Tislelizumab, a novel PD-1 monoclonal antibody in urothelial cancer: A real-world study

OBJECTIVE

Tislelizumab, a monoclonal antibody against programed death protein-1 (PD-1), has shown encouraging antitumor activity in urothelial cancer. This study was designed to assess the efficacy and safety of tislelizumab in urotelial cancer in a real-world setting.

METHODS

The study was a real-world retrospective study undertaken at Liaoning Cancer Hospital & Institute, China. Eligible patients were ≥18 years. Patients received 200-mg tislelizumab monotherapy intravenously every 3 weeks until the disease progressed to intolerable toxicity. Outcomes included an objective response rate (ORR), disease control rate (DCR), progression-free survival (PFS), overall survival (OS) and safety.

RESULTS

Between March 2020 and December 2022, 33 patients were enrolled. The median follow-up was 10.17 (IQR 5.73-12.47) months. Of all 33 patients, ORR and DCR were 30.30% (95% CI 15.6%-48.7%) and 42.42% (95% CI 25.48%-60.78%), respectively. The median PFS was 5.73 (95% CI 3.27-13.00) months, with a 12-month PFS rate of 31.90% (95% CI 19.20%-53.00%). The median OS was 17.7 (95% CI 12.80-not reach) months, with a 12-month OS rate of 67.50% (95% CI 52.70%-86.40%). Eleven (33.33%) and 8 (24.24%) experienced ≥grade 3 treatment-related adverse events (TRAEs) and immune-related Aes, respectively. No treatment-related deaths occurred.

CONCLUSION

The excellent efficacy and controllable safety of tislelizumab in locally advanced or metastatic urothelial cancer suggest that it may be a promising therapeutic option for this population.

Revolutionizing Postoperative Ileus Monitoring: Exploring GRU-D's Real-Time Capabilities and Cross-Hospital Transferability

Background

Postoperative ileus (POI) after colorectal surgery leads to increased morbidity, costs, and hospital stays. Identifying POI risk for early intervention is important for improving surgical outcomes especially given the increasing trend towards early discharge after surgery. While existing studies have assessed POI risk with regression models, the role of deep learning's remains unexplored.

Methods

We assessed the performance and transferability (brutal force/instance/parameter transfer) of Gated Recurrent Unit with Decay (GRU-D), a longitudinal deep learning architecture, for real-time risk assessment of POI among 7,349 colorectal surgeries performed across three hospital sites operated by Mayo Clinic with two electronic health records (EHR) systems. The results were compared with atemporal models on a panel of benchmark metrics.

Results

GRU-D exhibits robust transferability across different EHR systems and hospital sites, showing enhanced performance by integrating new measurements, even amid the extreme sparsity of real-world longitudinal data. On average, for labs, vitals, and assisted living status, 72.2%, 26.9%, and 49.3% respectively lack measurements within 24 hours after surgery. Over the follow-up period with 4-hour intervals, 98.7%, 84%, and 95.8% of data points are missing, respectively. A maximum of 5% decrease in AUROC was observed in brutal-force transfer between different EHR systems with non-overlapping surgery date frames. Multi-source instance transfer witnessed the best performance, with a maximum of 2.6% improvement in AUROC over local learning. The significant benefit, however, lies in the reduction of variance (a maximum of 86% decrease). The GRU-D model's performance mainly depends on the prediction task's difficulty, especially the case prevalence rate. Whereas the impact of training data and transfer strategy is less crucial, underscoring the challenge of effectively leveraging transfer learning for rare outcomes. While atemporal Logit models show notably superior performance at certain pre-surgical points, their performance fluctuate significantly and generally underperform GRU-D in post-surgical hours.

Conclusion

GRU-D demonstrated robust transferability across EHR systems and hospital sites with highly sparse real-world EHR data. Further research on built-in explainability for meaningful intervention would be highly valuable for its integration into clinical practice.

Assessment of Gender Differences in Letters of Recommendation for Physical Therapy Residency Applications

INTRODUCTION

Letters of recommendation (LOR) are an integral component of physical therapy residency applications. Identifying the influence of applicant and writer gender in LOR will help identify whether potential implicit gender bias exists in physical therapy residency application processes.

REVIEW OF LITERATURE

Several medical and surgical residency education programs have reported positive, neutral, or negative LOR female gender bias among applicants and writers. Little research exists on gender differences in LOR to physical therapy education programs or physical therapy residency programs.

SUBJECTS

Seven hundred sixty-eight LOR were analyzed from 256 applications to 3 physical therapy residency programs (neurologic, orthopaedic, sports) at one institution from 2014 to 2020.

METHODS

Thematic categories were developed to identify themes in a sample of LOR. Associations between writer and applicant gender were analyzed using summary statistics, word counts, thematic and psycholinguistic extraction, and rule-based and deep learning Natural Language Processing .

RESULTS

No significant difference in LOR word counts were found based on writer or applicant gender. Increased word counts were seen in sports residency LOR compared with the orthopaedic residency. Thematic analysis showed LOR gender differences with male applicants receiving more positive generalized recommendations and female applicants receiving more comments regarding interpersonal relationship skills. No thematic or psycholinguistic gender differences were seen by LOR writer. Male applicants were 1.9 times more likely to select all male LOR writers, whereas female applicants were 2.1 times more likely to choose all female LOR writers.

DISCUSSION AND CONCLUSION

Gender differences in LORs for physical therapy residencies were found using a comprehensive Natural Language Processing approach that identified both a positive recommendation male applicant gender bias and a positive interpersonal relationship skill female applicant gender bias. Applicants were not harmed nor helped by selecting LOR writers of the opposite gender. Admissions committees and LOR writers should be mindful of potential implicit gender biases in LOR submitted to physical therapy residency programs.

FedFSA: Hybrid and federated framework for functional status ascertainment across institutions

INTRODUCTION

Patients' functional status assesses their independence in performing activities of daily living, including basic ADLs (bADL), and more complex instrumental activities (iADL). Existing studies have discovered that patients' functional status is a strong predictor of health outcomes, particularly in older adults. Depite their usefulness, much of the functional status information is stored in electronic health records (EHRs) in either semi-structured or free text formats. This indicates the pressing need to leverage computational approaches such as natural language processing (NLP) to accelerate the curation of functional status information. In this study, we introduced FedFSA, a hybrid and federated NLP framework designed to extract functional status information from EHRs across multiple healthcare institutions.

METHODS

FedFSA consists of four major components: 1) individual sites (clients) with their private local data, 2) a rule-based information extraction (IE) framework for ADL extraction, 3) a BERT model for functional status impairment classification, and 4) a concept normalizer. The framework was implemented using the OHNLP Backbone for rule-based IE and open-source Flower and PyTorch library for federated BERT components. For gold standard data generation, we carried out corpus annotation to identify functional status-related expressions based on ICF definitions. Four healthcare institutions were included in the study. To assess FedFSA, we evaluated the performance of category- and institution-specific ADL extraction across different experimental designs.

RESULTS

ADL extraction performance ranges from an F1-score of 0.907 to 0.986 for bADL and 0.825 to 0.951 for iADL across the four healthcare sites. The performance for ADL extraction with impairment ranges from an F1-score of 0.722 to 0.954 for bADL and 0.674 to 0.813 for iADL across four healthcare sites. For category-specific ADL extraction, laundry and transferring yielded relatively high performance, while dressing, medication, bathing, and continence achieved moderate-high performance. Conversely, food preparation and toileting showed low performance.

CONCLUSION

NLP performance varied across ADL categories and healthcare sites. Federated learning using a FedFSA framework performed higher than non-federated learning for impaired ADL extraction at all healthcare sites. Our study demonstrated the potential of the federated learning framework in functional status extraction and impairment classification in EHRs, exemplifying the importance of a large-scale, multi-institutional collaborative development effort.

An Integrated Voice Recognition and Natural Language Processing Platform to Automatically Extract Thoracolumbar Injury Classification Score Features From Radiology Reports

BACKGROUND

Many predictive models for estimating clinical outcomes after spine surgery have been reported in the literature. However, implementation of predictive scores in practice is limited by the time-intensive nature of manually abstracting relevant predictors. In this study, we designed natural language processing (NLP) algorithms to automate data abstraction for the thoracolumbar injury classification score (TLICS).

METHODS

We retrieved the radiology reports of all Mayo Clinic patients with an International Classification of Diseases, 9th or 10th revision, code corresponding to a fracture of the thoracolumbar spine between January 2005 and October 2020. Annotated data were used to train an N-gram NLP model using machine learning methods, including random forest, stepwise linear discriminant analysis, k-nearest neighbors, and penalized logistic regression models.

RESULTS

A total of 1085 spine radiology reports were included in our analysis. Our dataset included 483 compression, 401 burst, 103 translational/rotational, and 98 distraction fractures. A total of 103 reports had documented an injury of the posterior ligamentous complex. The overall accuracy of the random forest model for fracture morphology feature detection was 76.96% versus 65.90% in the stepwise linear discriminant analysis, 50.69% in the k-nearest neighbors, and 62.67% in the penalized logistic regression. The overall accuracy to detect posterior ligamentous complex integrity was highest in the random forest model at 83.41%. Our random forest model was implemented in the backend of a web application in which users can dictate reports and have TLICS features automatically extracted.

CONCLUSIONS

We have developed a machine learning NLP model for extracting TLICS features from radiology reports, which we deployed in a web application that can be integrated into clinical practice.

Mortality Outcomes in a Large Population with and without Covert Cerebrovascular Disease

Covert cerebrovascular disease (CCD) is frequently reported on neuroimaging and associates with increased dementia and stroke risk. We aimed to determine how incidentally-discovered CCD during clinical neuroimaging in a large population associates with mortality. We screened CT and MRI reports of adults aged ≥50 in the Kaiser Permanente Southern California health system who underwent neuroimaging for a non-stroke clinical indication from 2009-2019. Natural language processing identified incidental covert brain infarcts (CBI) and/or white matter hyperintensities (WMH), grading WMH as mild/moderate/severe. Models adjusted for age, sex, ethnicity, multimorbidity, vascular risks, depression, exercise, and imaging modality. Of n=241,028, the mean age was 64.9 (SD=10.4); mean follow-up 4.46 years; 178,554 (74.1%) had CT; 62,474 (25.9%) had MRI; 11,328 (4.7%) had CBI; and 69,927 (29.0%) had WMH. The mortality rate per 1,000 person-years with CBI was 59.0 (95%CI 57.0-61.1); with WMH=46.5 (45.7-47.2); with neither=17.4 (17.1-17.7). In adjusted models, mortality risk associated with CBI was modified by age, e.g. HR 1.34 [1.21-1.48] at age 56.1 years vs HR 1.22 [1.17-1.28] at age 72 years. Mortality associated with WMH was modified by both age and imaging modality e.g., WMH on MRI at age 56.1 HR = 1.26 [1.18-1.35]; WMH on MRI at age 72 HR 1.15 [1.09-1.21]; WMH on CT at age 56.1 HR 1.41 [1.33-1.50]; WMH on CT at age 72 HR 1.28 [1.24-1.32], vs. patients without CBI or without WMH, respectively. Increasing WMH severity associated with higher mortality, e.g. mild WMH on MRI had adjusted HR=1.13 [1.06-1.20] while severe WMH on CT had HR=1.45 [1.33-1.59]. Incidentally-detected CBI and WMH on population-based clinical neuroimaging can predict higher mortality rates. We need treatments and healthcare planning for individuals with CCD.

Contextual Variation of Clinical Notes induced by EHR Migration

The structure and semantics of clinical notes vary considerably across different Electronic Health Record (EHR) systems, sites, and institutions. Such heterogeneity hampers the portability of natural language processing (NLP) models in extracting information from the text for clinical research or practice. In this study, we evaluate the contextual variation of clinical notes by measuring the semantic and syntactic similarity of the notes of two sets of physicians comprising four medical specialties across EHR migrations at two Mayo Clinic sites. We find significant semantic and syntactic variation imposed by the context of the EHR system and between medical specialties whereas only minor variation is caused by variation of spatial context across sites. Our findings suggest that clinical language models need to account for process differences at the specialty sublanguage level to be generalizable.

Digital Solutions Observed in Clinical Trials: A Formative Feasibility Scoping Review

Growing digital access accelerates digital transformation of clinical trials where digital solutions (DSs) are increasingly and widely leveraged for improving trial efficiency, effectiveness, and accessibility. Many factors impact DS success including technology barriers, privacy concerns, or user engagement activities. It is unclear how those factors are considered or reported in the literature. Here, we perform a formative feasibility scoping review to identify gaps impacting DS quality and reproducibility in trials. Articles containing digital terms published in English from 2009 to 2022 were collected (n=4,167). 130 articles published between 2016 and 2022 were randomly selected for full-text review. Eligible articles (n=100) were sorted into four identified categories: 16% Education, 59% Intervention, 8% Patient, 17% Treatment. Initial findings about DS trends and reporting practices inform protocol development for a large-scale study urging the generation of fundamental knowledge on reporting standardization, best practice guidelines, and evaluation methodologies related to DS for clinical trials.

Harnessing Transfer Learning for Dementia Prediction: Leveraging Sex-Different Mild Cognitive Impairment Prognosis

This paper presents a machine learning-based prediction for dementia, leveraging transfer learning to reuse the knowledge learned from prediction of mild cognitive impairment, a precursor of dementia. We also examine the impacts of temporal aspects of longitudinal data and sex differences. The methodology encompasses key components such as setting the duration window, comparing different modeling strategies, conducting comprehensive evaluations, and examining the sex-specific impacts of simulated scenarios. The findings reveal that cognitive deficits in females, once detected at the mild cognitive impairment stage, tend to deteriorate over time, while males exhibit more diverse decline across various characteristics without highlighting specific ones. However, the underlying reasons for these sex differences remain unknown and warrant further investigation.

An open natural language processing (NLP) framework for EHR-based clinical research: a case demonstration using the National COVID Cohort Collaborative (N3C)

Despite recent methodology advancements in clinical natural language processing (NLP), the adoption of clinical NLP models within the translational research community remains hindered by process heterogeneity and human factor variations. Concurrently, these factors also dramatically increase the difficulty in developing NLP models in multi-site settings, which is necessary for algorithm robustness and generalizability. Here, we reported on our experience developing an NLP solution for Coronavirus Disease 2019 (COVID-19) signs and symptom extraction in an open NLP framework from a subset of sites participating in the National COVID Cohort (N3C). We then empirically highlight the benefits of multi-site data for both symbolic and statistical methods, as well as highlight the need for federated annotation and evaluation to resolve several pitfalls encountered in the course of these efforts.

Stratifying future stroke risk with incidentally-discovered white matter disease severity and covert brain infarct site

BACKGROUND

Covert cerebrovascular disease (CCD) includes white matter disease (WMD) and covert brain infarction (CBI). Incidentally-discovered CCD is associated with increased risk of subsequent symptomatic stroke. However, it is unknown whether the severity of WMD or the location of CBI predicts risk.

OBJECTIVES

To examine the association of incidentally-discovered WMD severity and CBI location with risk of subsequent symptomatic stroke.

METHOD

This retrospective cohort study includes patients 50 years old in the Kaiser Permanente Southern California health system who received neuroimaging for a non-stroke indication between 2009-2019. Incidental CBI and WMD were identified via natural language processing of the neuroimage report, and WMD severity was classified into grades.

RESULTS

261,960 patients received neuroimaging; 78,555 (30.0%) were identified to have incidental WMD, and 12,857 (4.9%) to have incidental CBI. Increasing WMD severity is associated with increased incidence rate of future stroke. However, the stroke incidence rate in CT-identified WMD is higher at each level of severity compared to rates in MRI-identified WMD. Patients with mild WMD via CT have a stroke incidence rate of 24.9 per 1,000 person-years, similar to that of patients with severe WMD via MRI. Among incidentally-discovered CBI patients with a determined CBI location, 97.9% are subcortical rather than cortical infarcts. CBI confers a similar risk of future stroke, whether cortical or subcortical, or whether MRI- or CT-detected.

CONCLUSIONS

Increasing severity of incidental WMD is associated with an increased risk of future symptomatic stroke, dependent on the imaging modality. Subcortical and cortical CBI conferred similar risks.

External Validation of Natural Language Processing Algorithms to Extract Common Data Elements in THA Operative Notes

BACKGROUND

Natural language processing (NLP) systems are distinctive in their ability to extract critical information from raw text in electronic health records (EHR). We previously developed three algorithms for total hip arthroplasty (THA) operative notes with rules aimed at capturing (1) operative approach, (2) fixation method, and (3) bearing surface using inputs from a single institution. The purpose of this study was to externally validate and improve these algorithms as a prerequisite for broader adoption in automated registry data curation.

METHODS

The previous NLP algorithms developed at Mayo Clinic were deployed and refined on EHRs from OrthoCarolina, evaluating 39 randomly selected primary THA operative reports from 2018 to 2021. Operative reports were available only in PDF format, requiring conversion to "readable" text with Adobe software. Accuracy statistics were calculated against manual chart review.

RESULTS

The operative approach, fixation technique, and bearing surface algorithms all demonstrated perfect accuracy of 100%. By comparison, validated performance at the developing center yielded an accuracy of 99.2% for operative approach, 90.7% for fixation technique, and 95.8% for bearing surface.

CONCLUSION

NLP algorithms applied to data from an external center demonstrated excellent accuracy in delineating common elements in THA operative notes. Notably, the algorithms had no functional problems evaluating scanned PDFs that were converted to "readable" text by common software. Taken together, these findings provide promise for NLP applied to scanned PDFs as a source to develop large registries by reliably extracting data of interest from very large unstructured data sets in an expeditious and cost-effective manner.

Identification of delirium from real-world electronic health record clinical notes

Introduction

We tested the ability of our natural language processing (NLP) algorithm to identify delirium episodes in a large-scale study using real-world clinical notes.

Methods

We used the Rochester Epidemiology Project to identify persons ≥ 65 years who were hospitalized between 2011 and 2017. We identified all persons with an International Classification of Diseases code for delirium within ±14 days of a hospitalization. We independently applied our NLP algorithm to all clinical notes for this same population. We calculated rates using number of delirium episodes as the numerator and number of hospitalizations as the denominator. Rates were estimated overall, by demographic characteristics, and by year of episode, and differences were tested using Poisson regression.

Results

In total, 14,255 persons had 37,554 hospitalizations between 2011 and 2017. The code-based delirium rate was 3.02 per 100 hospitalizations (95% CI: 2.85, 3.20). The NLP-based rate was 7.36 per 100 (95% CI: 7.09, 7.64). Rates increased with age (both p < 0.0001). Code-based rates were higher in men compared to women (p = 0.03), but NLP-based rates were similar by sex (p = 0.89). Code-based rates were similar by race and ethnicity, but NLP-based rates were higher in the White population compared to the Black and Asian populations (p = 0.001). Both types of rates increased significantly over time (both p values < 0.001).

Conclusions

The NLP algorithm identified more delirium episodes compared to the ICD code method. However, NLP may still underestimate delirium cases because of limitations in real-world clinical notes, including incomplete documentation, practice changes over time, and missing clinical notes in some time periods.

Systematic design and data-driven evaluation of social determinants of health ontology (SDoHO)

OBJECTIVE

Social determinants of health (SDoH) play critical roles in health outcomes and well-being. Understanding the interplay of SDoH and health outcomes is critical to reducing healthcare inequalities and transforming a "sick care" system into a "health-promoting" system. To address the SDOH terminology gap and better embed relevant elements in advanced biomedical informatics, we propose an SDoH ontology (SDoHO), which represents fundamental SDoH factors and their relationships in a standardized and measurable way.

MATERIAL AND METHODS

Drawing on the content of existing ontologies relevant to certain aspects of SDoH, we used a top-down approach to formally model classes, relationships, and constraints based on multiple SDoH-related resources. Expert review and coverage evaluation, using a bottom-up approach employing clinical notes data and a national survey, were performed.

RESULTS

We constructed the SDoHO with 708 classes, 106 object properties, and 20 data properties, with 1,561 logical axioms and 976 declaration axioms in the current version. Three experts achieved 0.967 agreement in the semantic evaluation of the ontology. A comparison between the coverage of the ontology and SDOH concepts in 2 sets of clinical notes and a national survey instrument also showed satisfactory results.

DISCUSSION

SDoHO could potentially play an essential role in providing a foundation for a comprehensive understanding of the associations between SDoH and health outcomes and paving the way for health equity across populations.

CONCLUSION

SDoHO has well-designed hierarchies, practical objective properties, and versatile functionalities, and the comprehensive semantic and coverage evaluation achieved promising performance compared to the existing ontologies relevant to SDoH.

[A medium- and long-term comparative observation on volumetric changes of cervical disc herniation after symmetrically or asymmetrically decompression and conservative treatment for cervical spondylotic myelopathy]

Objective: To compare the volumetric changes of cervical disc herniation (CDH) after cervical microendoscopic laminoplasty(CMEL),expansive open-door laminoplasty (EOLP) and conservative treatment. Methods: A retrospective study was conducted involving 101 patients with cervical spondylotic myelopathy(CSM),at the Department of Orthopaedic Surgery,the First Affiliated Hospital of Zhengzhou University from April 2012 to April 2021. The patients included 52 males and 49 females with an age of (54.7±11.8) years(range:25 to 86 years). Among them, 35 patients accepted CMEL treatment,33 patients accepted EOLP treatment,while 33 patients accepted conservative treatment. Volume data of CDH were measured by three-dimensional analysis of the initial and follow-up MRI images. The absorption rate and reprotrusion rate of CDH were calculated. The happening of resorption or reprotrusion was defined when the ratio was greater than 5%. The clinical outcomes and quality of life were evaluated by the Japanese Orthopaedic Association (JOA) score and the neck disability index (NDI).Quantitative data was analyzed by one-way ANOVA with post LSD-t test (multiple comparison) or Kruskal-Wallis test. Categorical data was analyzed by χ2 test. Results: The follow-up time of the CMEL group,EOLP group and the conservative treatment group were (27.6±18.8)months,(21.6±6.9)months and(24.9±16.3)months respectively with no significant difference(P>0.05). Changes of CDH volume in patients:(1) There were 96 CDH of 35 patients in the CMEL group,among which 78 showed absorption. The absorption frequency was 81.3%(78/96) and the absorption rate was ranged 5.9% to 90.9%;9 CDH showed reprotrusion,the reprotrusion frequency was 9.4% (9/96) and the reprotrusion rate was 5.9% to 13.3%;(2) There were 94 CDH of 33 patients in the EOLP group,of which 45 showed absorption. The absorption prevalence was 47.9% (45/94) and the absorption rate was 5.0% to 26.7%;20 CDH showed reprotruded,with the reprotrusion frequency of 21.3% (20/94) and the reprotrusion rate was 5.8% to 28.3%;(3) There were 102 CDH in 33 patients of the conservative group. Among them, 5 showed absorption. The absorption frequency was 4.9% (5/102),and the absorption rate was 7.2% to 14.3%;58 CDH showed reprotruded with the re-protrusion ratio of 56.9% (58/102) and the re-protrusion rate was 5.4% to 174.1%. The absorption ratio and reprotrusion ratio of the CMEL group were statistically different from EOLP group or the conservative group (P<0.01).The absorption ratio and reprotrusion ratio of the EOLP group was different from conservative group (all P<0.01). In terms of clinical outcomes, the excellent/good rate of the JOA score and NDI scores in the CMEL group were different from that of conservative group (all P<0.01) but not from that of the EOLP group(P>0.05). Conclusions: CMEL is an effective method for the treatment of CSM,making CDH easier to resorption compared to the EOLP or conservative treatment,thus making a better decompression effect on the nerves. This study enlightened on a new strategy for the clinical treatment of CSM.

The IMPACT framework and implementation for accessible in silico clinical phenotyping in the digital era

Clinical phenotyping is often a foundational requirement for obtaining datasets necessary for the development of digital health applications. Traditionally done via manual abstraction, this task is often a bottleneck in development due to time and cost requirements, therefore raising significant interest in accomplishing this task via in-silico means. Nevertheless, current in-silico phenotyping development tends to be focused on a single phenotyping task resulting in a dearth of reusable tools supporting cross-task generalizable in-silico phenotyping. In addition, in-silico phenotyping remains largely inaccessible for a substantial portion of potentially interested users. Here, we highlight the barriers to the usage of in-silico phenotyping and potential solutions in the form of a framework of several desiderata as observed during our implementation of such tasks. In addition, we introduce an example implementation of said framework as a software application, with a focus on ease of adoption, cross-task reusability, and facilitating the clinical phenotyping algorithm development process.

Acquisition of a Lexicon for Family History Information: Bidirectional Encoder Representations From Transformers-Assisted Sublanguage Analysis

BACKGROUND

A patient's family history (FH) information significantly influences downstream clinical care. Despite this importance, there is no standardized method to capture FH information in electronic health records and a substantial portion of FH information is frequently embedded in clinical notes. This renders FH information difficult to use in downstream data analytics or clinical decision support applications. To address this issue, a natural language processing system capable of extracting and normalizing FH information can be used.

OBJECTIVE

In this study, we aimed to construct an FH lexical resource for information extraction and normalization.

METHODS

We exploited a transformer-based method to construct an FH lexical resource leveraging a corpus consisting of clinical notes generated as part of primary care. The usability of the lexicon was demonstrated through the development of a rule-based FH system that extracts FH entities and relations as specified in previous FH challenges. We also experimented with a deep learning-based FH system for FH information extraction. Previous FH challenge data sets were used for evaluation.

RESULTS

The resulting lexicon contains 33,603 lexicon entries normalized to 6408 concept unique identifiers of the Unified Medical Language System and 15,126 codes of the Systematized Nomenclature of Medicine Clinical Terms, with an average number of 5.4 variants per concept. The performance evaluation demonstrated that the rule-based FH system achieved reasonable performance. The combination of the rule-based FH system with a state-of-the-art deep learning-based FH system can improve the recall of FH information evaluated using the BioCreative/N2C2 FH challenge data set, with the F1 score varied but comparable.

CONCLUSIONS

The resulting lexicon and rule-based FH system are freely available through the Open Health Natural Language Processing GitHub.

Gender-based Language Differences in Letters of Recommendation

Gender stereotyping is the practice of assigning or ascribing specific characteristics, differences, or identities to a person solely based on their gender. Biased conceptions of gender can create barriers to equality and need to be proactively identified and addressed. In biomedical education, letters of recommendation (LOR) are considered an important source for evaluating candidates' past performance. Because LOR is subjective and has no standard formatting requirements for the writer, potential language bias can be introduced. Natural language processing (NLP) offers a promising solution to detect language bias in LOR through automatic extraction of sensitive language and identification of letters with strong biases. In our study, we developed, evaluated, and deployed four NLP different methods (sublanguage analysis, dictionary-based approach, rule-based approach, and deep learning approach) for the extraction of psycholinguistics and thematic characteristics in LORs from three different physical therapy residency programs (Neurologic, Orthopaedic, and Sport) at Mayo Clinic. The evaluation statistics suggest that both MedTaggerIE model and Bidirectional Encoder Representations from Transformers model achieved moderate-high performance across eight different thematic categories. Through the pilot demonstration study, we learned that male writers were more likely to use the words 'intelligence', 'exceptional', and 'pursue' and male applicants were more likely to have the words 'strength', 'interpersonal skills', 'conversations', and 'pursue' in their letters of recommendation. Thematic analysis suggested that male and female writers have significant differences in expressing doubt, motivation, and recommendation. Findings derived from the study needed to be carefully interpreted based on the context of the study setting, residency programs, and data. A follow-up demonstration study is needed to further evaluate and interpret the findings.

YAP activation inhibits inflammatory signalling and cartilage breakdown associated with reduced primary cilia expression

OBJECTIVE

To clarify the role of YAP in modulating cartilage inflammation and degradation and the involvement of primary cilia and associated intraflagellar transport (IFT).

METHODS

Isolated primary chondrocytes were cultured on substrates of different stiffness (6-1000 kPa) or treated with YAP agonist lysophosphatidic acid (LPA) or YAP antagonist verteporfin (VP), or genetically modified by YAP siRNA, all ± IL1β. Nitric oxide (NO) and prostaglandin E2 (PGE2) release were measured to monitor IL1β response. YAP activity was quantified by YAP nuclear/cytoplasmic ratio and percentage of YAP-positive cells. Mechanical properties of cartilage explants were tested to confirm cartilage degradation. The involvement of primary cilia and IFT was analysed using IFT88 siRNA and ORPK cells with hypomorphic mutation of IFT88.

RESULTS

Treatment with LPA, or increasing polydimethylsiloxane (PDMS) substrate stiffness, activated YAP nuclear expression and inhibited IL1β-induced release of NO and PGE2, in isolated chondrocytes. Treatment with LPA also inhibited IL1β-mediated inflammatory signalling in cartilage explants and prevented matrix degradation and the loss of cartilage biomechanics. YAP activation reduced expression of primary cilia, knockdown of YAP in the absence of functional cilia/IFT failed to induce an inflammatory response.

CONCLUSIONS

We demonstrate that both pharmaceutical and mechanical activation of YAP blocks pro-inflammatory signalling induced by IL1β and prevents cartilage breakdown and the loss of biomechanical functionality. This is associated with reduced expression of primary cilia revealing a potential anti-inflammatory mechanism with novel therapeutic targets for treatment of osteoarthritis (OA).

Characterization of a kg-scale archaeological lead-based PbWO4 cryogenic detector for the RES-NOVA experiment

Core-collapse Supernovae (SNe) are one of the most energetic events in the Universe, during which almost all the star's binding energy is released in the form of neutrinos. These particles are direct probes of the processes occurring in the stellar core and provide unique insights into the gravitational collapse. RES-NOVA will revolutionize how we detect neutrinos from astrophysical sources, by deploying the first ton-scale array of cryogenic detectors made from archaeological lead. Pb offers the highest neutrino interaction cross-section via coherent elastic neutrino-nucleus scattering (CEνNS). Such process will enable RES-NOVA to be equally sensitive to all neutrino flavours. For the first time, we propose the use archaeological Pb as sensitive target material in order to achieve an ultra-low background level in the region of interest (O(1 keV)). All these features make possible the deployment of the first cm-scale neutrino telescope for the investigation of astrophysical sources. In this contribution, we will characterize the radiopurity level and the performance of a small-scale proof-of-principle detector of RES-NOVA, consisting in a PbWO₄ crystal made from archaeological-Pb operated as cryogenic detector.

Recommended practices and ethical considerations for natural language processing-assisted observational research: A scoping review

An increasing number of studies have reported using natural language processing (NLP) to assist observational research by extracting clinical information from electronic health records (EHRs). Currently, no standardized reporting guidelines for NLP-assisted observational studies exist. The absence of detailed reporting guidelines may create ambiguity in the use of NLP-derived content, knowledge gaps in the current research reporting practices, and reproducibility challenges. To address these issues, we conducted a scoping review of NLP-assisted observational clinical studies and examined their reporting practices, focusing on NLP methodology and evaluation. Through our investigation, we discovered a high variation regarding the reporting practices, such as inconsistent use of references for measurement studies, variation in the reporting location (reference, appendix, and manuscript), and different granularity of NLP methodology and evaluation details. To promote the wide adoption and utilization of NLP solutions in clinical research, we outline several perspectives that align with the six principles released by the World Health Organization (WHO) that guide the ethical use of artificial intelligence for health.

Prediction of knee pain improvement over two years for knee osteoarthritis using a dynamic nomogram based on MRI-derived radiomics: a proof-of-concept study

OBJECTIVES

To develop and validate a nomogram to detect improved knee pain in osteoarthritis (OA) by integrating magnetic resonance imaging (MRI) radiomics signature of subchondral bone and clinical characteristics.

METHODS

Participants were selected from the Vitamin D Effects on Osteoarthritis (VIDEO) study. The primary outcome was 20% improvement of knee pain score over 2 years in participants administrated either vitamin D or placebo. Radiomics features of subchondral bone and clinical characteristics from 216 participants were extracted and analyzed. The participants were randomly split into the training and validation cohorts at a ratio of 8:2. Least absolute shrinkage and selection operator (LASSO) regression was used to select features and generate radiomics signatures. The optimal radiomics signature and clinical indicators were fitted into a nomogram using multivariable logistic regression model.

RESULTS

The nomogram showed favorable discrimination performance [AUC_training, 0.79 (95% CI: 0.72-0.79), AUC_validation, 0.83 (95% CI: 0.70-0.96)] as well as a good calibration. Additional contributing value of fusion radiomics signature to the nomogram was statistically significant (NRI, 0.23; IDI, 0.14, P < 0.001 in training cohort and NRI, 0.29; IDI, 0.18, P < 0.05 in validating cohort). Decision curve analysis confirmed the clinical usefulness of nomogram.

CONCLUSION

The radiomics-based nomogram comprising the MR radiomics signature and clinical variables achieves a favorable predictive efficacy and accuracy in differentiating improvement in knee pain among OA patients. This proof-of-concept study provides a promising way to predict clinically meaningful outcomes.

Predicting Physiological Response in Heart Failure Management: A Graph Representation Learning Approach using Electronic Health Records

Heart failure management is challenging due to the complex and heterogenous nature of its pathophysiology which makes the conventional treatments based on the "one size fits all" ideology not suitable. Coupling the longitudinal medical data with novel deep learning and network-based analytics will enable identifying the distinct patient phenotypic characteristics to help individualize the treatment regimen through the accurate prediction of the physiological response. In this study, we develop a graph representation learning framework that integrates the heterogeneous clinical events in the electronic health records (EHR) as graph format data, in which the patient-specific patterns and features are naturally infused for personalized predictions of lab test response. The framework includes a novel Graph Transformer Network that is equipped with a self-attention mechanism to model the underlying spatial interdependencies among the clinical events characterizing the cardiac physiological interactions in the heart failure treatment and a graph neural network (GNN) layer to incorporate the explicit temporality of each clinical event, that would help summarize the therapeutic effects induced on the physiological variables, and subsequently on the patient's health status as the heart failure condition progresses over time. We introduce a global attention mask that is computed based on event co-occurrences and is aggregated across all patient records to enhance the guidance of neighbor selection in graph representation learning. We test the feasibility of our model through detailed quantitative and qualitative evaluations on observational EHR data.

Hair Zinc and Chromium Levels Were Associated with a Reduced Likelihood of Age Related Cognitive Decline in Centenarians and Oldest-Old Adults

BACKGROUND

Cognitive function has inevitable decline with advancing age in nature, and age-related cognitive decline (ARCD) is of increasing concern to aging population. Scarce study has involved the associations between hair trace elements and ARCD in older adults, especially in centenarians and oldest-old adults. This study was to investigate the associations between hair trace elements and ARCD in centenarians and oldest-old adults.

METHODS

Based on the household registration information of centenarians and oldest-old adults provided by the Civil Affairs Department of Hainan Province, China, the investigators conducted a one-to-one household survey among centenarians (≥100 years old) and oldest-old adults (80-99 years old). All 50 centenarians had a median age of 103 years and females accounted for 68.0%. All 73 oldest-old adults aged 80-99 years had a median age of 90 years and females accounted for 82.2%. Basic information were obtained with questionnaire interview, physical examination, biological test and hair collection by pre-trained local doctors and nurses. An inductively coupled plasma mass spectrometer was used to measure hair trace elements. All data in this study comes from China. Age, sex, body mass index, systolic blood pressure, diastolic blood pressure, smoking, drinking, hemoglobin, albumin, fasting blood pressure, zinc, chromium, copper, selenium, iron, manganese, strontium, lead, magnesium, potassium, and barium were simultaneously included in multivariate Logistic regression analysis. One adjusted model was done with all hair trace elements together.

RESULTS

Zinc and chromium levels were significantly lower in participants with ARCD than those without ARCD (P < 0.05 for all). Multivariate Logistic regression analysis indicated that zinc [odds ratio (OR): 0.988, 95%confidence interval (95%CI): 0.977-0.999] and chromium (OR: 0.051, 95%CI: 0.004-0.705) were associated with a reduced likelihood of ARCD (P < 0.05 for all).

CONCLUSIONS

Hair zinc and chromium levels were associated with a reduced likelihood of ARCD in centenarians and oldest-old adults. Further studies are necessary to verify if zinc and chromium supplementation has the potential to improve cognitive function and prevent ARCD development.

Prediction Models for Knee Osteoarthritis: Review of Current Models and Future Directions

Background

Knee osteoarthritis (OA) is a prevalent joint disease. Clinical prediction models consider a wide range of risk factors for knee OA. This review aimed to evaluate published prediction models for knee OA and identify opportunities for future model development.

Methods

We searched Scopus, PubMed, and Google Scholar using the terms knee osteoarthritis, prediction model, deep learning, and machine learning. All the identified articles were reviewed by one of the researchers and we recorded information on methodological characteristics and findings. We only included articles that were published after 2000 and reported a knee OA incidence or progression prediction model.

Results

We identified 26 models of which 16 employed traditional regression-based models and 10 machine learning (ML) models. Four traditional and five ML models relied on data from the Osteoarthritis Initiative. There was significant variation in the number and type of risk factors. The median sample size for traditional and ML models was 780 and 295, respectively. The reported Area Under the Curve (AUC) ranged between 0.6 and 1.0. Regarding external validation, 6 of the 16 traditional models and only 1 of the 10 ML models validated their results in an external data set.

Conclusion

Diverse use of knee OA risk factors, small, non-representative cohorts, and use of magnetic resonance imaging which is not a routine evaluation tool of knee OA in daily clinical practice are some of the main limitations of current knee OA prediction models.

Assessing document section heterogeneity across multiple electronic health record systems for computational phenotyping: A case study of heart-failure phenotyping algorithm

BACKGROUND

The incorporation of information from clinical narratives is critical for computational phenotyping. The accurate interpretation of clinical terms highly depends on their associated context, especially the corresponding clinical section information. However, the heterogeneity across different Electronic Health Record (EHR) systems poses challenges in utilizing the section information.

OBJECTIVES

Leveraging the eMERGE heart failure (HF) phenotyping algorithm, we assessed the heterogeneity quantitatively through the performance comparison of machine learning (ML) classifiers which map clinical sections containing HF-relevant terms across different EHR systems to standard sections in Health Level 7 (HL7) Clinical Document Architecture (CDA).

METHODS

We experimented with both random forest models with sentence-embedding features and bidirectional encoder representations from transformers models. We trained MLs using an automated labeled corpus from an EHR system that adopted HL7 CDA standard. We assessed the performance using a blind test set (n = 300) from the same EHR system and a gold standard (n = 900) manually annotated from three other EHR systems.

RESULTS

The F-measure of those ML models varied widely (0.00-0.91%), indicating MLs with one tuning parameter set were insufficient to capture sections across different EHR systems. The error analysis indicates that the section does not always comply with the corresponding standardized sections, leading to low performance.

CONCLUSIONS

We presented the potential use of ML techniques to map the sections containing HF-relevant terms in multiple EHR systems to standard sections. However, the findings suggested that the quality and heterogeneity of section structure across different EHRs affect applications due to the poor adoption of documentation standards.

Characterizing Performance Gaps of a Code-Based Dementia Algorithm in a Population-Based Cohort of Cognitive Aging

BACKGROUND

Multiple algorithms with variable performance have been developed to identify dementia using combinations of billing codes and medication data that are widely available from electronic health records (EHR). If the characteristics of misclassified patients are clearly identified, modifying existing algorithms to improve performance may be possible.

OBJECTIVE

To examine the performance of a code-based algorithm to identify dementia cases in the population-based Mayo Clinic Study of Aging (MCSA) where dementia diagnosis (i.e., reference standard) is actively assessed through routine follow-up and describe the characteristics of persons incorrectly categorized.

METHODS

There were 5,316 participants (age at baseline (mean (SD)): 73.3 (9.68) years; 50.7% male) without dementia at baseline and available EHR data. ICD-9/10 codes and prescription medications for dementia were extracted between baseline and one year after an MCSA dementia diagnosis or last follow-up. Fisher's exact or Kruskal-Wallis tests were used to compare characteristics between groups.

RESULTS

Algorithm sensitivity and specificity were 0.70 (95% CI: 0.67, 0.74) and 0.95 (95% CI: 0.95, 0.96). False positives (i.e., participants falsely diagnosed with dementia by the algorithm) were older, with higher Charlson comorbidity index, more likely to have mild cognitive impairment (MCI), and longer follow-up (versus true negatives). False negatives (versus true positives) were older, more likely to have MCI, or have more functional limitations.

CONCLUSIONS

We observed a moderate-high performance of the code-based diagnosis method against the population-based MCSA reference standard dementia diagnosis. Older participants and those with MCI at baseline were more likely to be misclassified.

Natural Language Processing CAM Algorithm Improves Delirium Detection Compared With Conventional Methods

Delirium is known to be underdiagnosed and underdocumented. Delirium detection in retrospective studies occurs mostly by clinician diagnosis or nursing documentation. This study aims to assess the effectiveness of natural language processing-confusion assessment method (NLP-CAM) algorithm when compared to conventional modalities of delirium detection. A multicenter retrospective study analyzed 4351 COVID-19 hospitalized patient records to identify delirium occurrence utilizing three different delirium detection modalities namely clinician diagnosis, nursing documentation, and the NLP-CAM algorithm. Delirium detection by any of the 3 methods is considered positive for delirium occurrence as a comparison. NLP-CAM captured 80% of overall delirium, followed by clinician diagnosis at 55%, and nursing flowsheet documentation at 43%. Increase in age, Charlson comorbidity score, and length of hospitalization had increased delirium detection odds regardless of the detection method. Artificial intelligence-based NLP-CAM algorithm, compared to conventional methods, improved delirium detection from electronic health records and holds promise in delirium diagnostics.

Association of Incidentally Discovered Covert Cerebrovascular Disease Identified Using Natural Language Processing and Future Dementia

Background Covert cerebrovascular disease (CCD) has been shown to be associated with dementia in population-based studies with magnetic resonance imaging (MRI) screening, but dementia risk associated with incidentally discovered CCD is not known. Methods and Results Individuals aged ≥50 years enrolled in the Kaiser Permanente Southern California health system receiving head computed tomography (CT) or MRI for nonstroke indications from 2009 to 2019, without prior ischemic stroke/transient ischemic attack, dementia/Alzheimer disease, or visit reason/scan indication suggestive of cognitive decline or stroke were included. Natural language processing identified incidentally discovered covert brain infarction (id-CBI) and white matter disease (id-WMD) on the neuroimage report; white matter disease was characterized as mild, moderate, severe, or undetermined. We estimated risk of dementia associated with id-CBI and id-WMD. Among 241 050 qualified individuals, natural language processing identified 69 931 (29.0%) with id-WMD and 11 328 (4.7%) with id-CBI. Dementia incidence rates (per 1000 person-years) were 23.5 (95% CI, 22.9-24.0) for patients with id-WMD, 29.4 (95% CI, 27.9-31.0) with id-CBI, and 6.0 (95% CI, 5.8-6.2) without id-CCD. The association of id-WMD with future dementia was stronger in younger (aged <70 years) versus older (aged ≥70 years) patients and for CT- versus MRI-discovered lesions. For patients with versus without id-WMD on CT, the adjusted HR was 2.87 (95% CI, 2.58-3.19) for older and 1.87 (95% CI, 1.79-1.95) for younger patients. For patients with versus without id-WMD on MRI, the adjusted HR for dementia risk was 2.28 (95% CI, 1.99-2.62) for older and 1.48 (95% CI, 1.32-1.66) for younger patients. The adjusted HR for id-CBI was 2.02 (95% CI, 1.70-2.41) for older and 1.22 (95% CI, 1.15-1.30) for younger patients for either modality. Dementia risk was strongly correlated with id-WMD severity; adjusted HRs compared with patients who were negative for id-WMD by MRI ranged from 1.41 (95% CI, 1.25-1.60) for those with mild disease on MRI to 4.11 (95% CI, 3.58-4.72) for those with severe disease on CT. Conclusions Incidentally discovered CCD is common and associated with a high risk of dementia, representing an opportunity for prevention. The association is strengthened when discovered at younger age, by increasing id-WMD severity, and when id-WMD is detected by CT scan rather than MRI.

Early on-treatment tumor growth rate (EOT-TGR) determines treatment outcomes of advanced non-small-cell lung cancer patients treated with programmed cell death protein 1 axis inhibitor

BACKGROUND

Tumor growth rate (TGR), denoted as percentage change in tumor size per month, is a well-established indicator of tumor growth kinetics. The predictive value of early on-treatment TGR (EOT-TGR) for immunotherapy remains unclear. We sought to establish and validate the association of EOT-TGR with treatment outcomes in patients with advanced non-small-cell lung cancer (aNSCLC) undergoing anti-PD-1/PD-L1 (programmed cell death protein 1/programmed death-ligand 1) therapy.

PATIENTS AND METHODS

This bicenter retrospective cohort study included a training cohort, a contemporaneously treated internal validation cohort, and an external validation cohort. Computed tomography images were retrieved to calculate EOT-TGR, denoted as tumor burden change per month during a period between baseline and the first imaging evaluation after immunotherapy. Kaplan-Meier methodology and Cox regression analysis were conducted for survival analyses.

RESULTS

In the pooled cohort (n = 172), 125 patients (72.7%) were males; median age at diagnosis was 58 (range 28-79) years. Based on the training cohort, we determined the optimal cut-off value for EOT-TGR as 10.4%/month. Higher EOT-TGR was significantly associated with inferior overall survival [OS; hazard ratio (HR) 2.93, 95% confidence interval (CI) 1.47-5.83; P = 0.002], worse progression-free survival (PFS; HR 2.44, 95% CI 1.46-4.08; P = 0.001), and lower objective response rate (3.3% versus 20.9%; P = 0.040) and durable clinical benefit rate (6.7% versus 41.9%; P = 0.001). Results were reproducible in the two validation cohorts for OS and PFS. Among 43 patients who had a best response of progressive disease in the training cohort, those with high EOT-TGR had worse OS (HR 2.64; P = 0.041) and were more likely to progress due to target lesions at the first tumor evaluation (85.2% versus 0.0%; P <0.001).

CONCLUSIONS

Higher EOT-TGR was associated with inferior OS and immunotherapeutic response in patients with aNSCLC undergoing anti-PD-1/PD-L1 therapy. This easy-to-calculate radiologic biomarker may help evaluate the abilities of immunotherapy to prolong survival and assist in tailoring patients' management.

TRIAL REGISTRATION

ClinicalTrials.govNCT04722406; https://clinicaltrials.gov/ct2/show/NCT04722406.

Development of Parkinson Disease and Its Relationship with Incidentally Discovered White Matter Disease and Covert Brain Infarction in a Real-World Cohort

OBJECTIVE

This study aimed to examine the relationship between covert cerebrovascular disease, comprised of covert brain infarction and white matter disease, discovered incidentally in routine care, and subsequent Parkinson disease.

METHODS

Patients were ≥50 years and received neuroimaging for non-stroke indications in the Kaiser Permanente Southern California system from 2009 to 2019. Natural language processing identified incidentally discovered covert brain infarction and white matter disease and classified white matter disease severity. The Parkinson disease outcome was defined as 2 ICD diagnosis codes.

RESULTS

230,062 patients were included (median follow-up 3.72 years). A total of 1,941 Parkinson disease cases were identified (median time-to-event 2.35 years). Natural language processing identified covert cerebrovascular disease in 70,592 (30.7%) patients, 10,622 (4.6%) with covert brain infarction and 65,814 (28.6%) with white matter disease. After adjustment for known risk factors, white matter disease was associated with Parkinson disease (hazard ratio 1.67 [95%CI, 1.44, 1.93] for patients <70 years and 1.33 [1.18, 1.50] for those ≥70 years). Greater severity of white matter disease was associated with increased incidence of Parkinson disease(/1,000 person-years), from 1.52 (1.43, 1.61) in patients without white matter disease to 4.90 (3.86, 6.13) in those with severe disease. Findings were robust when more specific definitions of Parkinson disease were used. Covert brain infarction was not associated with Parkinson disease (adjusted hazard ratio = 1.05 [0.88, 1.24]).

INTERPRETATION

Incidentally discovered white matter disease was associated with subsequent Parkinson disease, an association strengthened with younger age and increased white matter disease severity. Incidentally discovered covert brain infarction did not appear to be associated with subsequent Parkinson disease. ANN NEUROL 2022;92:620-630.

Quality assessment of functional status documentation in EHRs across different healthcare institutions

The secondary use of electronic health records (EHRs) faces challenges in the form of varying data quality-related issues. To address that, we retrospectively assessed the quality of functional status documentation in EHRs of persons participating in Mayo Clinic Study of Aging (MCSA). We used a convergent parallel design to collect quantitative and qualitative data and independently analyzed the findings. We discovered a heterogeneous documentation process, where the care practice teams, institutions, and EHR systems all play an important role in how text data is documented and organized. Four prevalent instrument-assisted documentation (iDoc) expressions were identified based on three distinct instruments: Epic smart form, questionnaire, and occupational therapy and physical therapy templates. We found strong differences in the usage, information quality (intrinsic and contextual), and naturality of language among different type of iDoc expressions. These variations can be caused by different source instruments, information providers, practice settings, care events and institutions. In addition, iDoc expressions are context specific and thus shall not be viewed and processed uniformly. We recommend conducting data quality assessment of unstructured EHR text prior to using the information.

Real-time risk prediction of colorectal surgery-related post-surgical complications using GRU-D model

BACKGROUND

Post-surgical complications (PSCs) have been an increasing concern for hospitals in light of Medicare penalties for 30-day readmissions. PSCs have become a target for quality improvement and benchmark for the healthcare system. Over half (60 %) of the deep or organ space surgical site infections are discovered after discharge, leading to a readmission. There has thus been a push to develop risk prediction models for targeted preventive interventions for PSCs.

OBJECTIVE

We experiment several Gated Recurrent Unit with Decay (GRU-D) based deep learning architectures with various feature sampling schemes in predicting the risk of colorectal PSCs and compare with atemporal logistic regression models (logit).

METHOD

We used electronic health record (EHR) data of 3,535 colorectal surgical patients involved in the national surgical quality improvement program (NSQIP) between 2006 and 2018. Single layer, stacked layer, and multimodal GRU-D models with sigmoid activation were used to develop risk prediction models. Area Under the Receiver Operating Characteristic curve (AUROC) was calculated by comparing predicted probability of developing complications versus truly observed PSCs (NSQIP adjudicated) within 30 days after surgery. We set up cross-validation and an independent held-out dataset for testing model performance consistency.

RESULTS AND CONCLUSION

The primary contribution of our study is the formulation of a novel real-time PSC risk prediction task using GRU-D with demonstrated clinical utility. GRU-D outperforms the logit model in predicting wound and organ space infection and shows improved performance as additional data points become available. Logit model outperforms GRU-D before surgery for superficial infection and bleeding. For the same sampling scheme, there is no obvious advantage of complex architectures (stacked, multimodal) over single layer GRU-D. Obtaining more data points closer to the occurrence of PSCs is more important than using a more frequent sampling scheme in training GRU-D models. The fourth predicted risk quartile by single layer GRU-D contains 63 %, 59 %, and 66 % organ space infection cases, at 4 h before, 72 h after, and 168 h after surgery, respectively, suggesting its potential application as a bedside risk assessment tool.

[A preliminary exploration into the efficacy of personalized surgical schemes in the repair of maxillary sinus perforation and maxillary sinus fistula]

To explore the efficacy and value of personalized surgical schemes in the repair of maxillary sinus perforation and maxillary sinus fistula based on the size of the maxillary sinus perforation and maxillary sinus fistula. A total of 28 patients with maxillary sinus perforation and maxillary sinus fistula who were admitted to the Department of Oral and Maxillofacial Surgery, Stomatology Hospital of Kunming Medical University from July 2017 to May 2020 were included to conduct a prospective case clinical study. After the inflammation in the maxillary sinus was controlled, a proper surgical repair method was selected according to the size of the perforation and fistula based on the double-layer closure technique. The diameter of the perforation and fistula was measured with the assistance of cone-beam CT. After that, the platelet rich fibrin (PRF) repair was performed on the perforation and fistula with 3 mm≤diameter<7 mm in size in 14 patients. The PRF repair and buccal flap repair were performed on the perforation and fistula with 7 mm ≤diameter<15 mm in size in 7 patients. The adjacent buccal pad repair, palatine flap repair, and buccal flap repair were performed on the perforation and fistula with 15 mm≤ diameter<25 mm in size in 4 patients. The nasolabial axial flap repair and nasolabial free flap repair were performed on the perforation and fistula with a diameter ≥25 mm in size in 3 patients. The medical follow-up was conducted in all patients in the 1st, 2nd, and 4th week after surgery, with an overall success rate reaching 96.4% (27/28) after the initial intervention. The relapse of disease occurred in one patient (4.6%) with diabetes and a smoking history in the 2nd week after surgery. Identifying a proper surgical repair method according to the size of the oral and maxillary sinus perforation and maxillary sinus fistula based on the double-layer closure technique can improve the one-time cure rate in these patients under the premise that the inflammation in the maxillary sinus can be controlled.

Assessment of Electronic Health Record for Cancer Research and Patient Care Through a Scoping Review of Cancer Natural Language Processing

PURPOSE

The advancement of natural language processing (NLP) has promoted the use of detailed textual data in electronic health records (EHRs) to support cancer research and to facilitate patient care. In this review, we aim to assess EHR for cancer research and patient care by using the Minimal Common Oncology Data Elements (mCODE), which is a community-driven effort to define a minimal set of data elements for cancer research and practice. Specifically, we aim to assess the alignment of NLP-extracted data elements with mCODE and review existing NLP methodologies for extracting said data elements.

METHODS

Published literature studies were searched to retrieve cancer-related NLP articles that were written in English and published between January 2010 and September 2020 from main literature databases. After the retrieval, articles with EHRs as the data source were manually identified. A charting form was developed for relevant study analysis and used to categorize data including four main topics: metadata, EHR data and targeted cancer types, NLP methodology, and oncology data elements and standards.

RESULTS

A total of 123 publications were selected finally and included in our analysis. We found that cancer research and patient care require some data elements beyond mCODE as expected. Transparency and reproductivity are not sufficient in NLP methods, and inconsistency in NLP evaluation exists.

CONCLUSION

We conducted a comprehensive review of cancer NLP for research and patient care using EHRs data. Issues and barriers for wide adoption of cancer NLP were identified and discussed.

Stratifying Future Stroke Risk with Incidentally Discovered White Matter Disease Severity and Covert Brain Infarct Site

BACKGROUND

Covert cerebrovascular disease (CCD) includes white matter disease (WMD) and covert brain infarction (CBI). Incidentally discovered CCD is associated with increased risk of subsequent symptomatic stroke. However, it is unknown whether the severity of WMD or the location of CBI predicts risk.

OBJECTIVES

The aim of this study was to examine the association of incidentally discovered WMD severity and CBI location with risk of subsequent symptomatic stroke.

METHOD

This retrospective cohort study includes patients aged ≥50 years old in the Kaiser Permanente Southern California health system who received neuroimaging for a nonstroke indication between 2009 and 2019. Incidental CBI and WMD were identified via natural language processing of the neuroimage report, and WMD severity was classified into grades.

RESULTS

A total of 261,960 patients received neuroimaging; 78,555 patients (30.0%) were identified to have incidental WMD and 12,857 patients (4.9%) to have incidental CBI. Increasing WMD severity is associated with an increased incidence rate of future stroke. However, the stroke incidence rate in CT-identified WMD is higher at each level of severity compared to rates in MRI-identified WMD. Patients with mild WMD via CT have a stroke incidence rate of 24.9 per 1,000 person-years, similar to that of patients with severe WMD via MRI. Among incidentally discovered CBI patients with a determined CBI location, 97.9% are subcortical rather than cortical infarcts. CBI confers a similar risk of future stroke, whether cortical or subcortical or whether MRI- or CT-detected.

CONCLUSIONS

Increasing severity of incidental WMD is associated with an increased risk of future symptomatic stroke, dependent on the imaging modality. Subcortical and cortical CBI conferred similar risks.

Prediction of Incident Dementia Using Patient Temporal Health Status

Dementia is one of the most prevalent health problems in the aging population. Despite the significant number of people affected, dementia diagnoses are often significantly delayed, missing opportunities to maximize life quality. Early identification of older adults at high risk for dementia may help to maximize current quality of life and to improve planning for future health needs in dementia patients. However, most existing risk prediction models predominantly use static variables, not considering temporal patterns of health status. This study used an attention-based time-aware model to predict incident dementia that incorporated longitudinal temporal health conditions. The predictive performance of the time-aware model was compared with three traditional models using static variables and demonstrated higher predictive power.

The Implication of Latent Information Quality to the Reproducibility of Secondary Use of Electronic Health Records

Reproducibility is an important quality criterion for the secondary use of electronic health records (EHRs). However, multiple barriers to reproducibility are embedded in the heterogeneous EHR environment. These barriers include complex processes for collecting and organizing EHR data and dynamic multi-level interactions occurring during information use (e.g., inter-personal, inter-system, and cross-institutional). To ensure reproducible use of EHRs, we investigated four information quality dimensions and examine the implications for reproducibility based on a real-world EHR study. Four types of IQ measurements suggested that barriers to reproducibility occurred for all stages of secondary use of EHR data. We discussed our recommendations and emphasized the importance of promoting transparent, high-throughput, and accessible data infrastructures and implementation best practices (e.g., data quality assessment, reporting standard).

BETA: a comprehensive benchmark for computational drug-target prediction

Internal validation is the most popular evaluation strategy used for drug-target predictive models. The simple random shuffling in the cross-validation, however, is not always ideal to handle large, diverse and copious datasets as it could potentially introduce bias. Hence, these predictive models cannot be comprehensively evaluated to provide insight into their general performance on a variety of use-cases (e.g. permutations of different levels of connectiveness and categories in drug and target space, as well as validations based on different data sources). In this work, we introduce a benchmark, BETA, that aims to address this gap by (i) providing an extensive multipartite network consisting of 0.97 million biomedical concepts and 8.5 million associations, in addition to 62 million drug-drug and protein-protein similarities and (ii) presenting evaluation strategies that reflect seven cases (i.e. general, screening with different connectivity, target and drug screening based on categories, searching for specific drugs and targets and drug repurposing for specific diseases), a total of seven Tests (consisting of 344 Tasks in total) across multiple sampling and validation strategies. Six state-of-the-art methods covering two broad input data types (chemical structure- and gene sequence-based and network-based) were tested across all the developed Tasks. The best-worst performing cases have been analyzed to demonstrate the ability of the proposed benchmark to identify limitations of the tested methods for running over the benchmark tasks. The results highlight BETA as a benchmark in the selection of computational strategies for drug repurposing and target discovery.

Risk Factors for Silent Brain Infarcts and White Matter Disease in a Real-World Cohort Identified by Natural Language Processing

OBJECTIVE

To assess the frequency of silent brain infarcts (SBIs) and white matter disease (WMD) and associations with stroke risk factors (RFs) in a real-world population.

PATIENTS AND METHODS

This was an observational study of patients 50 years or older in the Kaiser Permanente Southern California health system from January 1, 2009, through June 30, 2019, with head computed tomography or magnetic resonance imaging for nonstroke indications and no history of stroke, transient ischemic attack, or dementia. A natural language processing (NLP) algorithm was applied to the electronic health record to identify individuals with reported SBIs or WMD. Multivariable Poisson regression estimated risk ratios of demographic characteristics, RFs, and scan modality on the presence of SBIs or WMD.

RESULTS

Among 262,875 individuals, the NLP identified 13,154 (5.0%) with SBIs and 78,330 (29.8%) with WMD. Stroke RFs were highly prevalent. Advanced age was strongly associated with increased risk of SBIs (adjusted relative risks [aRRs], 1.90, 3.23, and 4.72 for those aged in their 60s, 70s, and ≥80s compared with those in their 50s) and increased risk of WMD (aRRs, 1.79, 3.02, and 4.53 for those aged in their 60s, 70s, and ≥80s compared with those in their 50s). Magnetic resonance imaging was associated with a reduced risk of SBIs (aRR, 0.87; 95% CI, 0.83 to 0.91) and an increased risk of WMD (aRR, 2.86; 95% CI, 2.83 to 2.90). Stroke RFs had modest associations with increased risk of SBIs or WMD.

CONCLUSION

An NLP algorithm can identify a large cohort of patients with incidentally discovered SBIs and WMD. Advanced age is strongly associated with incidentally discovered SBIs and WMD.

Detection of Dementia Signals from Longitudinal Clinical Visits Using One-Class Classification

Dementia is one of the major health challenges in aging populations, with 50 million people diagnosed worldwide. However, dementia is often underdiagnosed or delayed resulting in missed opportunities for appropriate care plans. Identifying early signs of dementia is essential for better life quality of aging populations. Monitoring early signs of individual health changes could help clinicians diagnose dementia in its early stages with more effective treatment plans. However, rare data for dementia cases compared to the normal (i.e., imbalance class distribution) make it challenging to develop robust supervised learning models. In order to alleviate this issue, we investigated one-class classification (OCC) techniques, which use only majority class (i.e., normal cases) in model development to detect dementia signals from older adult clinical visits. The OCC models identify abnormality of older adults' longitudinal health conditions to predict incident dementia. The predictive performance of the OCC was compared with a recent streaming clustering-based technique and demonstrated higher predictive power. Our analysis showed that OCC has a promising potential to increase power in predicting dementia.