to particularities of the sensors, the devices, and the users we need suitable heuristics to extract meaningful data. Additionally, we need spe- cialized tools to simulate, visualize and validate the hypothesis after implementation. In this paper we will present basic considerations, requirements and heuris- tics to estimate spatial knowledge from position sensor data, and we will present our visualization and evalua- tion tool Trackr.

In this paper, we present an evaluation of learning costs of rule evaluation models based on objective indices for an iterative rule evaluation support method in data mining postprocessing. Post-processing of mined results is one of the key processes in a data mining process. However, it is difficult for human experts to completely evaluate several thousands of rules from a large dataset with noises. To reduce the costs in such rule evaluation task, we have developed the rule evaluation support method with rule evaluation models, which learn from objective indices for mined classification rules and evaluations by a human expert for each rule. To estimate learning costs for predicting human interests with objective rule evaluation indices, we have done the two case studies with actual data mining results, which include different phases of human interests. With regard to these results, we discuss about learning costs to predict real human interests with objective rule evaluation indices.

A machine learning technique called Graph-Based Induction (GBI) efficiently extracts typical patterns from graph-structured data by stepwise pair expansion (pairwise chunking). It is very efficient because of its greedy search. We have expanded GBI to construct a decision tree that can handle graph-structured data. DT-GBI constructs a decision tree while simultaneously constructing attributes for classification using GBI. In DT-GBI attributes, namely substructures useful for classification task, are constructed by GBI on the fly during the tree construction. We applied both GBI and DT-GBI to classification tasks of a real world hepatitis data. Three classification problems were solved in five experiments. In the first 4 experiments, DT-GBI was applied to build decision trees to classify 1) cirrhosis and non-cirrhosis (Experiments 1 and 2), 2) type C and type B (Experiment 3), and 3) positive and negative responses of interferon therapy (Experiment 4). As the patterns extracted in these experiments are thought discriminative, in the last experiment (Experiment 5) GBI was applied to extract descriptive patterns for interferon therapy. The preliminary results of experiments, both constructed decision trees and their predictive accuracies as well as extracted patterns, are reported in this paper. Some of the patterns match domain experts' experience and the overall results are encouraging.

In this paper, we summarize our endeavor for spiral discovery of a separate prediction model from chronic hepatitis data. We have initially proposed various learning/discovery methods including time-series decision tree, PrototypeLines, and peculiarity-oriented mining method for mining the data. This experience has motivated us to model physicians as considering typical cases with the specific disease and ruling out clearly exceptional cases. We have developed a spiral discovery system which learns a prediction model for each type of cases, and obtained promising results from experiments.

Objective: We discuss the usefulness of rule interestingness measures for medical KDD through experiments using clinical datasets, and, based on the outcomes of these experiments, also consider how to utilize these measures in postprocessing. Methods and materials: We first conducted an experiment to compare the evaluation results derived from a total of 40 various interestingness measures with those supplied by a medical expert for rules discovered in a clinical dataset on meningitis. We calculated and compared the performance of each interestingness measure to estimate a medical expert's interest using f-measure and correlation coefficient. We then conducted a similar experiment for hepatitis. Results and conclusion: The comprehensive results of experiments on meningitis and hepatitis indicate that the interestingness measures, accuracy, chi-square measure for one quadrant, relative risk, uncovered negative, and peculiarity, have a stable, reasonable performance in estimating real human interest in the medical domain. The results also indicate that the performance of interestingness measures is influenced by the certainty of a hypothesis made by the medical expert, and that the combinational use of interestingness measures will contribute to support medical experts to generate and confirm their hypotheses through human-system interaction.

There are two activities for Japanese endoscopy information system. One is for a standard terminology (Minimal Standard Terminology: MST) for endoscopy reporting. Other is Integrating Healthcare Enterprise Japan (IHE-J) for an integration of hospital information system. In IHE-J activity, the members revealed specificities of an endoscopy workflow by making a comparison with a radiology workflow. The authors will propose a scheme for systematic standardization based on our experiences in the standardization activities.

Since 1994, following the leading efforts by the European Society for Gastrointestinal Endoscopy, Organisation Mondiale d'Endoscopie Digestive (OMED) has succeeded in compiling minimal number of terms required for computer generation of digestive endoscopy reports nicknamed MST (Minimal Standard Terminology). Though with some insufficiencies, and though developed only for digestive endoscopy, MST has been the only available terminology that is globally standardized in medicine. By utilizing the merits of a unified, structured terminology that can be used in multiple languages we can utilize the data stored in different languages as a common database. For this purpose, a standing, terminology-managing organization that manages and maintains and, when required, expands the terminology on a global level, is absolutely necessary. Unfortunately, however, the organization that performs version control of MST (OMED terminology, standardization and data processing committee) is currently suspending its activity. Medical practice of the world demands more and more specialization, with resultant needs for information exchange among specialized territories. As the cooperation between endoscopy and pathology has become currently the most important problem in the Endoscopy Working Group of Integrating Healthcare Enterprise-Japan (IHE-J,) the cooperation among different specialties is essential. There are DICOM or HL7 standards as the protocols for storage, and exchange (communication) of the data, but there is yet no organization that manages the terminology itself astride different specialties. We hereby propose to establish, within IEEE, for example, a system that promotes standardization of the terminology that can transversely describe a patient, and that can control different societies and groups, as far as the terminology is concerned.

In this paper, we present the implementation of an integrated time-series data mining environment. Time-series data mining is one of key issues to get useful knowledge from databases. With mined time-series patterns, users can aware not only positive results but also negative result called risk after their observation period. However, users often face difficulties during time-series data mining process for data pre-processing method selection/construction, mining algorithm selection, and post-processing to refine the data mining process as other data mining processes. It is needed to develop a time-series data mining environment based on systematic analysis of the process. To get more valuable rules for domain experts from a time-series data mining process, we have designed an environment which integrates time-series pattern extraction methods, rule induction methods and rule evaluation methods with active human-system interaction. After implementing this environment, we have done a case study to mine time-series rules from blood and urine biochemical test database on chronic hepatitis patients. Then a physician has evaluated and refined his hypothesis on this environment. We discuss the availability of how much support to mine interesting knowledge for an expert.

In this paper, we present evaluations of learning algorithms for a novel rule evaluation support method in data mining post-processing, which is one of the key processes in a data mining process. It is difficult for human experts to evaluate many thousands of rules from a large dataset with noises completely. To reduce the costs of rule evaluation task, we have developed the rule evaluation support method with rule evaluation models, which are learned from a dataset consisted of objective indices and evaluations of a human expert for each rule. To enhance adaptability of rule evaluation models, we introduced a constructive meta-learning system to choose proper learning algorithms for constructing them. Then, we have done a case study on the meningitis data mining result, the hepatitis data mining results and rule sets from the eight UCI datasets.

This paper discusses the utilization of rule interestingness measures in medical KDD. The authors selected various interestingness measures and conducted experiments using clinical datasets to examine how they can estimate real human interest. The results indicate that some of them have a stable, reasonable estimation performance and the combinational use of interestingness measures will contribute to medical KDD. We then developed a prototype of medical KDD support user interface based on the experimental outcomes. We conducted a case study in which a medical expert tried to discover medical knowledge with the prototype. Some interesting rules were actually obtained and that indicates the potential of the user interface

In this paper, we propose a method which splits examples into typical and exceptional by mainly assuming that an example represents a case. The split is based on our previously developed data mining methods and a novel likelihood-based criterion. Such a split represents a highly intellectual activity thus the method is assumed to support the users, who are typically medical experts. Experiments with the chronic hepatitis data showed that our proposed method is effective and promising from various viewpoints.

In this paper, we give experimental evaluation of our time-series decision tree induction method under various conditions. Our time-series tree has a value (i.e. a time sequence) of a time-series attribute in its internal node, and splits examples based on dissimilarity between a pair of time sequences. Our method selects, for a split test, a time sequence which exists in data by exhaustive search based on class and shape information. It has been empirically observed that the method induces accurate and comprehensive decision trees in time-series classification, which has gaining increasing attention due to its importance in various real-world applications. The evaluation has revealed several important findings including interaction between a split test and its measure of goodness.

This research experimentally investigates the performance of conventional rule interestingness measures and discusses their usefulness for supporting KDD through human-system interaction in medical domain. We compared the evaluation results by a medical expert and those by selected sixteen kinds of interestingness measures for the rules discovered in a dataset on hepatitis. χ2 measure, recall, and accuracy demonstrated the highest performance, and specificity and prevalence did the lowest. The interestingness measures showed a complementary relationship for each other. These results indicated that some interestingness measures have the possibility to predict really interesting rules at a certain level and that the combinational use of interestingness measures will be useful. We then discussed how to combinationally utilize interestingness measures and proposed a post-processing user interface utilizing them, which supports KDD through human-system interaction.

When therapy using IFN (interferon) medication for chronic hepatitis patients, various conceptual knowledge/rules will benefit for giving a treatment. The paper describes our work on cooperatively using various data mining agents including the GDT-RS inductive learning system for discovering decision rules, the LOI (learning with ordered information) for discovering ordering rules and important features, as well as the POM (peculiarity oriented mining) for finding peculiarity data/rules, in a spiral discovery process with multi-phase such as pre-processing, rule mining, and post-processing, for multi-aspect analysis of the hepatitis data and meta learning. Our methodology and experimental results show that the perspective of medical doctors will be changed from a single type of experimental data analysis towards a holistic view, by using our multi-aspect mining approach.

We have proposed a method called Decision Tree Graph-Based Induction (DT-GBI), which constructs a classifier (decision tree) for graph-structured data while simultaneously constructing attributes for classification. Graph-Based Induction (GBI) is utilized in DT-GBI for efficiently extracting typical patterns from graph-structured data by stepwise pair expansion (pairwise chunking). Attributes, i.e., substructures useful for classification task, are constructed by GBI on the fly while constructing a decision tree in DT-GBI. We applied DT-GBI to four classification tasks of hepatitis data using only the time-series data of blood inspection and urinalysis, which was provided by Chiba University Hospital. In the first and second experiments, the stages of fibrosis were used as classes and a decision tree was constructed for discriminating patients with F4 (cirrhosis) from patients with the other stages. In the third experiment, the types of hepatitis (B and C) were used as classes, and in the fourth experiment the effectiveness of interferon therapy was used as class label. The preliminary results of experiments, both constructed decision trees and their predictive accuracies, are reported in this paper. The validity of extracted patterns is now being evaluated by the domain experts (medical doctors). Some of the patterns match experts' experience and the overall results are encouraging.

We propose a method which visualizes irregular multidimensional time-series data as a sequence of probabilistic prototypes for detecting exceptions from medical test data. Conventional visualization methods often require iterative analysis and considerable skill thus are not totally supported by a wide range of medical experts. Our PrototypeLines displays summarized information based on a probabilistic mixture model by using hue only thus is considered to exhibit novelty. The effectiveness of the summarization is pursued mainly through use of a novel information criterion. We report our endeavor with chronic hepatitis data, especially discoveries of interesting exceptions by a nonexpert and an untrained expert.

This research empirically investigates the performance of conventional rule interestingness measures and discusses their practicality for supporting KDD through human-system interaction in medical domain. We compared the evaluation results by a medical expert and those by selected measures for the rules discovered from a dataset on hepatitis. Recall, Jaccard, Kappa, CST, X2-M, and Peculiarity demonstrated the highest performance, and many measures showed a complementary trend under our experimental conditions. These results indicate that some measures can predict really interesting rules at a certain level and that their combinational use will be useful.