Deep learning-based glomerulus detection and classification with generative morphology augmentation in renal pathology images.

Glomerulus morphology on renal pathology images provides valuable diagnosis and outcome prediction information. To provide better care, an efficient, standardized, and scalable method is urgently needed to optimize the time-consuming and labor-intensive interpretation process by renal pathologists. This paper proposes a deep convolutional neural network (CNN)-based approach to automatically detect and classify glomeruli with different stains in renal pathology images. In the glomerulus detection stage, this paper proposes a flattened Xception with a feature pyramid network (FX-FPN). The FX-FPN is employed as a backbone in the framework of faster region-based CNN to improve glomerulus detection performance. In the classification stage, this paper considers classifications of five glomerulus morphologies using a flattened Xception classifier. To endow the classifier with higher discriminability, this paper proposes a generative data augmentation approach for patch-based glomerulus morphology augmentation. New glomerulus patches of different morphologies are generated for data augmentation through the cycle-consistent generative adversarial network (CycleGAN). The single detection model shows the F1 score up to 0.9524 in H&E and PAS stains. The classification result shows that the average sensitivity and specificity are 0.7077 and 0.9316, respectively, by using the flattened Xception with the original training data. The sensitivity and specificity increase to 0.7623 and 0.9443, respectively, by using the generative data augmentation. Comparisons with different deep CNN models show the effectiveness and superiority of the proposed approach.

The Incidence and Disparities in Use of Stigmatizing Language in Clinical Notes for Patients With Substance Use Disorder.

OBJECTIVE: The language used to describe people with substance use disorder impacts stigma and influences clinical decision making. This study evaluates the presence of stigmatizing language (SL) in clinical notes and detects patient- and provider-level differences. METHODS: All free-text notes generated in a large health system for patients with substance-related diagnoses between December 2020 and November 2021 were included. A natural language processing algorithm using the National Institute on Drug Abuse's "Words Matter" list was developed to identify use of SL in context. RESULTS: There were 546,309 notes for 30,391 patients, of which 100,792 (18.4%) contained SL. A total of 18,727 patients (61.6%) had at least one note with SL. The most common SLs used were "abuse" and "substance abuse." Nurses were least likely to use SL (4.1%) while physician assistants were most likely (46.9%). Male patients were more likely than female patients to have SL in their notes (adjusted odds ratio [aOR], 1.17; 95% confidence internal [CI], 1.11-1.23), younger patients aged 18 to 24 were less likely to have SL than patients 45 to 54 years (aOR, 0.55; 95% CI, 0.50-0.61), Asian patients were less likely to have SL than White patients (aOR, 0.45; 95% CI, 0.36-0.56), and Hispanic patients were less likely to have SL than non-Hispanic patients (aOR, 0.88; 95% CI, 0.80-0.98). CONCLUSIONS: The majority of patients with substance-related diagnoses had at least one note containing SL. There were also several patient characteristic disparities associated with patients having SL in their notes. The work suggests that more clinician interventions about use of SL are needed.

Risk of Severe Alphaherpesvirus Infection after Solid Organ Transplantation: A Nationwide Population-Based Cohort Study.

Patients after solid organ transplantation (SOT) are more susceptible to various viral infections, including alphaherpesviruses. Therefore, the aim of our study was to investigate the risk of alphaherpesvirus infections, including herpes simplex and herpes zoster, after solid organ transplantation. Inpatient records from the Taiwan National Health Insurance Research Database (NHIRD) defined solid organ recipients, including heart, liver, lung, and kidney, hospitalized for alphaherpesvirus infections as a severe case group of transplants and matched them with a nontransplant cohort. We enrolled 18,064 individuals, of whom 9032 were in each group. A higher risk of severe alphaherpesvirus infection was noted in solid organ recipients (aHR = 9.19; p < 0.001) than in the general population. In addition, solid organ transplant recipients had the highest risk of alphaherpesvirus infection within 1 year after transplantation (aHR = 25.18). The comparison found a higher risk of herpes zoster and herpes simplex infections in recipients of kidney (aHR = 9.13; aHR = 12.13), heart (aHR = 14.34; aHR = 18.54), and liver (aHR = 5.90; aHR = 8.28) transplants. Patients who underwent solid organ transplantation had a significantly higher risk of alphaherpesvirus infection than the general population.

Developing Validated Tools to Identify Pulmonary Embolism in Electronic Databases: Rationale and Design of the PE-EHR+ Study.

BACKGROUND: Contemporary pulmonary embolism (PE) research, in many cases, relies on data from electronic health records (EHRs) and administrative databases that use International Classification of Diseases (ICD) codes. Natural language processing (NLP) tools can be used for automated chart review and patient identification. However, there remains uncertainty with the validity of ICD-10 codes or NLP algorithms for patient identification. METHODS: The PE-EHR+ study has been designed to validate ICD-10 codes as Principal Discharge Diagnosis, or Secondary Discharge Diagnoses, as well as NLP tools set out in prior studies to identify patients with PE within EHRs. Manual chart review by two independent abstractors by predefined criteria will be the reference standard. Sensitivity, specificity, and positive and negative predictive values will be determined. We will assess the discriminatory function of code subgroups for intermediate- and high-risk PE. In addition, accuracy of NLP algorithms to identify PE from radiology reports will be assessed. RESULTS: A total of 1,734 patients from the Mass General Brigham health system have been identified. These include 578 with ICD-10 Principal Discharge Diagnosis codes for PE, 578 with codes in the secondary position, and 578 without PE codes during the index hospitalization. Patients within each group were selected randomly from the entire pool of patients at the Mass General Brigham health system. A smaller subset of patients will also be identified from the Yale-New Haven Health System. Data validation and analyses will be forthcoming. CONCLUSIONS: The PE-EHR+ study will help validate efficient tools for identification of patients with PE in EHRs, improving the reliability of efficient observational studies or randomized trials of patients with PE using electronic databases.

Identifying and Reconciling Patients' Allergy Information Within the Electronic Health Record.

Allergy information is often documented in diverse sections of the electronic health record (EHR). Systematically reconciling allergy information across the EHR is critical to improve the accuracy and completeness of patients' allergy lists and ensure patient safety. In this retrospective cohort study, we examined the prevalence of incompleteness, inaccuracy, and redundancy of allergy information for patients with a clinical encounter at any Mass General Brigham facility between January 1, 2018 and December 31, 2018. We identified 4 key places in the EHR containing reconcilable allergy information: 1) allergy modules (including free text comments and duplicate allergen entries), 2) medication laboratory tests results, 3) oral medication allergy challenge tests, and 4) medication orders that have been discontinued due to adverse drug reactions (ADRs). Within our cohort, 718,315 (45.2% of the total 1,588,979) patients had an active allergy entry; of which, 266,275 (37.1%) patient's records indicated a need for reconciliation.

Reconciling Allergy Information in the Electronic Health Record After a Drug Challenge Using Natural Language Processing.

Background: Drug challenge tests serve to evaluate whether a patient is allergic to a medication. However, the allergy list in the electronic health record (EHR) is not consistently updated to reflect the results of the challenge, affecting clinicians' prescription decisions and contributing to inaccurate allergy labels, inappropriate drug-allergy alerts, and potentially ineffective, more toxic, and/or costly care. In this study, we used natural language processing (NLP) to automatically detect discrepancies between the EHR allergy list and drug challenge test results and to inform the clinical recommendations provided in a real-time allergy reconciliation module. Methods: This study included patients who received drug challenge tests at the Mass General Brigham (MGB) Healthcare System between June 9, 2015 and January 5, 2022. At MGB, drug challenge tests are performed in allergy/immunology encounters with routine clinical documentation in notes and flowsheets. We developed a rule-based NLP tool to analyze and interpret the challenge test results. We compared these results against EHR allergy lists to detect potential discrepancies in allergy documentation and form a recommendation for reconciliation if a discrepancy was identified. To evaluate the capability of our tool in identifying discrepancies, we calculated the percentage of challenge test results that were not updated and the precision of the NLP algorithm for 200 randomly sampled encounters. Results: Among 200 samples from 5,312 drug challenge tests, 59% challenged penicillin reactivity and 99% were negative. 42.0%, 61.5%, and 76.0% of the results were confirmed by flowsheets, NLP, or both, respectively. The precision of the NLP algorithm was 96.1%. Seven percent of patient allergy lists were not updated based on drug challenge test results. Flowsheets alone were used to identify 2.0% of these discrepancies, and NLP alone detected 5.0% of these discrepancies. Because challenge test results can be recorded in both flowsheets and clinical notes, the combined use of NLP and flowsheets can reliably detect 5.5% of discrepancies. Conclusion: This NLP-based tool may be able to advance global delabeling efforts and the effectiveness of drug allergy assessments. In the real-time EHR environment, it can be used to examine patient allergy lists and identify drug allergy label discrepancies, mitigating patient risks.

PASCLex: A comprehensive post-acute sequelae of COVID-19 (PASC) symptom lexicon derived from electronic health record clinical notes.

OBJECTIVE: To develop a comprehensive post-acute sequelae of COVID-19 (PASC) symptom lexicon (PASCLex) from clinical notes to support PASC symptom identification and research. METHODS: We identified 26,117 COVID-19 positive patients from the Mass General Brigham's electronic health records (EHR) and extracted 328,879 clinical notes from their post-acute infection period (day 51-110 from first positive COVID-19 test). PASCLex incorporated Unified Medical Language System® (UMLS) Metathesaurus concepts and synonyms based on selected semantic types. The MTERMS natural language processing (NLP) tool was used to automatically extract symptoms from a development dataset. The lexicon was iteratively revised with manual chart review, keyword search, concept consolidation, and evaluation of NLP output. We assessed the comprehensiveness of PASCLex and the NLP performance using a validation dataset and reported the symptom prevalence across the entire corpus. RESULTS: PASCLex included 355 symptoms consolidated from 1520 UMLS concepts of 16,466 synonyms. NLP achieved an averaged precision of 0.94 and an estimated recall of 0.84. Symptoms with the highest frequency included pain (43.1%), anxiety (25.8%), depression (24.0%), fatigue (23.4%), joint pain (21.0%), shortness of breath (20.8%), headache (20.0%), nausea and/or vomiting (19.9%), myalgia (19.0%), and gastroesophageal reflux (18.6%). DISCUSSION AND CONCLUSION: PASC symptoms are diverse. A comprehensive lexicon of PASC symptoms can be derived using an ontology-driven, EHR-guided and NLP-assisted approach. By using unstructured data, this approach may improve identification and analysis of patient symptoms in the EHR, and inform prospective study design, preventative care strategies, and therapeutic interventions for patient care.

Development and Validation of a Deep Learning Model for Earlier Detection of Cognitive Decline From Clinical Notes in Electronic Health Records.

Importance: Detecting cognitive decline earlier among older adults can facilitate enrollment in clinical trials and early interventions. Clinical notes in longitudinal electronic health records (EHRs) provide opportunities to detect cognitive decline earlier than it is noted in structured EHR fields as formal diagnoses. Objective: To develop and validate a deep learning model to detect evidence of cognitive decline from clinical notes in the EHR. Design, Setting, and Participants: Notes documented 4 years preceding the initial mild cognitive impairment (MCI) diagnosis were extracted from Mass General Brigham's Enterprise Data Warehouse for patients aged 50 years or older and with initial MCI diagnosis during 2019. The study was conducted from March 1, 2020, to June 30, 2021. Sections of notes for cognitive decline were labeled manually and 2 reference data sets were created. Data set I contained a random sample of 4950 note sections filtered by a list of keywords related to cognitive functions and was used for model training and testing. Data set II contained 2000 randomly selected sections without keyword filtering for assessing whether the model performance was dependent on specific keywords. Main Outcomes and Measures: A deep learning model and 4 baseline models were developed and their performance was compared using the area under the receiver operating characteristic curve (AUROC) and area under the precision recall curve (AUPRC). Results: Data set I represented 1969 patients (1046 [53.1%] women; mean [SD] age, 76.0 [13.3] years). Data set II comprised 1161 patients (619 [53.3%] women; mean [SD] age, 76.5 [10.2] years). With some overlap of patients deleted, the unique population was 2166. Cognitive decline was noted in 1453 sections (29.4%) in data set I and 69 sections (3.45%) in data set II. Compared with the 4 baseline models, the deep learning model achieved the best performance in both data sets, with AUROC of 0.971 (95% CI, 0.967-0.976) and AUPRC of 0.933 (95% CI, 0.921-0.944) for data set I and AUROC of 0.997 (95% CI, 0.994-0.999) and AUPRC of 0.929 (95% CI, 0.870-0.969) for data set II. Conclusions and Relevance: In this diagnostic study, a deep learning model accurately detected cognitive decline from clinical notes preceding MCI diagnosis and had better performance than keyword-based search and other machine learning models. These results suggest that a deep learning model could be used for earlier detection of cognitive decline in the EHRs.

Implementation of an Electronic National Early Warning System to Decrease Clinical Deterioration in Hospitalized Patients at a Tertiary Medical Center.

The National Early Warning Score (NEWS) is an early warning system that predicts clinical deterioration. The impact of the NEWS on the outcome of healthcare remains controversial. This study was conducted to evaluate the effectiveness of implementing an electronic version of the NEWS (E-NEWS), to reduce unexpected clinical deterioration. We developed the E-NEWS as a part of the Health Information System (HIS) and Nurse Information System (NIS). All adult patients admitted to general wards were enrolled into the current study. The "adverse event" (AE) group consisted of patients who received cardiopulmonary resuscitation (CPR), were transferred to an intensive care unit (ICU) due to unexpected deterioration, or died. Patients without AE were allocated to the control group. The development of the E-NEWS was separated into a baseline (October 2018 to February 2019), implementation (March to August 2019), and intensive period (September. to December 2019). A total of 39,161 patients with 73,674 hospitalization courses were collected. The percentage of overall AEs was 6.06%. Implementation of E-NEWS was associated with a significant decrease in the percentage of AEs from 6.06% to 5.51% (p = 0.001). CPRs at wards were significantly reduced (0.52% to 0.34%, p = 0.012). The number of patients transferred to the ICU also decreased significantly (3.63% to 3.49%, p = 0.035). Using multivariate analysis, the intensive period was associated with reducing AEs (p = 0.019). In conclusion, we constructed an E-NEWS system, updating the NEWS every hour automatically. Implementing the E-NEWS was associated with a reduction in AEs, especially CPRs at wards and transfers to ICU from ordinary wards.

A dynamic reaction picklist for improving allergy reaction documentation in the electronic health record.

OBJECTIVE: Incomplete and static reaction picklists in the allergy module led to free-text and missing entries that inhibit the clinical decision support intended to prevent adverse drug reactions. We developed a novel, data-driven, "dynamic" reaction picklist to improve allergy documentation in the electronic health record (EHR). MATERIALS AND METHODS: We split 3 decades of allergy entries in the EHR of a large Massachusetts healthcare system into development and validation datasets. We consolidated duplicate allergens and those with the same ingredients or allergen groups. We created a reaction value set via expert review of a previously developed value set and then applied natural language processing to reconcile reactions from structured and free-text entries. Three association rule-mining measures were used to develop a comprehensive reaction picklist dynamically ranked by allergen. The dynamic picklist was assessed using recall at top k suggested reactions, comparing performance to the static picklist. RESULTS: The modified reaction value set contained 490 reaction concepts. Among 4 234 327 allergy entries collected, 7463 unique consolidated allergens and 469 unique reactions were identified. Of the 3 dynamic reaction picklists developed, the 1 with the optimal ranking achieved recalls of 0.632, 0.763, and 0.822 at the top 5, 10, and 15, respectively, significantly outperforming the static reaction picklist ranked by reaction frequency. CONCLUSION: The dynamic reaction picklist developed using EHR data and a statistical measure was superior to the static picklist and suggested proper reactions for allergy documentation. Further studies might evaluate the usability and impact on allergy documentation in the EHR.

Epiretinal Membrane Detection at the Ophthalmologist Level using Deep Learning of Optical Coherence Tomography.

PURPOSE: Previous deep learning studies on optical coherence tomography (OCT) mainly focused on diabetic retinopathy and age-related macular degeneration. We proposed a deep learning model that can identify epiretinal membrane (ERM) in OCT with ophthalmologist-level performance. DESIGN: Cross-sectional study. PARTICIPANTS: A total of 3,618 central fovea cross section OCT images from 1,475 eyes of 964 patients. METHODS: We retrospectively collected 7,652 OCT images from 1,197 patients. From these images, 2,171 were normal and 1,447 were ERM OCT. A total of 3,141 OCT images was used as training dataset and 477 images as testing dataset. DL algorithm was used to train the interpretation model. Diagnostic results by four board-certified non-retinal specialized ophthalmologists on the testing dataset were compared with those generated by the DL model. MAIN OUTCOME MEASURES: We calculated for the derived DL model the following characteristics: sensitivity, specificity, F1 score and area under curve (AUC) of the receiver operating characteristic (ROC) curve. These were calculated according to the gold standard results which were parallel diagnoses of the retinal specialist. Performance of the DL model was finally compared with that of non-retinal specialized ophthalmologists. RESULTS: Regarding the diagnosis of ERM in OCT images, the trained DL model had the following characteristics in performance: sensitivity: 98.7%, specificity: 98.0%, and F1 score: 0.945. The accuracy on the training dataset was 99.7% (95% CI: 99.4 - 99.9%), and for the testing dataset, diagnostic accuracy was 98.1% (95% CI: 96.5 - 99.1%). AUC of the ROC curve was 0.999. The DL model slightly outperformed the average non-retinal specialized ophthalmologists. CONCLUSIONS: An ophthalmologist-level DL model was built here to accurately identify ERM in OCT images. The performance of the model was slightly better than the average non-retinal specialized ophthalmologists. The derived model may play a role to assist clinicians to promote the efficiency and safety of healthcare in the future.

Treatment of chronic active antibody-mediated rejection in renal transplant recipients - a single center retrospective study.

BACKGROUND: Chronic active antibody-mediated rejection is a major etiology of graft loss in renal transplant recipients. However, there is no consensus on the optimal treatment strategies. METHODS: Computerized records from Taichung Veterans General Hospital were collected to identify renal transplant biopsies performed in the past 7 years with a diagnosis of chronic active antibody-mediated rejection. The patients were divided into two groups according to treatment strategy: Group 1 received aggressive treatment (double filtration plasmapheresis and one of the followings: rituximab, intravenous immunoglobulin, antithymogycte globulin, bortezomib, or methylprednisolone pulse therapy); and group 2 received supportive treatment. RESULTS: From February 2009 to December 2017, a total of 82 patients with biopsy-proven chronic antibody mediated rejection were identified. Kaplan-Meier analysis of death-censored graft survival showed a worse survival in group 2 (P = 0.015 by log-rank test). Adverse event-free survival was lower in group 1, whereas patient survival was not significantly different. Proteinuria and supportive treatment were independent risk factors for graft loss in multivariate analysis. CONCLUSIONS: Aggressive treatment was associated with better graft outcome. However, higher incidence of adverse events merit personalized treatment, especially for those with higher risk of infection. Appropriate prophylactic antibiotics are recommended for patients undergoing aggressive treatment.

Duloxetine-Induced Hyponatremia in an Elderly Male Patient with Treatment-Refractory Major Depressive Disorder.

Several classes of antidepressants can induce syndrome of inappropriate antidiuretic hormone hypersecretion (SIADH), thereby causing hyponatremia. Initial symptoms of hyponatremia include neuropsychiatric and gastrointestinal manifestations can mimic depression, especially in elderly people with multiple somatic complaints. Here we present a case of a 68-year-old man with treatment-refractory depression and general anxiety disorder who developed duloxetine-induced hyponatremia. His symptoms of hyponatremia including unsteady gait, dizziness, nausea, general malaise, and poor appetite subsided after discontinuing the offending medication. Our case illustrates that drug-induced SIADH and potential drug-drug interactions should be considered in elderly patients who develop hyponatremia following the initiation of antidepressants.

Young-Adult Polycystic Kidney Disease is Associated with Major Cardiovascular Complications.

Background: Patients with polycystic kidney disease (PKD) might have a risk of cardiovascular diseases because several cardiovascular risk factors are occasionally associated with PKD patients. Data on the association between PKD and the risk of cardiovascular events, including acute coronary syndrome (ACS), stroke, and congestive heart failure (CHF), are scant. Methods: Patients aged ≥20 years who were newly diagnosed with PKD (International Classification of Diseases, Ninth Revision, Clinical Modification codes 753.12 and 753.13) between 2000 and 2011 were selected as a PKD cohort (N = 5157). The association between PKD and cardiovascular events was analyzed. Results: We randomly selected a comparison cohort of people without PKD, who were frequency-matched by sex, age, and index date of diagnosis. At the end of 2011, the PKD cohort had a 1.40-fold greater incidence of ACS compared with the comparison cohort (8.59 vs. 6.17 per 1000 person-years), in addition to a 1.40-fold greater incidence of stroke, a 1.49-fold greater incidence of CHF, and a 1.64-fold greater incidence of mortality. Conclusions: This retrospective cohort study shows that patients with PKD have an increased risk of cardiovascular events including ACS, stroke, and CHF as well as mortality, particularly in younger patients. Early identification is necessary to attenuate the risk of cardiovascular complications in patients with PKD.

Spironolactone and the risk of urinary tract cancer in patients with hypertension: a nationwide population-based retrospective case-control study.

AIM: This was a nationwide study by National Health Insurance Research Database to investigate the risk of urinary tract cancers (UTCs) for renin-angiotensin-aldosterone system inhibitors including spironolactone. METHODS: A total of 32 167 UTC patients with hypertension were enrolled in the National Health Insurance program between 2005 and 2011. RESULTS: Among different subclasses of renin-angiotensin-aldosterone system inhibitors, the adjusted odds ratio (OR) for UTC risk was 1.00 [95% confidence interval (CI) = 0.96-1.04] in angiotensin-converting enzyme inhibitors, 1.22 (95% CI = 1.18-1.26) in patients who received angiotensin II receptor blockers, 0.91 (95% CI = 0.87-0.96) in spironolactone. Spironolactone is associated with a significantly lower risk of prostate cancer (adjusted OR = 0.88, 95% CI = 0.82-0.94) in the male patients. A similar trend was observed in the female patients for the risk of bladder cancer (adjusted OR = 0.81, 95% CI = 0.72-0.92). CONCLUSION: Our findings show that a lower risk of UTCs significantly associated with spironolactone in patients.

Validated Simulation: The Preliminary Experience of Anesthesiologist Board Examination in Taiwan.

High fidelity simulation-based teaching has played an important role in medical education, especially in anesthesiology and emergency. But there is not any currently validated scoring system or prediction model for high fidelity simulation. We will develop a validated prediction model to enhance the efficiency and validation of clinical training with high fidelity simulation.

Building Chronic Kidney Disease Clinical Practice Guidelines Using the openEHR Guideline Definition Language.

BACKGROUND: As a result of the disease's high prevalence, chronic kidney disease (CKD) has become a global public health problem. A clinical decision support system that integrates with computer-interpretable guidelines (CIGs) should improve clinical outcomes and help to ensure patient safety. OBJECTIVES: The openEHR guideline definition language (GDL) is a formal language used to represent CIGs. This study explores the feasibility of using a GDL approach for CKD; it also attempts to identify any potential gaps between the ideal concept and reality. METHODS: Using the Kidney Disease Improving Global Outcomes (KDIGO) anemia guideline as material, we designed a development workflow in order to establish a series of GDL guidelines. Focus group discussions were conducted in order to identify important issues related to GDL implementation. RESULTS: Ten GDL guidelines and 37 archetypes were established using the KDIGO guideline document. For the focus group discussions, 16 clinicians and 22 IT experts were recruited and their perceptions, opinions and attitudes towards the GDL approach were explored. Both groups provided positive feedback regarding the GDL approach, but raised various concerns about GDL implementation. CONCLUSIONS: Based on the findings of this study, we identified some potential gaps that might exist during implementation between the GDL concept and reality. Three directions remain to be investigated in the future. Two of them are related to the openEHR GDL approach. Firstly, there is a need for the editing tool to be made more sophisticated. Secondly, there needs to be integration of the present approach into non openEHR-based hospital information systems. The last direction focuses on the applicability of guidelines and involves developing a method to resolve any conflicts that occur with insurance payment regulations.

Draft Genome Sequence of Mycobacterium tuberculosis Clinical Strain W06, a Prevalent Beijing Genotype Isolated in Taiwan.

Mycobacterium tuberculosis strain W06, analyzed by molecular methods, was classified as a modern Beijing M. tuberculosis strain, the most predominant strain in Taiwan. To our knowledge, this is the first draft genome announcement of a Beijing M. tuberculosis strain in Taiwan.