Natural language processing for the assessment of cardiovascular disease comorbidities: The cardio-Canary comorbidity project

Collaborative and privacy-enhancing workflows on a clinical data warehouse: an example developing natural language processing pipelines to detect medical conditions

OBJECTIVE

To develop and validate a natural language processing (NLP) pipeline that detects 18 conditions in French clinical notes, including 16 comorbidities of the Charlson index, while exploring a collaborative and privacy-enhancing workflow.

MATERIALS AND METHODS

The detection pipeline relied both on rule-based and machine learning algorithms, respectively, for named entity recognition and entity qualification, respectively. We used a large language model pre-trained on millions of clinical notes along with annotated clinical notes in the context of 3 cohort studies related to oncology, cardiology, and rheumatology. The overall workflow was conceived to foster collaboration between studies while respecting the privacy constraints of the data warehouse. We estimated the added values of the advanced technologies and of the collaborative setting.

RESULTS

The pipeline reached macro-averaged F1-score positive predictive value, sensitivity, and specificity of 95.7 (95%CI 94.5-96.3), 95.4 (95%CI 94.0-96.3), 96.0 (95%CI 94.0-96.7), and 99.2 (95%CI 99.0-99.4), respectively. F1-scores were superior to those observed using alternative technologies or non-collaborative settings. The models were shared through a secured registry.

CONCLUSIONS

We demonstrated that a community of investigators working on a common clinical data warehouse could efficiently and securely collaborate to develop, validate and use sensitive artificial intelligence models. In particular, we provided an efficient and robust NLP pipeline that detects conditions mentioned in clinical notes.

Comorbidity-Guided Text Mining and Omics Pipeline to Identify Candidate Genes and Drugs for Alzheimer's Disease

Alzheimer's disease (AD), a multifactorial neurodegenerative disorder, is prevalent among the elderly population. It is a complex trait with mutations in multiple genes. Although the US Food and Drug Administration (FDA) has approved a few drugs for AD treatment, a definitive cure remains elusive. Research efforts persist in seeking improved treatment options for AD. Here, a hybrid pipeline is proposed to apply text mining to identify comorbid diseases for AD and an omics approach to identify the common genes between AD and five comorbid diseases-dementia, type 2 diabetes, hypertension, Parkinson's disease, and Down syndrome. We further identified the pathways and drugs for common genes. The rationale behind this approach is rooted in the fact that elderly individuals often receive multiple medications for various comorbid diseases, and an insight into the genes that are common to comorbid diseases may enhance treatment strategies. We identified seven common genes-PSEN1, PSEN2, MAPT, APP, APOE, NOTCH, and HFE-for AD and five comorbid diseases. We investigated the drugs interacting with these common genes using LINCS gene-drug perturbation. Our analysis unveiled several promising candidates, including MG-132 and Masitinib, which exhibit potential efficacy for both AD and its comorbid diseases. The pipeline can be extended to other diseases.

Using natural language processing for automated classification of disease and to identify misclassified ICD codes in cardiac disease

Aims

ICD codes are used for classification of hospitalizations. The codes are used for administrative, financial, and research purposes. It is known, however, that errors occur. Natural language processing (NLP) offers promising solutions for optimizing the process. To investigate methods for automatic classification of disease in unstructured medical records using NLP and to compare these to conventional ICD coding.

Methods and results

Two datasets were used: the open-source Medical Information Mart for Intensive Care (MIMIC)-III dataset (n = 55.177) and a dataset from a hospital in Belgium (n = 12.706). Automated searches using NLP algorithms were performed for the diagnoses 'atrial fibrillation (AF)' and 'heart failure (HF)'. Four methods were used: rule-based search, logistic regression, term frequency-inverse document frequency (TF-IDF), Extreme Gradient Boosting (XGBoost), and Bio-Bidirectional Encoder Representations from Transformers (BioBERT). All algorithms were developed on the MIMIC-III dataset. The best performing algorithm was then deployed on the Belgian dataset. After preprocessing a total of 1438 reports was retained in the Belgian dataset. XGBoost on TF-IDF matrix resulted in an accuracy of 0.94 and 0.92 for AF and HF, respectively. There were 211 mismatches between algorithm and ICD codes. One hundred and three were due to a difference in data availability or differing definitions. In the remaining 108 mismatches, 70% were due to incorrect labelling by the algorithm and 30% were due to erroneous ICD coding (2% of total hospitalizations).

Conclusion

A newly developed NLP algorithm attained a high accuracy for classifying disease in medical records. XGBoost outperformed the deep learning technique BioBERT. NLP algorithms could be used to identify ICD-coding errors and optimize and support the ICD-coding process.

Lipoprotein(a) and Major Adverse Cardiovascular Events in Patients With or Without Baseline Atherosclerotic Cardiovascular Disease

BACKGROUND

Lipoprotein(a) [Lp(a)] is associated with an increased risk of atherosclerotic cardiovascular disease (ASCVD). However, whether the optimal Lp(a) threshold for risk assessment should differ based on baseline ASCVD status is unknown.

OBJECTIVES

The purpose of this study was to assess the association between Lp(a) and major adverse cardiovascular events (MACE) among patients with and without baseline ASCVD.

METHODS

We studied a retrospective cohort of patients with Lp(a) measured at 2 medical centers in Boston, Massachusetts, from 2000 to 2019. To assess the association of Lp(a) with incident MACE (nonfatal myocardial infarction [MI], nonfatal stroke, coronary revascularization, or cardiovascular mortality), Lp(a) percentile groups were generated with the reference group set at the first to 50th Lp(a) percentiles. Cox proportional hazards modeling was used to assess the association of Lp(a) percentile group with MACE.

RESULTS

Overall, 16,419 individuals were analyzed with a median follow-up of 11.9 years. Among the 10,181 (62%) patients with baseline ASCVD, individuals in the 71st to 90th percentile group had a 21% increased hazard of MACE (adjusted HR: 1.21; P < 0.001), which was similar to that of individuals in the 91st to 100th group (adjusted HR: 1.26; P < 0.001). Among the 6,238 individuals without established ASCVD, there was a continuously higher hazard of MACE with increasing Lp(a), and individuals in the 91st to 100th Lp(a) percentile group had the highest relative risk with an adjusted HR of 1.93 (P < 0.001).

CONCLUSIONS

In a large, contemporary U.S. cohort, elevated Lp(a) is independently associated with long-term MACE among individuals with and without baseline ASCVD. Our results suggest that the threshold for risk assessment may be different in primary vs secondary prevention cohorts.

Applications of the Natural Language Processing Tool ChatGPT in Clinical Practice: Comparative Study and Augmented Systematic Review

BACKGROUND

This research integrates a comparative analysis of the performance of human researchers and OpenAI's ChatGPT in systematic review tasks and describes an assessment of the application of natural language processing (NLP) models in clinical practice through a review of 5 studies.

OBJECTIVE

This study aimed to evaluate the reliability between ChatGPT and human researchers in extracting key information from clinical articles, and to investigate the practical use of NLP in clinical settings as evidenced by selected studies.

METHODS

The study design comprised a systematic review of clinical articles executed independently by human researchers and ChatGPT. The level of agreement between and within raters for parameter extraction was assessed using the Fleiss and Cohen κ statistics.

RESULTS

The comparative analysis revealed a high degree of concordance between ChatGPT and human researchers for most parameters, with less agreement for study design, clinical task, and clinical implementation. The review identified 5 significant studies that demonstrated the diverse applications of NLP in clinical settings. These studies' findings highlight the potential of NLP to improve clinical efficiency and patient outcomes in various contexts, from enhancing allergy detection and classification to improving quality metrics in psychotherapy treatments for veterans with posttraumatic stress disorder.

CONCLUSIONS

Our findings underscore the potential of NLP models, including ChatGPT, in performing systematic reviews and other clinical tasks. Despite certain limitations, NLP models present a promising avenue for enhancing health care efficiency and accuracy. Future studies must focus on broadening the range of clinical applications and exploring the ethical considerations of implementing NLP applications in health care settings.

Natural Language Processing for the Ascertainment and Phenotyping of Left Ventricular Hypertrophy and Hypertrophic Cardiomyopathy on Echocardiogram Reports

Extracting and accurately phenotyping electronic health documentation is critical for medical research and clinical care. We sought to develop a highly accurate and open-source natural language processing (NLP) module to ascertain and phenotype left ventricular hypertrophy (LVH) and hypertrophic cardiomyopathy (HCM) diagnoses from echocardiogram reports within a diverse hospital network. After the initial development on 17,250 echocardiogram reports, 700 unique reports from 6 hospitals were randomly selected from data repositories within the Mass General Brigham healthcare system and manually adjudicated by physicians for 10 subtypes of LVH and diagnoses of HCM. Using an open-source NLP system, the module was formally tested on 300 training set reports and validated on 400 reports. The sensitivity, specificity, positive predictive value, and negative predictive value were calculated to assess the discriminative accuracy of the NLP module. The NLP demonstrated robust performance across the 10 LVH subtypes, with the overall sensitivity and specificity exceeding 96%. In addition, the NLP module demonstrated excellent performance in detecting HCM diagnoses, with sensitivity and specificity exceeding 93%. In conclusion, we designed a highly accurate NLP module to determine the presence of LVH and HCM on echocardiogram reports. Our work demonstrates the feasibility and accuracy of NLP to detect diagnoses on imaging reports, even when described in free text. This module has been placed in the public domain to advance research, trial recruitment, and population health management for patients with LVH-associated conditions.

A pragmatic clinical trial assessing the effect of a targeted notification and clinical support pathway on the diagnostic evaluation and treatment of individuals with left ventricular hypertrophy (NOTIFY-LVH)

BACKGROUND

Electronic health records contain vast amounts of cardiovascular data, including potential clues suggesting unrecognized conditions. One important example is the identification of left ventricular hypertrophy (LVH) on echocardiography. If the underlying causes are untreated, individuals are at increased risk of developing clinically significant pathology. As the most common cause of LVH, hypertension accounts for more cardiovascular deaths than any other modifiable risk factor. Contemporary healthcare systems have suboptimal mechanisms for detecting and effectively implementing hypertension treatment before downstream consequences develop. Thus, there is an urgent need to validate alternative intervention strategies for individuals with preexisting-but potentially unrecognized-LVH.

METHODS

Through a randomized pragmatic trial within a large integrated healthcare system, we will study the impact of a centralized clinical support pathway on the diagnosis and treatment of hypertension and other LVH-associated diseases in individuals with echocardiographic evidence of concentric LVH. Approximately 600 individuals who are not treated for hypertension and who do not have a known cardiomyopathy will be randomized. The intervention will be directed by population health coordinators who will notify longitudinal clinicians and offer to assist with the diagnostic evaluation of LVH. Our hypothesis is that an intervention that alerts clinicians to the presence of LVH will increase the detection and treatment of hypertension and the diagnosis of alternative causes of thickened myocardium. The primary outcome is the initiation of an antihypertensive medication. Secondary outcomes include new hypertension diagnoses and new cardiomyopathy diagnoses. The trial began in March 2023 and outcomes will be assessed 12 months from the start of follow-up.

CONCLUSION

The NOTIFY-LVH trial will assess the efficacy of a centralized intervention to improve the detection and treatment of hypertension and LVH-associated diseases. Additionally, it will serve as a proof-of-concept for how to effectively utilize previously collected electronic health data to improve the recognition and management of a broad range of chronic cardiovascular conditions.

TRIAL REGISTRATION

NCT05713916.

Survey on natural language processing in medical image analysis

Recent advancement in natural language processing (NLP) and medical imaging empowers the wide applicability of deep learning models. These developments have increased not only data understanding, but also knowledge of state-of-the-art architectures and their real-world potentials. Medical imaging researchers have recognized the limitations of only targeting images, as well as the importance of integrating multimodal inputs into medical image analysis. The lack of comprehensive surveys of the current literature, however, impedes the progress of this domain. Existing research perspectives, as well as the architectures, tasks, datasets, and performance measures examined in the present literature, are reviewed in this work, and we also provide a brief description of possible future directions in the field, aiming to provide researchers and healthcare professionals with a detailed summary of existing academic research and to provide rational insights to facilitate future research.