Developing a Natural Language Processing tool to identify perinatal self-harm in electronic healthcare records

Artificial intelligence and natural language processing for improved telemedicine: Before, during and after remote consultation

The rapid evolution of telemedicine has revealed significant documentation and workflow challenges. Clinicians often struggle with the administrative burdens of telehealth visits, sacrificing valuable time better spent in direct patient interaction. This issue is further compounded by the need to maintain accurate and comprehensive records, which can be time-consuming and prone to error when approached manually. In this context, integrating artificial intelligence (AI) and natural language processing (NLP) technologies presents a transformative opportunity. Automating documentation and enhancing workflow efficiency can revolutionize healthcare delivery, alleviating clinician workloads and improving clinical quality and patient safety. Therefore, examining the application of these cutting-edge technologies becomes imperative in addressing the pressing needs of modern healthcare and optimizing health outcomes. The significance of integrating AI and NLP technologies in clinical remote practice cannot be overstated. Hence, this article aims to inspire and motivate healthcare professionals to embrace these transformative changes.

The Future of Artificial Intelligence in Mental Health Nursing Practice: An Integrative Review

Artificial intelligence (AI) has been increasingly used in delivering mental healthcare worldwide. Within this context, the traditional role of mental health nurses has been changed and challenged by AI-powered cutting-edge technologies emerging in clinical practice. The aim of this integrative review is to identify and synthesise the evidence of AI-based applications with relevance for, and potential to enhance, mental health nursing practice. Five electronic databases (CINAHL, PubMed, PsycINFO, Web of Science and Scopus) were systematically searched. Seventy-eight studies were identified, critically appraised and synthesised following a comprehensive integrative approach. We found that AI applications with potential use in mental health nursing vary widely from machine learning algorithms to natural language processing, digital phenotyping, computer vision and conversational agents for assessing, diagnosing and treating mental health challenges. Five overarching themes were identified: assessment, identification, prediction, optimisation and perception reflecting the multiple levels of embedding AI-driven technologies in mental health nursing practice, and how patients and staff perceive the use of AI in clinical settings. We concluded that AI-driven technologies hold great potential for enhancing mental health nursing practice. However, humanistic approaches to mental healthcare may pose some challenges to effectively incorporating AI into mental health nursing. Meaningful conversations between mental health nurses, service users and AI developers should take place to shaping the co-creation of AI technologies to enhance care in a way that promotes person-centredness, empowerment and active participation.

Scalable incident detection via natural language processing and probabilistic language models

Post marketing safety surveillance depends in part on the ability to detect concerning clinical events at scale. Spontaneous reporting might be an effective component of safety surveillance, but it requires awareness and understanding among healthcare professionals to achieve its potential. Reliance on readily available structured data such as diagnostic codes risks under-coding and imprecision. Clinical textual data might bridge these gaps, and natural language processing (NLP) has been shown to aid in scalable phenotyping across healthcare records in multiple clinical domains. In this study, we developed and validated a novel incident phenotyping approach using unstructured clinical textual data agnostic to Electronic Health Record (EHR) and note type. It's based on a published, validated approach (PheRe) used to ascertain social determinants of health and suicidality across entire healthcare records. To demonstrate generalizability, we validated this approach on two separate phenotypes that share common challenges with respect to accurate ascertainment: (1) suicide attempt; (2) sleep-related behaviors. With samples of 89,428 records and 35,863 records for suicide attempt and sleep-related behaviors, respectively, we conducted silver standard (diagnostic coding) and gold standard (manual chart review) validation. We showed Area Under the Precision-Recall Curve of ~ 0.77 (95% CI 0.75-0.78) for suicide attempt and AUPR ~ 0.31 (95% CI 0.28-0.34) for sleep-related behaviors. We also evaluated performance by coded race and demonstrated differences in performance by race differed across phenotypes. Scalable phenotyping models, like most healthcare AI, require algorithmovigilance and debiasing prior to implementation.

Artificial intelligence in perinatal mental health research: A scoping review

The intersection of Artificial Intelligence (AI) and perinatal mental health research presents promising avenues, yet uncovers significant challenges for innovation. This review explicitly focuses on this multidisciplinary field and undertakes a comprehensive exploration of existing research therein. Through a scoping review guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, we searched relevant literature spanning a decade (2013-2023) and selected fourteen studies for our analysis. We first provide an overview of the main AI techniques and their development, including traditional methods across different categories, as well as recent emerging methods in the field. Then, through our analysis of the literature, we summarize the predominant AI and ML techniques adopted and their applications in perinatal mental health studies, such as identifying risk factors, predicting perinatal mental health disorders, voice assistants, and Q&A chatbots. We also discuss existing limitations and potential challenges that hinder AI technologies from improving perinatal mental health outcomes, and suggest several promising directions for future research to meet real needs in the field and facilitate the translation of research into clinical settings.

Classifying early infant feeding status from clinical notes using natural language processing and machine learning

The objective of this study is to develop and evaluate natural language processing (NLP) and machine learning models to predict infant feeding status from clinical notes in the Epic electronic health records system. The primary outcome was the classification of infant feeding status from clinical notes using Medical Subject Headings (MeSH) terms. Annotation of notes was completed using TeamTat to uniquely classify clinical notes according to infant feeding status. We trained 6 machine learning models to classify infant feeding status: logistic regression, random forest, XGBoost gradient descent, k-nearest neighbors, and support-vector classifier. Model comparison was evaluated based on overall accuracy, precision, recall, and F1 score. Our modeling corpus included an even number of clinical notes that was a balanced sample across each class. We manually reviewed 999 notes that represented 746 mother-infant dyads with a mean gestational age of 38.9 weeks and a mean maternal age of 26.6 years. The most frequent feeding status classification present for this study was exclusive breastfeeding [n = 183 (18.3%)], followed by exclusive formula bottle feeding [n = 146 (14.6%)], and exclusive feeding of expressed mother's milk [n = 102 (10.2%)], with mixed feeding being the least frequent [n = 23 (2.3%)]. Our final analysis evaluated the classification of clinical notes as breast, formula/bottle, and missing. The machine learning models were trained on these three classes after performing balancing and down sampling. The XGBoost model outperformed all others by achieving an accuracy of 90.1%, a macro-averaged precision of 90.3%, a macro-averaged recall of 90.1%, and a macro-averaged F1 score of 90.1%. Our results demonstrate that natural language processing can be applied to clinical notes stored in the electronic health records to classify infant feeding status. Early identification of breastfeeding status using NLP on unstructured electronic health records data can be used to inform precision public health interventions focused on improving lactation support for postpartum patients.

Scalable Incident Detection via Natural Language Processing and Probabilistic Language Models

Post marketing safety surveillance depends in part on the ability to detect concerning clinical events at scale. Spontaneous reporting might be an effective component of safety surveillance, but it requires awareness and understanding among healthcare professionals to achieve its potential. Reliance on readily available structured data such as diagnostic codes risk under-coding and imprecision. Clinical textual data might bridge these gaps, and natural language processing (NLP) has been shown to aid in scalable phenotyping across healthcare records in multiple clinical domains. In this study, we developed and validated a novel incident phenotyping approach using unstructured clinical textual data agnostic to Electronic Health Record (EHR) and note type. It's based on a published, validated approach (PheRe) used to ascertain social determinants of health and suicidality across entire healthcare records. To demonstrate generalizability, we validated this approach on two separate phenotypes that share common challenges with respect to accurate ascertainment: 1) suicide attempt; 2) sleep-related behaviors. With samples of 89,428 records and 35,863 records for suicide attempt and sleep-related behaviors, respectively, we conducted silver standard (diagnostic coding) and gold standard (manual chart review) validation. We showed Area Under the Precision-Recall Curve of ∼ 0.77 (95% CI 0.75-0.78) for suicide attempt and AUPR ∼ 0.31 (95% CI 0.28-0.34) for sleep-related behaviors. We also evaluated performance by coded race and demonstrated differences in performance by race were dissimilar across phenotypes and require algorithmovigilance and debiasing prior to implementation.

Natural Language Processing in Electronic Health Records in relation to healthcare decision-making: A systematic review

BACKGROUND

Natural Language Processing (NLP) is widely used to extract clinical insights from Electronic Health Records (EHRs). However, the lack of annotated data, automated tools, and other challenges hinder the full utilisation of NLP for EHRs. Various Machine Learning (ML), Deep Learning (DL) and NLP techniques are studied and compared to understand the limitations and opportunities in this space comprehensively.

METHODOLOGY

After screening 261 articles from 11 databases, we included 127 papers for full-text review covering seven categories of articles: (1) medical note classification, (2) clinical entity recognition, (3) text summarisation, (4) deep learning (DL) and transfer learning architecture, (5) information extraction, (6) Medical language translation and (7) other NLP applications. This study follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.

RESULT AND DISCUSSION

EHR was the most commonly used data type among the selected articles, and the datasets were primarily unstructured. Various ML and DL methods were used, with prediction or classification being the most common application of ML or DL. The most common use cases were: the International Classification of Diseases, Ninth Revision (ICD-9) classification, clinical note analysis, and named entity recognition (NER) for clinical descriptions and research on psychiatric disorders.

CONCLUSION

We find that the adopted ML models were not adequately assessed. In addition, the data imbalance problem is quite important, yet we must find techniques to address this underlining problem. Future studies should address key limitations in studies, primarily identifying Lupus Nephritis, Suicide Attempts, perinatal self-harmed and ICD-9 classification.

Hospitalisation for non-lethal self-harm and premature mortality in the 3 years following adolescent pregnancy: Population-based nationwide cohort study

OBJECTIVE

To evaluate the risk of non-lethal self-harm and mortality related to adolescent pregnancy.

DESIGN

Nationwide population-based retrospective cohort.

SETTING

Data were extracted from the French national health data system.

POPULATION

We included all adolescents aged 12-18 years with an International Statistical Classification of Diseases and Related Health Problems, 10th Revision (ICD-10) code for pregnancy in 2013-2014.

METHODS

Pregnant adolescents were compared with age-matched non-pregnant adolescents and with first-time pregnant women aged 19-25 years.

MAIN OUTCOME MEASURES

Any hospitalisation for non-lethal self-harm and mortality during a 3-year follow-up period. Adjustment variables were age, a history of hospitalisation for physical diseases, psychiatric disorders, self-harm and reimbursed psychotropic drugs. Cox proportional hazards regression models were used.

RESULTS

In 2013-2014, 35 449 adolescent pregnancies were recorded in France. After adjustment, pregnant adolescents had an increased risk of subsequent hospitalisation for non-lethal self-harm in comparison with both non-pregnant adolescents (n = 70 898) (1.3% vs 0.2%, HR 3.06, 95% CI 2.57-3.66) and pregnant young women (n = 233 406) (0.5%, HR 2.41, 95% CI 2.14-2.71). Rates of hospitalisation for non-lethal self-harm were lower during pregnancy and higher between 12 and 8 months pre-delivery, 3-7 months postpartum and in the month following abortion. Mortality was significantly higher in pregnant adolescents (0.7‰) versus pregnant young women (0.4‰, HR 1.74, 95% CI 1.12-2.72), but not versus non-pregnant adolescents (0.4‰, HR 1.61, 95% CI 0.92-2.83).

CONCLUSIONS

Adolescent pregnancy is associated with an increased risk of hospitalisation for non-lethal self-harm and premature death. Careful psychological evaluation and support should be systematically implemented for adolescents who are pregnant.

Application of Natural Language Processing (NLP) in Detecting and Preventing Suicide Ideation: A Systematic Review

(1) Introduction: Around a million people are reported to die by suicide every year, and due to the stigma associated with the nature of the death, this figure is usually assumed to be an underestimate. Machine learning and artificial intelligence such as natural language processing has the potential to become a major technique for the detection, diagnosis, and treatment of people. (2) Methods: PubMed, EMBASE, MEDLINE, PsycInfo, and Global Health databases were searched for studies that reported use of NLP for suicide ideation or self-harm. (3) Result: The preliminary search of 5 databases generated 387 results. Removal of duplicates resulted in 158 potentially suitable studies. Twenty papers were finally included in this review. (4) Discussion: Studies show that combining structured and unstructured data in NLP data modelling yielded more accurate results than utilizing either alone. Additionally, to reduce suicides, people with mental problems must be continuously and passively monitored. (5) Conclusions: The use of AI&ML opens new avenues for considerably guiding risk prediction and advancing suicide prevention frameworks. The review's analysis of the included research revealed that the use of NLP may result in low-cost and effective alternatives to existing resource-intensive methods of suicide prevention.

Using natural language processing to extract self-harm and suicidality data from a clinical sample of patients with eating disorders: a retrospective cohort study

OBJECTIVES

The objective of this study was to determine risk factors for those diagnosed with eating disorders who report self-harm and suicidality.

DESIGN AND SETTING

This study was a retrospective cohort study within a secondary mental health service, South London and Maudsley National Health Service Trust.

PARTICIPANTS

All diagnosed with an F50 diagnosis of eating disorder from January 2009 to September 2019 were included.

INTERVENTION AND MEASURES

Electronic health records (EHRs) for these patients were extracted and two natural language processing tools were used to determine documentation of self-harm and suicidality in their clinical notes. These tools were validated manually for attribute agreement scores within this study.

RESULTS

The attribute agreements for precision of positive mentions of self-harm were 0.96 and for suicidality were 0.80; this demonstrates a 'near perfect' and 'strong' agreement and highlights the reliability of the tools in identifying the EHRs reporting self-harm or suicidality. There were 7434 patients with EHRs available and diagnosed with eating disorders included in the study from the dates January 2007 to September 2019. Of these, 4591 (61.8%) had a mention of self-harm within their records and 4764 (64.0%) had a mention of suicidality; 3899 (52.4%) had mentions of both. Patients reporting either self-harm or suicidality were more likely to have a diagnosis of anorexia nervosa (AN) (self-harm, AN OR=3.44, 95% CI 1.05 to 11.3, p=0.04; suicidality, AN OR=8.20, 95% CI 2.17 to 30.1; p=0.002). They were also more likely to have a diagnosis of borderline personality disorder (p≤0.001), bipolar disorder (p<0.001) or substance misuse disorder (p<0.001).

CONCLUSION

A high percentage of patients (>60%) diagnosed with eating disorders report either self-harm or suicidal thoughts. Relative to other eating disorders, those diagnosed with AN were more likely to report either self-harm or suicidal thoughts. Psychiatric comorbidity, in particular borderline personality disorder and substance misuse, was also associated with an increase risk in self-harm and suicidality. Therefore, risk assessment among patients diagnosed with eating disorders is crucial.