Psychiatric symptom recognition without labeled data using distributional representations of phrases and on-line knowledge

The interaction network and potential clinical effectiveness of dimensional psychopathology phenotyping based on EMR: a Bayesian network approach

The current DSM-oriented diagnostic paradigm has introduced the issue of heterogeneity, as it fails to account for the identification of the neurological processes underlying mental illnesses, which affects the precision of treatment. The Research Domain Criteria (RDoC) framework serves as a recognized approach to addressing this heterogeneity, and several assessment and translation techniques have been proposed. Among these methods, transforming RDoC scores from electronic medical records (EMR) using Natural Language Processing (NLP) has emerged as a suitable technique, demonstrating clinical effectiveness. Numerous studies have sought to use RDoC to understand the Diagnostic and Statistical Manual of Mental Disorders (DSM) categories from a qualified perspective, but few studies have examined the distribution variations and interaction characteristics of RDoC within various DSM categories through retrospective analyses. Therefore, we employed unsupervised learning to translate five domains of eRDoC scores derived from electronic medical records (EMR) of patients diagnosed with Major Depressive Disorder (MDD), Schizophrenia (SCZ), and Bipolar Disorder (BD) at West China Hospital between 2008 and 2021. The distribution characteristics, interaction networks, and potential clinical effectiveness of RDoC domains were analyzed. Using non-parametric statistical tests, we found that MDD had the highest score in Negative Valence System (NVS) (4.1, p < 0.001), while BD exhibited the highest score in Positive Valence System (PVS) score (4.9, p < 0.001) and Arousal System (AS) (4.4, p < 0.001). SCZ demonstrated the highest scores in Cognitive Systems (CS) (5.8, p < 0.001) and Social Processes Systems (SPS) (4.6, p < 0.001). Through Bayesian network (BN) analysis, we identified relatively consistent interaction relationships among various RDoC domains (NVS → AS, NVS → CS, NVS → PVS, as well as CS → SPS; parameter range = 0.156 to 0.635, p < 0.001). Lastly, using logistic regression and Cox proportional hazards models, we demonstrated that AS was significantly associated with the length of hospital stay (-0.21, p < 0.05) and 30-day readmission risk (adjusted odds ratio [aOR] = 0.91, 95% confidence interval [CI] 0.91-0.99) to some extent. In conclusion, we suggest that the eRDoC characteristics varied in different DSM. By Bayesian Network, we found NVS and CS might be potential source in interacting with other system. Furthermore, CS, SPS and AS were associated with the length of stay and 30-days readmission, making them effective for predicting prognosis of psychiatric disorders.

Digital systems for improving outcomes in patients with primary immune defects

PURPOSE OF REVIEW

Healthcare has already been impacted by the fourth industrial revolution exemplified by tip of spear technology, such as artificial intelligence and quantum computing. Yet, there is much to be accomplished as systems remain suboptimal, and full interoperability of digital records is not realized. Given the footprint of technology in healthcare, the field of clinical immunology will certainly see improvements related to these tools.

RECENT FINDINGS

Biomedical informatics spans the gamut of technology in biomedicine. Within this distinct field, advances are being made, which allow for engineering of systems to automate disease detection, create computable phenotypes and improve record portability. Within clinical immunology, technologies are emerging along these lines and are expected to continue.

SUMMARY

This review highlights advancements in digital health including learning health systems, electronic phenotyping, artificial intelligence and use of registries. Technological advancements for improving diagnosis and care of patients with primary immunodeficiency diseases is also highlighted.

Mental Health Severity Detection from Psychological Forum Data using Domain-Specific Unlabelled Data

Mental health has become a growing concern in the medical field, yet remains difficult to study due to both privacy concerns and the lack of objectively quantifiable measurements (e.g., lab tests, physical exams). Instead, the data that is available for mental health is largely based on subjective accounts of a patient's experience, and thus typically is expressed exclusively in text. An important source of such data comes from online sources and directly from the patient, including many forms of social media. In this work, we utilize the datasets provided by the CLPsych shared tasks in 2016 and 2017, derived from online forum posts of ReachOut which have been manually classified according to mental health severity. We implemented an automated severity labeling system using different machine and deep learning algorithms. Our approach combines both supervised and semi-supervised embedding methods using corpus from ReachOut (both labeled and unlabelled) and WebMD (unlabelled). Metadata, syntactic, semantic, and embedding features were used to classify the posts into four categories (green, amber, red, and crisis). The developed systems outperformed other state-of-the-art systems developed on the ReachOut dataset and obtained the maximum micro- averaged F-scores of 0.86 and 0.80 for CLPsych 2016 and 2017 test datasets, respectively, using the above features.

Precursor-induced conditional random fields: connecting separate entities by induction for improved clinical named entity recognition

BACKGROUND

This paper presents a conditional random fields (CRF) method that enables the capture of specific high-order label transition factors to improve clinical named entity recognition performance. Consecutive clinical entities in a sentence are usually separated from each other, and the textual descriptions in clinical narrative documents frequently indicate causal or posterior relationships that can be used to facilitate clinical named entity recognition. However, the CRF that is generally used for named entity recognition is a first-order model that constrains label transition dependency of adjoining labels under the Markov assumption.

METHODS

Based on the first-order structure, our proposed model utilizes non-entity tokens between separated entities as an information transmission medium by applying a label induction method. The model is referred to as precursor-induced CRF because its non-entity state memorizes precursor entity information, and the model's structure allows the precursor entity information to propagate forward through the label sequence.

RESULTS

We compared the proposed model with both first- and second-order CRFs in terms of their F₁-scores, using two clinical named entity recognition corpora (the i2b2 2012 challenge and the Seoul National University Hospital electronic health record). The proposed model demonstrated better entity recognition performance than both the first- and second-order CRFs and was also more efficient than the higher-order model.

CONCLUSION

The proposed precursor-induced CRF which uses non-entity labels as label transition information improves entity recognition F₁ score by exploiting long-distance transition factors without exponentially increasing the computational time. In contrast, a conventional second-order CRF model that uses longer distance transition factors showed even worse results than the first-order model and required the longest computation time. Thus, the proposed model could offer a considerable performance improvement over current clinical named entity recognition methods based on the CRF models.

Psychiatric stressor recognition from clinical notes to reveal association with suicide

Suicide takes the lives of nearly a million people each year and it is a tremendous economic burden globally. One important type of suicide risk factor is psychiatric stress. Prior studies mainly use survey data to investigate the association between suicide and stressors. Very few studies have investigated stressor data in electronic health records, mostly due to the data being recorded in narrative text. This study takes the initiative to automatically extract and classify psychiatric stressors from clinical text using natural language processing-based methods. Suicidal behaviors were also identified by keywords. Then, a statistical association analysis between suicide ideations/attempts and stressors extracted from a clinical corpus is conducted. Experimental results show that our natural language processing method could recognize stressor entities with an F-measure of 89.01 percent. Mentions of suicidal behaviors were identified with an F-measure of 97.3 percent. The top three significant stressors associated with suicide are health, pressure, and death, which are similar to previous studies. This study demonstrates the feasibility of using natural language processing approaches to unlock information from psychiatric notes in electronic health record, to facilitate large-scale studies about associations between suicide and psychiatric stressors.

Extracting psychiatric stressors for suicide from social media using deep learning

BACKGROUND

Suicide has been one of the leading causes of deaths in the United States. One major cause of suicide is psychiatric stressors. The detection of psychiatric stressors in an at risk population will facilitate the early prevention of suicidal behaviors and suicide. In recent years, the widespread popularity and real-time information sharing flow of social media allow potential early intervention in a large-scale population. However, few automated approaches have been proposed to extract psychiatric stressors from Twitter. The goal of this study was to investigate techniques for recognizing suicide related psychiatric stressors from Twitter using deep learning based methods and transfer learning strategy which leverages an existing annotation dataset from clinical text.

METHODS

First, a dataset of suicide-related tweets was collected from Twitter streaming data with a multiple-step pipeline including keyword-based retrieving, filtering and further refining using an automated binary classifier. Specifically, a convolutional neural networks (CNN) based algorithm was used to build the binary classifier. Next, psychiatric stressors were annotated in the suicide-related tweets. The stressor recognition problem is conceptualized as a typical named entity recognition (NER) task and tackled using recurrent neural networks (RNN) based methods. Moreover, to reduce the annotation cost and improve the performance, transfer learning strategy was adopted by leveraging existing annotation from clinical text.

RESULTS & CONCLUSIONS

To our best knowledge, this is the first effort to extract psychiatric stressors from Twitter data using deep learning based approaches. Comparison to traditional machine learning algorithms shows the superiority of deep learning based approaches. CNN is leading the performance at identifying suicide-related tweets with a precision of 78% and an F-1 measure of 83%, outperforming Support Vector Machine (SVM), Extra Trees (ET), etc. RNN based psychiatric stressors recognition obtains the best F-1 measure of 53.25% by exact match and 67.94% by inexact match, outperforming Conditional Random Fields (CRF). Moreover, transfer learning from clinical notes for the Twitter corpus outperforms the training with Twitter corpus only with an F-1 measure of 54.9% by exact match. The results indicate the advantages of deep learning based methods for the automated stressors recognition from social media.

Adapting Word Embeddings from Multiple Domains to Symptom Recognition from Psychiatric Notes

Mental health is increasingly recognized an important topic in healthcare. Information concerning psychiatric symptoms is critical for the timely diagnosis of mental disorders, as well as for the personalization of interventions. However, the diversity and sparsity of psychiatric symptoms make it challenging for conventional natural language processing techniques to automatically extract such information from clinical text. To address this problem, this study takes the initiative to use and adapt word embeddings from four source domains - intensive care, biomedical literature, Wikipedia and Psychiatric Forum - to recognize symptoms in the target domain of psychiatry. We investigated four different approaches including 1) only using word embeddings of the source domain, 2) directly combining data of the source and target to generate word embeddings, 3) assigning different weights to word embeddings, and 4) retraining the word embedding model of the source domain using a corpus of the target domain. To the best of our knowledge, this is the first work of adapting multiple word embeddings of external domains to improve psychiatric symptom recognition in clinical text. Experimental results showed that the last two approaches outperformed the baseline methods, indicating the effectiveness of our new strategies to leverage embeddings from other domains.

Development of an automated phenotyping algorithm for hepatorenal syndrome

OBJECTIVE

Hepatorenal Syndrome (HRS) is a devastating form of acute kidney injury (AKI) in advanced liver disease patients with high morbidity and mortality, but phenotyping algorithms have not yet been developed using large electronic health record (EHR) databases. We evaluated and compared multiple phenotyping methods to achieve an accurate algorithm for HRS identification.

MATERIALS AND METHODS

A national retrospective cohort of patients with cirrhosis and AKI admitted to 124 Veterans Affairs hospitals was assembled from electronic health record data collected from 2005 to 2013. AKI was defined by the Kidney Disease: Improving Global Outcomes criteria. Five hundred and four hospitalizations were selected for manual chart review and served as the gold standard. Electronic Health Record based predictors were identified using structured and free text clinical data, subjected through NLP from the clinical Text Analysis Knowledge Extraction System. We explored several dimension reduction techniques for the NLP data, including newer high-throughput phenotyping and word embedding methods, and ascertained their effectiveness in identifying the phenotype without structured predictor variables. With the combined structured and NLP variables, we analyzed five phenotyping algorithms: penalized logistic regression, naïve Bayes, support vector machines, random forest, and gradient boosting. Calibration and discrimination metrics were calculated using 100 bootstrap iterations. In the final model, we report odds ratios and 95% confidence intervals.

RESULTS

The area under the receiver operating characteristic curve (AUC) for the different models ranged from 0.73 to 0.93; with penalized logistic regression having the best discriminatory performance. Calibration for logistic regression was modest, but gradient boosting and support vector machines were superior. NLP identified 6985 variables; a priori variable selection performed similarly to dimensionality reduction using high-throughput phenotyping and semantic similarity informed clustering (AUC of 0.81 - 0.82).

CONCLUSION

This study demonstrated improved phenotyping of a challenging AKI etiology, HRS, over ICD-9 coding. We also compared performance among multiple approaches to EHR-derived phenotyping, and found similar results between methods. Lastly, we showed that automated NLP dimension reduction is viable for acute illness.