A Continuous Registry of Medical Record, Patient Input, and Epidemiological Data of Patients With Ulcerative Colitis: a Multicentre, Prospective, Observational Clinical Registry Study in Japan.

BACKGROUND: This registry aims to allow for a prospective non-interventional observational study of ulcerative colitis. This will facilitate monitoring of the current state of ulcerative colitis in Japan and improving the long-term disease course and adverse events associated with current treatment options. METHODS: Inclusion of patients from five centres in Japan is planned. The study is expected to take place from July 15, 2020, to November 30, 2024. Background, demographics, and medical history/information will be collected from electronic medical records at enrolment. Medical information including medications, laboratory data, and disease activity will be collected automatically from electronic medical records throughout the study. Patient-reported quality of life data will be collected directly from patients via smartphone. Efficacy endpoints (clinical remission rate, clinical improvement rate, and endoscopic healing rate) and safety endpoints (incidence of adverse events and specific ulcerative colitis-related events) will be collected according to treatment administered. Treatment categories include no treatment, 5-aminosalicylic acids, corticosteroids, immunomodulators, immunosuppressants, anti-tumour necrosis alpha agents, cytapheresis, Janus kinase inhibitors, anti-integrin antibodies, and anti-interleukin-12/23 antibodies. CONCLUSIONS: The dataset will include cross-sectional and longitudinal data and is expected to capture the state of ulcerative colitis in Japan. Patients will be included on a large scale, and the registry will be established automatically from electronic medical records and direct patient input, facilitating the accurate recording of medical information for patients with ulcerative colitis in Japan and minimizing limitations intrinsic to databases that require manual data entry, such as the burden on participating investigators and entry of data with errors/typos.

A Novel Kidney Failure Prediction Model in Individuals with CKD: Impact of Serum Bilirubin Levels.

CONTEXT: Predicting the progression of chronic kidney disease (CKD) to end-stage kidney disease (ESKD) is crucial for improving patient outcomes. OBJECTIVE: To reveal the highly predictive activity of serum bilirubin levels for the progression of CKD to ESKD, and to develop and validate a novel ESKD prediction model incorporating serum bilirubin levels. METHODS: We assessed the relative importance of 20 candidate predictors for ESKD, including serum bilirubin levels, in a CKD cohort (15< eGFR <60 mL/min/1.73 m2), and subsequently developed a prediction model using the selected variables. The development cohort comprised 4,103 individuals with CKD who underwent follow-up at Kyushu University Hospital, Japan, from 2008 to 2018. The primary outcome was incident ESKD, defined as an eGFR <15 mL/min/1.73 m2, chronic dialysis, or renal transplantation. RESULTS: The mean follow-up time was 7.0 ± 4.2 years, during which 489 individuals (11.9%) progressed to ESKD. The Cox proportional hazard model selected eGFR, serum bilirubin, proteinuria, age, diabetes, gender, hypertension, serum albumin, and hemoglobin in order of their importance. The predictive performance of the model was optimized by incorporating these 9 variables in discrimination evaluated by time-dependent area under the curve (AUC). This model also demonstrated excellent calibration. Additionally, this model exhibited excellent predictive performance in both discrimination (2-year AUC: 0.943, 5-year AUC: 0.935) and calibration in a validation cohort (n=2,799). CONCLUSION: Serum bilirubin levels were strong predictors for the progression of CKD to ESKD. Our novel model that incorporates serum bilirubin levels could accurately predict ESKD in individuals with CKD.

Development of Machine Learning Prediction Models for Self-Extubation After Delirium Using Emergency Department Data.

Delirium is common in the emergency department, and once it develops, there is a risk of self-extubation of drains and tubes, so it is critical to predict delirium before it occurs. Machine learning was used to create two prediction models in this study: one for predicting the occurrence of delirium and one for predicting self-extubation after delirium. Each model showed high discriminative performance, indicating the possibility of selecting high-risk cases. Visualization of predictors using Shapley additive explanation (SHAP), a machine learning interpretability method, showed that the predictors of delirium were different from those of self-extubation after delirium. Data-driven decisions, rather than empirical decisions, on whether or not to use physical restraints or other actions that cause patient suffering will result in improved value in medical care.

Development of artificial intelligence prognostic model for surgically resected non-small cell lung cancer.

There are great expectations for artificial intelligence (AI) in medicine. We aimed to develop an AI prognostic model for surgically resected non-small cell lung cancer (NSCLC). This study enrolled 1049 patients with pathological stage I-IIIA surgically resected NSCLC at Kyushu University. We set 17 clinicopathological factors and 30 preoperative and 22 postoperative blood test results as explanatory variables. Disease-free survival (DFS), overall survival (OS), and cancer-specific survival (CSS) were set as objective variables. The eXtreme Gradient Boosting (XGBoost) was used as the machine learning algorithm. The median age was 69 (23-89) years, and 605 patients (57.7%) were male. The numbers of patients with pathological stage IA, IB, IIA, IIB, and IIIA were 553 (52.7%), 223 (21.4%), 100 (9.5%), 55 (5.3%), and 118 (11.2%), respectively. The 5-year DFS, OS, and CSS rates were 71.0%, 82.8%, and 88.7%, respectively. Our AI prognostic model showed that the areas under the curve of the receiver operating characteristic curves of DFS, OS, and CSS at 5 years were 0.890, 0.926, and 0.960, respectively. The AI prognostic model using XGBoost showed good prediction accuracy and provided accurate predictive probability of postoperative prognosis of NSCLC.

Impact of postoperative complications on long-term survival in bladder cancer patients.

OBJECTIVE: To determine the impact of postoperative complications on long-term survival outcomes in patients with bladder cancer undergoing radical cystectomy. METHODS: This retrospective multi-institutional study included 766 bladder cancer patients who underwent radical cystectomy between 2011 and 2017. Patient characteristics, perioperative outcomes, all complications within 90 days after surgery and survival outcomes were collected. Each complication was graded based on the Clavien-Dindo system, and grouped using a standardized grouping method. The Comprehensive Complication Index, which incorporates all complications into a single formula weighted by their severity, was utilized. Overall survival and recurrence-free survival (local, distant or urothelial recurrences) were stratified by Comprehensive Complication Index (high: ≥26.2; low: <26.2). A multivariate model was utilized to identify independent prognostic factors. RESULTS: The incidence of any and major complications (≥Clavien-Dindo grade III) was 70 and 24%, respectively. In terms of Comprehensive Complication Index, 34% (261/766) of the patients had ≥26.2. Patients with Comprehensive Complication Index ≥ 26.2 had shorter overall survival (4-year, 59.5 vs. 69.8%, respectively, log-rank test, P = 0.0037) and recurrence free survival (51.9 vs. 60.1%, respectively, P = 0.0234), than those with Comprehensive Complication Index < 26.2. The Cox multivariate model identified the age, performance status, pT-stage, pN-stage and higher CCI (overall survival: HR = 1.35, P = 0.0174, recurrence-free survival: HR = 1.26, P = 0.0443) as independent predictors of both overall survivial and recurrence-free survival. CONCLUSIONS: Postoperative complications assessed by Comprehensive Complication Index had adverse effects on long-term survival outcomes. Physicians should be aware that major postoperative complications can adversely affect long-term disease control.

Impact of the pretreatment prognostic nutritional index on the survival after first-line immunotherapy in non-small-cell lung cancer patients.

BACKGROUND: Immunotherapy has become a standard-of-care for patients with non-small-cell lung cancer (NSCLC). Although several biomarkers, such as programmed cell death-1, have been shown to be useful in selecting patients likely to benefit from immune checkpoint inhibitors (ICIs), more useful and reliable ones should be investigated. The prognostic nutritional index (PNI) is a marker of the immune and nutritional status of the host, and is derived from serum albumin level and peripheral lymphocyte count. Although several groups reported its prognostic role in patients with NSCLC receiving a single ICI, there exist no reports which have demonstrated its role in the first-line ICI combined with or without chemotherapy. MATERIALS AND METHODS: Two-hundred and eighteen patients with NSCLC were included in the current study and received pembrolizumab alone or chemoimmunotherapy as the first-line therapy. Cutoff value of the pretreatment PNI was set as 42.17. RESULTS: Among 218 patients, 123 (56.4%) had a high PNI (≥42.17), while 95 (43.6%) had a low PNI (<42.17). A significant association was observed between the PNI and both the progression-free survival (PFS; hazard ratio [HR] = 0.67, 95% confidence interval [CI]: 0.51-0.88, p = 0.0021) and overall survival (OS; HR = 0.46, 95% CI: 0.32-0.67, p < 0.0001) in the entire population, respectively. The multivariate analysis identified the pretreatment PNI as an independent prognosticator for the PFS (p = 0.0011) and OS (p < 0.0001), and in patients receiving either pembrolizumab alone or chemoimmunotherapy, the pretreatment PNI remained an independent prognostic factor for the OS (p = 0.0270 and 0.0006, respectively). CONCLUSION: The PNI might help clinicians appropriately identifying patients with better treatment outcomes when receiving first-line ICI therapy.

Artificial intelligence-derived gut microbiome as a predictive biomarker for therapeutic response to immunotherapy in lung cancer: protocol for a multicentre, prospective, observational study.

INTRODUCTION: Immunotherapy is the fourth leading therapy for lung cancer following surgery, chemotherapy and radiotherapy. Recently, several studies have reported about the potential association between the gut microbiome and therapeutic response to immunotherapy. Nevertheless, the specific composition of the gut microbiome or combination of gut microbes that truly predict the efficacy of immunotherapy is not definitive. METHODS AND ANALYSIS: The present multicentre, prospective, observational study aims to discover the specific composition of the gut microbiome or combination of gut microbes predicting the therapeutic response to immunotherapy in lung cancer using artificial intelligence. The main inclusion criteria are as follows: (1) pathologically or cytologically confirmed metastatic or postoperative recurrent lung cancer including non-small cell lung cancer and small cell lung cancer; (2) age≥20 years at the time of informed consent; (3) planned treatment with immunotherapy including combination therapy and monotherapy, as the first-line immunotherapy; and (4) ability to provide faecal samples. In total, 400 patients will be enrolled prospectively. Enrolment will begin in 2021, and the final analyses will be completed by 2024. ETHICS AND DISSEMINATION: The study protocol was approved by the institutional review board of each participating centre in 2021 (Kyushu Cancer Center, IRB approved No. 2021-13, 8 June 2021 and Kyushu Medical Center, IRB approved No. 21-076, 31 August 2021). Study results will be disseminated through peer-reviewed journals and national and international conferences. TRIAL REGISTRATION NUMBER: UMIN000046428.

Laurel Attenuates Dexamethasone-Induced Skeletal Muscle Atrophy In Vitro and in a Rat Model.

Prevention of muscle atrophy contributes to improved quality of life and life expectancy. In this study, we investigated the effects of laurel, selected from 34 spices and herbs, on dexamethasone (DEX)-induced skeletal muscle atrophy and deciphered the underlying mechanisms. Co-treatment of C2C12 myotubes with laurel for 12 h inhibited the DEX-induced expression of intracellular ubiquitin ligases-muscle atrophy F-box (atrogin-1/MAFbx) and muscle RING finger 1 (MuRF1)-and reduction in myotube diameter. Male Wistar rats were supplemented with 2% laurel for 17 days, with DEX-induced skeletal muscle atrophy occurring in the last 3 days. Laurel supplementation inhibited the mRNA expression of MuRF1, regulated DNA damage and development 1 (Redd1), and forkhead box class O 1 (Foxo1) in the muscles of rats. Mechanistically, we evaluated the effects of laurel on the cellular proteolysis machinery-namely, the ubiquitin/proteasome system and autophagy-and the mTOR signaling pathway, which regulates protein synthesis. These data indicated that the amelioration of DEX-induced skeletal muscle atrophy induced by laurel, is mainly mediated by the transcriptional inhibition of downstream factors of the ubiquitin-proteasome system. Thus, laurel may be a potential food ingredient that prevents muscle atrophy.

Comparative study of postoperative complications after radical cystectomy during the past two decades in Japan: Radical cystectomy remains associated with significant postoperative morbidities.

OBJECTIVES: During the past 2 decades, in order to improve perioperative and oncological outcomes, a minimally invasive approach, neoadjuvant chemotherapy (NAC), and an enhanced postoperative recovery program after surgery have been introduced into routine clinical practice of radical cystectomy (RC). Our aim was to examine the differences in clinical practice and postoperative complications after RC by comparing our previous and current cohorts. MATERIALS AND METHODS: A retrospective multi-institutional study. We collected all complications within 90 days after surgery between 2011 and 2017 (current cohort), and categorized them according to a standardized methodology. Then, we compared the outcomes with those in our previous study (previous cohort, 1997-2010). A multivariate logistic regression model was utilized to determine predictors of complications in the current cohort. RESULTS: A total of 838 patients were newly collected (current cohort), and 919 from the previous cohort were included in the subsequent analyses. In the current cohort, the rate of performing NAC was significantly higher (13% vs. 4%, respectively, P < 0.0001), and 26% (222/838) underwent laparoscopic RC (LRC, without robotic assistance: n = 210, with robotic assistance: n = 12). There was no significant difference in the overall complication [69% (580/838) vs. 68% (629/919), respectively, P = 0.7284] or major complication (Grades 3-5) [25% (211/838) vs. 22% (201/919), respectively, P = 0.1022] rates between the 2 cohorts. In both cohorts, the most frequent categories were infectious, gastrointestinal, wound-related, and genitourinary. In the current cohort, the performance status (odds ratio, OR = 2.11, P = 0.0013) and operative time (OR = 1.003, P = 0.0016) remained significant predictors of major complications. NAC was not associated with any or major complications. CONCLUSIONS: Surgical complications related to RC still remain significant problems, despite the recent improvements in surgical techniques and perioperative care. NAC did not increase the complications.

Machine learning for classification of postoperative patient status using standardized medical data.

BACKGROUND AND OBJECTIVE: Real-world evidence is defined as clinical evidence regarding the use and potential benefits or risks of a medical product derived from real-world data analyses. Standardization and structuring of data are necessary to analyze medical real-world data collected from different medical institutions. An electronic message and repository have been developed to link electronic medical records in this research project, which has simplified the data integration. Therefore, this paper proposes an analysis method and learning health systems to determine the priority of clinical intervention by clustering and visualizing time-series and prioritizing patient outcomes and status during hospitalization. METHODS: Common data items for reimbursement (Diagnosis Procedure Combination [DPC]) and clinical pathway data were examined in this project at each participating institution that runs the verification test. Long-term hospitalization data were analyzed using the data stored in the cloud platform of the institutions' repositories using multiple machine learning methods for classification, visualization, and interpretation. RESULTS: The ePath platform contributed to integrate the standardized data from multiple institutions. The distribution of DPC items or variances could be confirmed by clustering, temporal tendency through the directed graph, and extracting variables that contributed to the prediction and evaluation of SHapley Additive Explanation effects. Constipation was determined to be the risk factor most strongly related to long-term hospitalization. Drainage management was identified as a factor that can improve long-term hospitalization. These analyses effectively extracted patient status to provide feedback to the learning health system. CONCLUSIONS: We successfully generated evidence of medical processes by gathering patient status, medical purposes, and patient outcomes with high data quality from multiple institutions, which were difficult with conventional electronic medical records. Regarding the significant analysis results, the learning health system will be used on this project to provide feedback to each institution, operate it for a certain period, and analyze and re-evaluate it.

A functional learning health system in Japan: Experience with processes and information infrastructure toward continuous health improvement.

Introduction and definition of the term Learning Health System (LHS) appears to have occurred initially around 2007. Prior to this and the introduction of electronic health records (EHR), a predecessor could be found in the Clinical Pathways concept as a standard medical care plan and a tool to improve medical quality. Since 1997, Japan's Saiseikai Kumamoto Hospital (SKH) has been studying and implementing Clinical Pathways. In 2010, they implemented EHR, which facilitated the collection of structured data in common templates that aligned with outcome measurements defined through Japan's Society of Clinical Pathways. For each patient at this hospital, variances from the desired outcomes have been recorded, producing volumes of structured data in formats that could readily be aggregated and analyzed. A visualization tool was introduced to display graphs on the home page of the EHR such that each patient can be compared to similar patients. Knowledge learned from patient care is shared regularly through Clinical Pathways meetings that are supported by all staff within the hospital. The SKH experience over the past two decades is worth exploring further in the context of the development of a fully functional LHS and the attributes/characteristics thereof. In this report, the SKH experience and processes are compared with previously published attributes of a fully functional LHS (ie, characteristics of an LHS that can indicate maturity). Specific examples of the SKH system are detailed with respect to leveraging knowledge gained to change performance that improves patient care as prescribed by learning health cycles. The SKH experience and its information infrastructure and culture exemplify a functional LHS, which is now being expanded to additional hospitals with the hope that it can be scaled and serve as a solid platform for measures aimed at improving medical care, thus establishing broader and more global learning health systems.

Prognostic value of postoperative decrease in serum albumin on surgically resected early-stage non-small cell lung carcinoma: A multicenter retrospective study.

BACKGROUND: Preoperative nutritional status is an important host-related prognostic factor for non-small cell lung carcinoma (NSCLC); however, the significance of postoperative changes in nutritional status remains unclear. This study aimed to elucidate the significance of postoperative decreases in serum albumin (ΔAlb) on the outcomes of early-stage NSCLC. METHODS: We analyzed 443 training cohort (TC) and 642 validation cohort (VC) patients with pStage IA NSCLC who underwent surgery and did not recur within 1 year. We measured preoperative serum albumin levels (preAlb) and postoperative levels 1 year after surgery (postAlb), and calculated ΔAlb as (preAlb - postAlb)/preAlb × 100%. A cutoff value of 11% for ΔAlb was defined on the basis of the receiver operating characteristic curve for the TC. RESULTS: Patients were divided into ΔAlb-Decreased and ΔAlb-Stable groups, including 100 (22.6%) and 343 (77.4%) in the TC, and 58 (9.0%) and 584 (90.1%) in the VC. ΔAlb-Decreased was associated with male sex (p = 0.0490), smoking (p = 0.0156), and non-adenocarcinoma (p<0.0001) in the TC, and pT1b (p = 0.0169) and non-adenocarcinoma (p = 0.0251) in the VC. Multivariable analysis identified ΔAlb as an independent prognostic factor for disease-free survival (DFS) and overall survival (OS) in both cohorts (VC: DFS, HR = 1.9, 95%CI: 1.10-3.15, p = 0.0197; OS, HR = 2.0, 95%CI: 1.13-3.45, p = 0.0173). Moreover, subgroup analysis demonstrated that the prognostic value of ΔAlb was consistent for age, sex, smoking history, surgical procedure, and histological type. CONCLUSION: We demonstrated a negative impact of postoperative decrease of the serum albumin on the prognosis of patients with early-stage NSCLC. Postoperative changes in nutritional status might be important in NSCLC outcomes.

Impact of a learning health system on acute care and medical complications after intracerebral hemorrhage.

INTRODUCTION: Patients with stroke often experience pneumonia during the acute stage after stroke onset. Oral care may be effective in reducing the risk of stroke-associated pneumonia (SAP). We aimed to determine the changes in oral care, as well as the incidence of SAP, in patients with intracerebral hemorrhage, following implementation of a learning health system in our hospital. METHODS: We retrospectively analyzed the data of 1716 patients with intracerebral hemorrhage who were hospitalized at a single stroke center in Japan between January 2012 and December 2018. Data were stratified on the basis of three periods of evolving oral care: period A, during which conventional, empirically driven oral care was provided (n = 725); period B, during which standardized oral care was introduced, with SAP prophylaxis based on known risk factors (n = 469); and period C, during which oral care was risk-appropriate based on learning health system data (n = 522). Logistic regression analysis was performed to evaluate associations between each of the three treatment approaches and the risk of SAP. RESULTS: Among the included patients, the mean age was 71.3 ± 13.6 years; 52.6% of patients were men. During the course of each period, the frequency of oral care within 24 hours of admission increased (P < .001), as did the adherence rate to oral care ≥3 times per day (P < .001). After adjustment for confounding factors, a change in the risk of SAP was not observed in period B; however, the risk significantly decreased in period C (odds ratio 0.61; 95% confidence interval 0.43-0.87) compared with period A. These associations were maintained for SAP diagnosed using strict clinical criteria or after exclusion of 174 patients who underwent neurosurgical treatment. CONCLUSIONS: Risk-appropriate care informed by the use of learning health system data could improve care and potentially reduce the risk of SAP in patients with intracerebral hemorrhage in the acute stage.

Prognostic Impact of Albumin-bilirubin (ALBI) Grade on Non-small Lung Cell Carcinoma: A Propensity-score Matched Analysis.

BACKGROUND/AIM: Albumin-bilirubin (ALBI) grade is an indicator of liver dysfunction and is useful for predicting postoperative prognosis of hepatocellular carcinomas. However, the significance of ALBI grade in non-small cell lung carcinoma (NSCLC) has not been elucidated. PATIENTS AND METHODS: We analyzed 947 patients with pStage IA-IIIA NSCLC. We divided patients into ALBI grade 1 and grade 2/3 groups. We then analyzed the association of ABLI grade with clinicopathological characteristics and prognosis in NSCLC by using propensity-score matching. RESULTS: ALBI grade 2/3 was significantly associated with older age, male sex, advanced pT status, and histological type. Even after propensity-score matching, ALBI grade 2/3 patients had significantly worse cancer-specific survival (CSS) than ALBI grade 1 patients (5-year CSS: 87.3% versus 92.8%; p=0.0247). In multivariate analysis, ALBI grade 2/3 was an independent predictor of CSS (HR=1.9; 95%CI=1.11-3.11; p=0.0177). CONCLUSION: ALBI grade was an independent prognostic factor in surgically resected NSCLC.

The Development of an Electronic Phenotyping Algorithm for Identifying Rhabdomyolysis Patients in the MID-NET Database.

We aimed to develop rhabdomyolysis (RB) phenotyping algorithms using machine learning techniques and to create subphenotyping algorithms to identify RB patients who lack RB diagnosis. Two pattern algorithms, one with a focus on improving predictive value and one focused on improving sensitivity, were finally created and had a high area under the curve value of 0.846. Although we were unable to create subphenotyping algorithms, an attempt to detect unknown RB patients is important for epidemiological studies.

Effect of Governance Functionality for Data Standardization Management of the Medical Information Database Network Project.

Data standardiztion an important aspect to ensure data quality for utilizing large-scale, medical information databases such as the Medical Information Database Network (MID-NET) Project in Japan. We established a governance center to assess the consistency of standard codes across MID-NET-cooperating medical institutions. Moreover, we developed a real-time validation tool and determined its effect in improving data quality in medical institutions by providing a central feedback on the detected differences in standard disease-name codes.

Evaluating the impact of regulatory action on denosumab-induced hypocalcaemia in Japan.

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.

Graph Clustering System for Text-Based Records in a Clinical Pathway.

The progressive digitization of medical records has resulted in the accumulation of large amounts of data. Electronic medical data include structured numerical data and unstructured text data. Although text-based medical record processing has been researched, few studies contribute to medical practice. The analysis of unstructured text data can improve medical processes. Hence, this study presents a clustering approach for detecting typical patient's condition from text-based medical record of clinical pathway. In this approach, the sentences in a cluster are merged to generate a "sentence graph" of the cluster after classified feature word by Louvain method. An analysis of real text-based medical records indicates that sentence graphs can represent the medical treatment and patient's condition in a medical process. This method could help the standardization of text-based medical records and the recognition of feature medical processes for improving medical treatment.

Choroidal Thickness Evaluation Before and After Hemodialysis in Patients With and Without Diabetes.

PURPOSE: We evaluated the effect of hemodialysis on the choroidal thickness in patients with and without diabetes who have end-stage kidney disease (ESKD). METHODS: Forty-one patients with ESKD were recruited and divided into two groups: those with ESKD due to diabetic nephropathy (DM group, 37 eyes of 20 patients) and those with nondiabetic ESKD (NDM group, 40 eyes of 21 patients). Using spectral-domain optical coherence tomography (SD-OCT), the subfoveal choroidal thickness (SCT) was measured before and after hemodialysis, and the change ratio (ΔSCT [%]) was calculated. RESULTS: The SCT decreased in all eyes after hemodialysis. The ΔSCT value in the DM group (-12.6 ± 2.7%) was significantly (P = 0.00027) larger than that in the NDM group (-6.9 ± 2.3%). Moreover, the ΔSCT per body fluid removal (BFR [L]) in the DM group was significantly (P = 0.013) greater than in the NDM group. In the DM group, the mean ΔSCT in the eyes treated with panretinal photocoagulation (PRP; n = 19) was significantly (P = 0.035) larger than that in eyes not treated with PRP (n = 18). The relationship between the ΔSCT and BFR was not significant (R² = 0.0038, P = 0.80) in the DM group but was significant (R² = 0.54, P = 0.00013) in the NDM group. CONCLUSIONS: The current results may reflect that systemic fluid accumulation has a greater effect on the diabetic choroid, probably due to damage to the choroidal vasculature, in patients with ESKD.

Temporal Relation Extraction in Outcome Variances of Clinical Pathways.

Recently the clinical pathway has progressed with digitalization and the analysis of activity. There are many previous studies on the clinical pathway but not many feed directly into medical practice. We constructed a mind map system that applies the spanning tree. This system can visualize temporal relations in outcome variances, and indicate outcomes that affect long-term hospitalization.