Electrodeposited Manganese Dioxides and Their Composites as Electrocatalysts for Energy Conversion Reactions.

Enhancing the efficiencies of electrochemical reactions for converting renewable energy into clean chemical fuels as well as generating clean energy is critical to achieving carbon neutrality. However, this enhancement can be achieved using materials that are not constrained by resource limitations and those that can be converted into devices in a scalable manner, preferably for industrial applications. This review explores the applications of electrochemically deposited manganese dioxides (MnO2) and their composites as electrochemical catalysts for oxygen evolution (OER) and hydrogen evolution reactions for converting renewable energy into chemical fuels. It also explores their applications as electrochemical catalysts for oxygen reduction reaction (ORR) and bifunctional OER/ORR for the efficient operation of fuel cells and metal-air batteries, respectively. Manganese is the second most abundant transition metal in the Earth's crust, and electrodeposition represents a binder-free and scalable technique for fabricating devices (electrodes). To propose an improved catalyst design, the studies on the electrodeposition mechanism of MnO2 as well as the fabrication techniques for MnO2-based nanocomposites accumulated in the development of electrodes for supercapacitors are also included in this review.

Enhancing the Functionalities of Personal Health Record Systems: Empirical Study Based on the HL7 Personal Health Record System Functional Model Release 1.

Background: The increasing demand for personal health record (PHR) systems is driven by individuals' desire to actively manage their health care. However, the limited functionality of current PHR systems has affected users' willingness to adopt them, leading to lower-than-expected usage rates. The HL7 (Health Level Seven) PHR System Functional Model (PHR-S FM) was proposed to address this issue, outlining all possible functionalities in PHR systems. Although the PHR-S FM provides a comprehensive theoretical framework, its practical effectiveness and applicability have not been fully explored. Objective: This study aimed to design and develop a tethered PHR prototype in accordance with the guidelines of the PHR-S FM. It sought to explore the feasibility of applying the PHR-S FM in PHR systems by comparing the prototype with the results of previous research. Methods: The PHR-S FM profile was defined to meet broad clinical data management requirements based on previous research. We designed and developed a PHR prototype as a web application using the Fast Healthcare Interoperability Resources R4 (FHIR) and Logical Observation Identifiers Names and Codes (LOINC) coding system for interoperability and data consistency. We validated the prototype using the Synthea dataset, which provided realistic synthetic medical records. In addition, we compared the results produced by the prototype with those of previous studies to evaluate the feasibility and implementation of the PHR-S FM framework. Results: The PHR prototype was developed based on the PHR-S FM profile. We verified its functionality by demonstrating its ability to synchronize data with the FHIR server, effectively managing and displaying various health data types. Validation using the Synthea dataset confirmed the prototype's accuracy, achieving 100% coverage across 1157 data items. A comparison with the findings of previous studies indicated the feasibility of implementing the PHR-S FM and highlighted areas for future research and improvements. Conclusions: The results of this study offer valuable insights into the potential for practical application and broad adoption of the PHR-S FM in real-world health care settings.

Achievement of guideline-recommended target blood pressure is associated with reducing the risk of hemorrhagic and ischemic stroke in Japanese coronary artery disease patients -the CLIDAS study.

The Japanese Society of Hypertension have established a blood pressure (BP) target of 130/80 mmHg for patients with coronary artery disease (CAD). We evaluated the data of 8793 CAD patients in the Clinical Deep Data Accumulation System database who underwent cardiac catheterization at six university hospitals and the National Cerebral and Cardiovascular Center (average age 70 ± 11 years, 78% male, 43% with acute coronary syndrome [ACS]). Patients were divided into two groups based on whether or not they achieved the guideline-recommended BP of <130/80 mmHg. We analyzed the relationship between BP classification and major adverse cardiac and cerebral event (MACCE) separately in two groups: those with ACS and those with chronic coronary syndrome (CCS). During an average follow-up period of 33 months, 710 MACCEs occurred. A BP below 130/80 mmHg was associated with fewer MACCEs in both the overall (hazard ratio [HR] 0.83, 95% confidence interval [CI] 0.70-1.00, p = 0.048) and the ACS group (HR 0.67, 95%CI 0.51-0.88, p = 0.003). In particular, stroke events were also lower among those with a BP below 130/80 mmHg in both the overall (HR 0.69, 95%CI 0.53-0.90, p = 0.006) and ACS groups (HR 0.44, 95%CI 0.30-0.67, p < 0.001). In conclusion, the achievement of BP guidelines was associated with improved outcomes in CAD patients, particularly in reducing stroke risk among those with ACS.

Change in pulse pressure and cardiovascular outcomes after percutaneous coronary intervention: The CLIDAS study.

Background: Limited data exist on the prognostic value of changes in pulse pressure (PP, the difference between systolic and diastolic blood pressure) during hospitalization for patients with coronary artery disease who have undergone percutaneous coronary intervention (PCI). Methods: In the Clinical Deep Data Accumulation System (CLIDAS), we studied 8,708 patients who underwent PCI. We aimed to examine the association between discharge PP and cardiovascular outcomes. PP was measured before PCI and at discharge. Patients were divided into five groups (quintiles) based on the change in PPQ1 (-18.0 ± 9.9 mmHg), Q2 (-3.8 ± 2.6), Q3 (reference; 3.7 ± 2.0), Q4 (11.3 ± 2.6), and Q5 (27.5 ± 11.2). We then analyzed the relationship between PP change and outcomes. Results: The mean patient age was 70 ± 11 years, with 6,851 (78 %) men and 3,786 (43 %) having acute coronary syndrome. U-shaped relationships were observed for the incidence rates of major adverse cardiac or cerebrovascular events (MACCE, a composite endpoint of cardiovascular death, myocardial infarction, and stroke), revascularization, and hospitalization for heart failure (HF). After adjusting for confounding factors, higher PP at discharge was associated with an increased risk of MACCE (adjusted hazard ratio 1.41; 95 %CI, 1.06-1.87 in Q5 [73.9 ± 9.3 mmHg]). Evaluating PP change revealed a U-shaped association with MACCE (1.50; 1.11-2.02 in Q1 and 1.47; 0.98-2.20 in Q5). Additionally, Q5 had a higher risk for hospitalization for HF (1.37; 1.00-1.88). Conclusions: Our findings demonstrate a U-shaped association between changes in PP and cardiovascular outcomes. This data suggests the significance of blood pressure control during hospitalization for patients who have undergone PCI.

Corrigendum to "Impact of heart failure severity and major bleeding events after percutaneous coronary intervention on subsequent major adverse cardiac events" [Int. J. Cardiol. Cardiovasc. Risk and Prev. 2023 Jun 25:18:200193].

[This corrects the article DOI: 10.1016/j.ijcrp.2023.200193.].

Relationship between the number of drugs used during percutaneous coronary intervention and adverse events in patients with chronic coronary syndrome: Analysis of CLIDAS database.

Background: Polypharmacy is associated with an increased risk of adverse events due to the higher number of drugs used. This is particularly notable in patients with chronic coronary syndrome (CCS), who are known to use a large number of drugs. Therefore, we investigated polypharmacy in patients with CCS, using CLIDAS, a multicenter database of patients who underwent percutaneous coronary intervention. Method and results: Between 2017 and 2020, 1411 CCS patients (71.5 ± 10.5 years old; 77.3 % male) were enrolled. The relationship between cardiovascular events occurring during the median follow-up of 514 days and the number of drugs at the time of PCI was investigated. The median number of drugs prescribed was nine. Major adverse cardiovascular events (MACE), defined as cardiovascular death, myocardial infarction, stroke, heart failure, transient ischemic attack, or unstable angina, occurred in 123 patients, and all-cause mortality occurred in 68 patients. For each additional drug, the adjusted hazard ratios for MACE and all-cause mortality increased by 2.069 (p = 0.003) and 1.102 (p = 0.010). The adjusted hazard ratios for MACE and all-cause mortality were significantly higher in the group using nine or more drugs compared to the group using eight or fewer drugs (1.646 and 2.253, both p < 0.001). Conclusion: This study showed that an increase in the number of drugs used for CCS may be associated with MACE and all-cause mortality. In patients with CCS, it might be beneficial to minimize the number of medications as much as possible, while managing comorbidities and using guideline-recommended drugs.

GPT-Based Model for Concise Summaries of Patient Health Information.

Although Patient Health Records (PHRs) are vital tools for patients, enabling them to access and manage health information, it remains challenging for doctors and patients to gather a swift overview of a patient's health status based on the extensive information included in the PHR. Our study introduces a generative pre-trained transformer-based language model to summarize health information documented in previously developed PHRs efficiently. By fine-tuning the model, we achieved results comparable to those of other studies in this domain, despite utilizing a smaller dataset. This data-to-text application represents a novel method that can be expected to promote enhanced information management in the medical field.

Implementation of the World Health Organization Minimum Dataset for Emergency Medical Teams to Create Disaster Profiles for the Indonesian SATUSEHAT Platform Using Fast Healthcare Interoperability Resources: Development and Validation Study.

Background: The National Disaster Management Agency (Badan Nasional Penanggulangan Bencana) handles disaster management in Indonesia as a health cluster by collecting, storing, and reporting information on the state of survivors and their health from various sources during disasters. Data were collected on paper and transferred to Microsoft Excel spreadsheets. These activities are challenging because there are no standards for data collection. The World Health Organization (WHO) introduced a standard for health data collection during disasters for emergency medical teams (EMTs) in the form of a minimum dataset (MDS). Meanwhile, the Ministry of Health of Indonesia launched the SATUSEHAT platform to integrate all electronic medical records in Indonesia based on Fast Healthcare Interoperability Resources (FHIR). Objective: This study aims to implement the WHO EMT MDS to create a disaster profile for the SATUSEHAT platform using FHIR. Methods: We extracted variables from 2 EMT MDS medical records-the WHO and Association of Southeast Asian Nations (ASEAN) versions-and the daily reporting form. We then performed a mapping process to match these variables with the FHIR resources and analyzed the gaps between the variables and base resources. Next, we conducted profiling to see if there were any changes in the selected resources and created extensions to fill the gap using the Forge application. Subsequently, the profile was implemented using an open-source FHIR server. Results: The total numbers of variables extracted from the WHO EMT MDS, ASEAN EMT MDS, and daily reporting forms were 30, 32, and 46, with the percentage of variables matching FHIR resources being 100% (30/30), 97% (31/32), and 85% (39/46), respectively. From the 40 resources available in the FHIR ID core, we used 10, 14, and 9 for the WHO EMT MDS, ASEAN EMT MDS, and daily reporting form, respectively. Based on the gap analysis, we found 4 variables in the daily reporting form that were not covered by the resources. Thus, we created extensions to address this gap. Conclusions: We successfully created a disaster profile that can be used as a disaster case for the SATUSEHAT platform. This profile may standardize health data collection during disasters.

Protein Cryoprotectant Ability of the Aqueous Zwitterionic Solution.

Protein cryopreservation is important for the long-term storage of unstable proteins. Recently, we found that N-acetylglucosaminyltransferase-V (GnT-V) can be cryopreserved in a deep freezer without temperature control using a dilute binary aqueous solution of 3-(1-(2-(2-methoxyethoxy)ethyl)imidazol-3-io)butane-1-carboxylate (OE2imC3C) [10 wt %, mole fraction of solute (x) = 7.75 × 10-3], an artificial zwitterion. However, it is unclear which solvent properties are required in these media to preserve unstable proteins, such as GnT-V. In this study, we investigated the melting phenomena and solution structure of dilute binary aqueous OE2imC3C solutions [x = 0-2.96 × 10-2 (0-30 wt %)] using differential scanning calorimetry (DSC) and Raman and Fourier transform infrared (FTIR) spectroscopies combined with molecular dynamics (MD) simulation to compare the cryoprotectant ability of OE2imC3C with two general cryoprotectants (CPAs), glycerol and dimethyl sulfoxide. DSC results indicated that aqueous OE2imC3C solutions can be melted at lower temperatures with less energy than the control CPA solution, with increasing x, primarily due to OE2imC3C having a higher content of unfrozen water molecules. Moreover, Raman and FTIR results showed that the high content of unfrozen water molecules in aqueous OE2imC3C solutions was due to the hydration around the ionic parts (the COO- group and imidazolium ring) and the OCH2CH2O segment. In addition, the MD simulation results showed that there were fewer structured water molecules around the OCH2CH2O segment than the hydration water molecules around the ionic parts. These solvent properties suggest that dilute aqueous OE2imC3C solutions are effective in preventing freezing, even in a deep freezer. Therefore, this medium has the potential to act as a novel cryoprotectant for proteins in biotechnology and biomedical fields.

BNP level predicts bleeding event in patients with heart failure after percutaneous coronary intervention.

OBJECTIVE: This study aimed to investigate the association between heart failure (HF) severity measured based on brain natriuretic peptide (BNP) levels and future bleeding events after percutaneous coronary intervention (PCI). BACKGROUND: The Academic Research Consortium for High Bleeding Risk presents a bleeding risk assessment for antithrombotic therapy in patients after PCI. HF is a risk factor for bleeding in Japanese patients. METHODS: Using an electronic medical record-based database with seven tertiary hospitals in Japan, this retrospective study included 7160 patients who underwent PCI between April 2014 and March 2020 and who completed a 3-year follow-up and were divided into three groups: no HF, HF with high BNP level and HF with low BNP level. The primary outcome was bleeding events according to the Global Use of Streptokinase and t-PA for Occluded Coronary Arteries classification of moderate and severe bleeding. The secondary outcome was major adverse cardiovascular events (MACE). Furthermore, thrombogenicity was measured using the Total Thrombus-Formation Analysis System (T-TAS) in 536 consecutive patients undergoing PCI between August 2013 and March 2017 at Kumamoto University Hospital. RESULTS: Multivariate Cox regression showed that HF with high BNP level was significantly associated with bleeding events, MACE and all-cause death. In the T-TAS measurement, the thrombogenicity was lower in patients with HF with high BNP levels than in those without HF and with HF with low BNP levels. CONCLUSIONS: HF with high BNP level is associated with future bleeding events, suggesting that bleeding risk might differ depending on HF severity.

Implementation of a Patient Summary Web Application According to the International Patient Summary and Validation in Common Use Cases in Japan.

BACKGROUND: The application of standardized patient summaries would reduce the risk of information overload and related problems for physicians and nurses. Although the International Patient Summary (IPS) standard has been developed, disseminating its applications has challenges, including data conversion of existing systems and development of application matching with common use cases in Japan. This study aimed to develop a patient summary application that summarizes and visualizes patient information accumulated by existing systems. METHODS: We converted clinical data from the Standardized Structured Medical Information eXchange version 2 (SS-MIX2) storage at Tohoku University Hospital into the Health Level 7 Fast Healthcare Interoperability Resource (FHIR) repository. Subsequently, we implemented a patient summary web application concerning the IPS and evaluated 12 common use cases of the discharge summary. RESULTS: The FHIR resources of seven of the necessary IPS sections were successfully converted from existing SS-MIX2 data. In the main view of the application we developed, all the minimum necessary patient information was summarized and visualized. All types of mandatory or required sections in the IPS and all structured information items of the discharge summary were displayed. Of the discharge summary, 75% of sections and 61.7% of information items were completely displayed, matching 12 common use cases in Japan. CONCLUSIONS: We implemented a patient summary application that summarizes and visualizes patient information accumulated by existing systems and is evaluated in common use cases in Japan. Efficient sharing of the minimum necessary patient information for physicians is expected to reduce information overload, workload, and burnout.

Prediction of respiratory failure risk in patients with pneumonia in the ICU using ensemble learning models.

The aim of this study was to develop early prediction models for respiratory failure risk in patients with severe pneumonia using four ensemble learning algorithms: LightGBM, XGBoost, CatBoost, and random forest, and to compare the predictive performance of each model. In this study, we used the eICU Collaborative Research Database (eICU-CRD) for sample extraction, built a respiratory failure risk prediction model for patients with severe pneumonia based on four ensemble learning algorithms, and developed compact models corresponding to the four complete models to improve clinical practicality. The average area under receiver operating curve (AUROC) of the models on the test sets after ten random divisions of the dataset and the average accuracy at the best threshold were used as the evaluation metrics of the model performance. Finally, feature importance and Shapley additive explanation values were introduced to improve the interpretability of the model. A total of 1676 patients with pneumonia were analyzed in this study, of whom 297 developed respiratory failure one hour after admission to the intensive care unit (ICU). Both complete and compact CatBoost models had the highest average AUROC (0.858 and 0.857, respectively). The average accuracies at the best threshold were 75.19% and 77.33%, respectively. According to the feature importance bars and summary plot of the predictor variables, activetx (indicates whether the patient received active treatment), standard deviation of prothrombin time-international normalized ratio, Glasgow Coma Scale verbal score, age, and minimum oxygen saturation and respiratory rate were important. Compared with other ensemble learning models, the complete and compact CatBoost models have significantly higher average area under the curve values on the 10 randomly divided test sets. Additionally, the standard deviation (SD) of the compact CatBoost model is relatively small (SD:0.050), indicating that the performance of the compact CatBoost model is stable among these four ensemble learning models. The machine learning predictive models built in this study will help in early prediction and intervention of respiratory failure risk in patients with pneumonia in the ICU.

Comprehensive evaluation of machine learning algorithms for predicting sleep-wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability.

Introduction: Perinatal women tend to have difficulties with sleep along with autonomic characteristics. This study aimed to identify a machine learning algorithm capable of achieving high accuracy in predicting sleep-wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability (HRV). Methods: Nine HRV indicators (features) and sleep-wake conditions of 154 pregnant women were measured for 1 week, from the 23rd to the 32nd weeks of pregnancy. Ten machine learning and three deep learning methods were applied to predict three types of sleep-wake conditions (wake, shallow sleep, and deep sleep). In addition, the prediction of four conditions, in which the wake conditions before and after sleep were differentiated-shallow sleep, deep sleep, and the two types of wake conditions-was also tested. Results and Discussion: In the test for predicting three types of sleep-wake conditions, most of the algorithms, except for Naïve Bayes, showed higher areas under the curve (AUCs; 0.82-0.88) and accuracy (0.78-0.81). The test using four types of sleep-wake conditions with differentiation between the wake conditions before and after sleep also resulted in successful prediction by the gated recurrent unit with the highest AUC (0.86) and accuracy (0.79). Among the nine features, seven made major contributions to predicting sleep-wake conditions. Among the seven features, "the number of interval differences of successive RR intervals greater than 50 ms (NN50)" and "the proportion dividing NN50 by the total number of RR intervals (pNN50)" were useful to predict sleep-wake conditions unique to pregnancy. These findings suggest alterations in the vagal tone system specific to pregnancy.

Impact of heart failure severity and major bleeding events after percutaneous coronary intervention on subsequent major adverse cardiac events.

Background: Heart failure (HF) is associated with a high bleeding risk after percutaneous coronary intervention (PCI). Additionally, major bleeding events increase the risk of subsequent major adverse cardiac events (MACE). However, whether brain natriuretic peptide (BNP) levels and major bleeding events following PCI are associated with MACE and all-cause death remains unknown. This study aimed to investigate the impact of HF severity or bleeding on subsequent MACE and all-cause death. Methods: The Clinical Deep Data Accumulation System (CLIDAS), a multicenter database involving seven hospitals in Japan, was developed to collect data from electronic medical records. This retrospective analysis included 7160 patients who underwent PCI between April 2014 and March 2020 and completed a three-year follow-up. Patients were divided according to the presence of HF with high BNP (HFhBNP) (>100 pg/ml) and major bleeding events within 30 days post-PCI (30-day bleeding): HFhBNP with bleeding (n = 14), HFhBNP without bleeding (n = 370), non-HFhBNP with bleeding (n = 74), and non-HFhBNP without bleeding (n = 6702). Results: In patients without 30-day bleeding, HFhBNP was a risk factor for MACE (hazard ratio, 2.19; 95% confidence interval, 1.56-3.07) and all-cause death (hazard ratio, 1.60; 95% confidence interval, 1.60-2.23). Among HFhBNP patients, MACE incidence was higher in patients with 30-day bleeding than in those without bleeding, but the difference was not significant (p = 0.075). The incidence of all-cause death was higher in patients with bleeding (p = 0.001). Conclusions: HF with high BNP and bleeding events in the early stage after PCI might be associated with subsequent MACE and all-cause death.

Validation study on definition of cause of death in Japanese claims data.

Identifying the cause of death is important for the study of end-of-life patients using claims data in Japan. However, the validity of how cause of death is identified using claims data remains unknown. Therefore, this study aimed to verify the validity of the method used to identify the cause of death based on Japanese claims data. Our study population included patients who died at two institutions between January 1, 2018 and December 31, 2019. Claims data consisted of medical data and Diagnosis Procedure Combination (DPC) data, and five definitions developed from disease classification in each dataset were compared with death certificates. Nine causes of death, including cancer, were included in the study. The definition with the highest positive predictive values (PPVs) and sensitivities in this study was the combination of "main disease" in both medical and DPC data. For cancer, these definitions had PPVs and sensitivities of > 90%. For heart disease, these definitions had PPVs of > 50% and sensitivities of > 70%. For cerebrovascular disease, these definitions had PPVs of > 80% and sensitivities of> 70%. For other causes of death, PPVs and sensitivities were < 50% for most definitions. Based on these results, we recommend definitions with a combination of "main disease" in both medical and DPC data for cancer and cerebrovascular disease. However, a clear argument cannot be made for other causes of death because of the small sample size. Therefore, the results of this study can be used with confidence for cancer and cerebrovascular disease but should be used with caution for other causes of death.

Sex Differences in Long-Term Outcomes in Patients With Chronic Coronary Syndrome After Percutaneous Coronary Intervention　- Insights From a Japanese Real-World Database Using a Storage System.

BACKGROUND: Several studies have reported some sex differences in patients with coronary artery diseases. However, the results regarding long-term outcomes in patients with chronic coronary syndrome (CCS) are inconsistent. Therefore, the present study investigated sex differences in long-term outcomes in patients with CCS after percutaneous coronary intervention (PCI).Methods and Results: This was a retrospective, multicenter cohort study. We enrolled patients with CCS who underwent PCI between April 2013 and March 2019 using the Clinical Deep Data Accumulation System (CLIDAS) database. The primary outcome was major adverse cardiovascular events (MACE), defined as a composite of cardiovascular death, non-fatal myocardial infarction, or hospitalization for heart failure. In all, 5,555 patients with CCS after PCI were included in the analysis (4,354 (78.4%) men, 1,201 (21.6%) women). The median follow-up duration was 917 days (interquartile range 312-1,508 days). The incidence of MACE was not significantly different between the 2 groups (hazard ratio [HR] 1.20; 95% confidential interval [CI] 0.97-1.47; log-rank P=0.087). After performing multivariable Cox regression analyses on 4 different models, there were still no differences in the incidence of MACE between women and men. CONCLUSIONS: There were no significant sex differences in MACE in patients with CCS who underwent PCI and underwent multidisciplinary treatments.

Relationships Among Heart Rate, ß-Blocker Dosage, and Prognosis in Patients With Coronary Artery Disease in a Real-World Database Using a Multimodal Data Acquisition System.

BACKGROUND: The optimal heart rate (HR) and optimal dose of ß-blockers (BBs) in patients with coronary artery disease (CAD) have been unclear. We sought to clarify the relationships among HR, BB dose, and prognosis in patients with CAD using a multimodal data acquisition system.Methods and Results: We evaluated the data for 8,744 CAD patients who underwent cardiac catheterization from 6 university hospitals and the National Cerebral and Cardiovascular Center and who were registered using the Clinical Deep Data Accumulation System. Patients were divided into quartile groups based on their HR at discharge: Q1 (HR <60 beats/min), Q2 (HR 60-66 beats/min), Q3 (HR 67-74 beats/min), and Q4 (HR ≥75 beats/min). Among patients with acute coronary syndrome (ACS) and patients with chronic coronary syndrome (CCS), those in Q4 (HR ≥75 beats/min) had a significantly greater incidence of major adverse cardiac and cerebral events (MACCE) compared with those in Q1 (ACS patients: hazard ratio 1.65, P=0.001; CCS patients: hazard ratio 1.45, P=0.019). Regarding the use of BBs (n=4,964), low-dose administration was significantly associated with MACCE in the ACS group (hazard ratio 1.41, P=0.012), but not in patients with CCS after adjustment for covariates. CONCLUSIONS: HR ≥75 beats/min was associated with worse outcomes in patients with CCS or ACS.

Machine learning models to detect social distress, spiritual pain, and severe physical psychological symptoms in terminally ill patients with cancer from unstructured text data in electronic medical records.

BACKGROUND: Few studies have developed automatic systems for identifying social distress, spiritual pain, and severe physical and phycological symptoms from text data in electronic medical records. AIM: To develop models to detect social distress, spiritual pain, and severe physical and psychological symptoms in terminally ill patients with cancer from unstructured text data contained in electronic medical records. DESIGN: A retrospective study of 1,554,736 narrative clinical records was analyzed 1 month before patients died. Supervised machine learning models were trained to detect comprehensive symptoms, and the performance of the models was tested using the area under the receiver operating characteristic curve (AUROC) and precision recall curve (AUPRC). SETTING/PARTICIPANTS: A total of 808 patients was included in the study using records obtained from a university hospital in Japan between January 1, 2018 and December 31, 2019. As training data, we used medical records labeled for detecting social distress (n = 10,000) and spiritual pain (n = 10,000), and records that could be combined with the Support Team Assessment Schedule (based on date) for detecting severe physical/psychological symptoms (n = 5409). RESULTS: Machine learning models for detecting social distress had AUROC and AUPRC values of 0.98 and 0.61, respectively; values for spiritual pain, were 0.90 and 0.58, respectively. The machine learning models accurately identified severe symptoms (pain, dyspnea, nausea, insomnia, and anxiety) with a high level of discrimination (AUROC > 0.8). CONCLUSION: The machine learning models could detect social distress, spiritual pain, and severe symptoms in terminally ill patients with cancer from text data contained in electronic medical records.

Hemodialysis Record Sharing: Solution for Work Burden Reduction and Disaster Preparedness.

BACKGROUND: After the Great East Japan Earthquake in 2011, backup systems for clinical information were launched in Japan. The system in Miyagi Prefecture called the Miyagi Medical and Welfare Information Network (MMWIN) is used as a health information exchange network to share clinical information among various medical facilities for patients who have opted in. Hospitals and clinics specializing in chronic renal failure require patients' data and records during hemodialysis to facilitate communication in daily clinical activity and preparedness for disasters. OBJECTIVE: This study aimed to facilitate the sharing of clinical data of patients undergoing hemodialysis among different hemodialysis facilities. METHODS: We introduced a document-sharing system to make hemodialysis reports available on the MMWIN. We also recruited hospitals and clinics to share the hemodialysis reports of their patients and promoted the development of a network between emergency and dialysis clinics. RESULTS: In addition to basic patient information as well as information on diagnosis, prescription, laboratory data, hospitalization, allergy, and image data from different facilities, specific information about hemodialysis is available, as well as a backup of indispensable information in preparation for disasters. As of June 1, 2021, 12 clinics and 10 hospitals of 68 dialysis facilities in Miyagi participated in the MMWIN. The number of patients who underwent hemodialysis in Miyagi increased by more than 40%. CONCLUSIONS: Our backup system successfully developed a network of hemodialysis facilities. We have accumulated data that are beneficial to prevent the fragmentation of patient information and would be helpful in transferring patients efficiently during unpredictable disasters.

Coverage of Clinical Research Data Retrieved from Standardized Structured Medical Information eXchange Storage.

Clinical researchers hold high expectations for the utility of health data sourced from hospital information systems. In Japan, the standardized structured medical information eXchange version 2 (SS-MIX2) storage is a common resource for obtaining clinical data from different medical databases. However, little is known about the coverage of the data types derived from the SS-MIX2 storage. In this regard, we calculated the proportions of a dataset that could be extracted via SS-MIX2 for various clinical study categories listed in various articles published in the New England Journal of Medicine. In the 95 articles reviewed, the proportions varied from 13.3% ± 13.3% (mean ± SD) for dementia to 61.8% ± 13.7% for diabetes. For cardiology, the proportion of data accessed in a unique format (SEAMAT) increased significantly. We further noted that there was room for improvement in the coverage of SS-MIX2 data.