Exploring the Documentation of Delirium in Patients After Cardiac Surgery: A Retrospective Patient Record Study.

Delirium is a common disorder for patients after cardiac surgery. Its manifestation and care can be examined through EHRs. The aim of this retrospective, comparative, and descriptive patient record study was to describe the documentation of delirium symptoms in the EHRs of patients who have undergone cardiac surgery and to explore how the documentation evolved between two periods (2005-2009 and 2015-2020). Randomly selected care episodes were annotated with a template, including delirium symptoms, treatment methods, and adverse events. The patients were then manually classified into two groups: nondelirious (n = 257) and possibly delirious (n = 172). The data were analyzed quantitatively and descriptively. According to the data, the documentation of symptoms such as disorientation, memory problems, motoric behavior, and disorganized thinking improved between periods. Yet, the key symptoms of delirium, inattention, and awareness were seldom documented. The professionals did not systematically document the possibility of delirium. Particularly, the way nurses recorded structural information did not facilitate an overall understanding of a patient's condition with respect to delirium. Information about delirium or proposed care was seldom documented in the discharge summaries. Advanced machine learning techniques can augment instruments that facilitate early detection, care planning, and transferring information to follow-up care.

Using Natural Language Processing to Identify Stigmatizing Language in Labor and Birth Clinical Notes.

INTRODUCTION: Stigma and bias related to race and other minoritized statuses may underlie disparities in pregnancy and birth outcomes. One emerging method to identify bias is the study of stigmatizing language in the electronic health record. The objective of our study was to develop automated natural language processing (NLP) methods to identify two types of stigmatizing language: marginalizing language and its complement, power/privilege language, accurately and automatically in labor and birth notes. METHODS: We analyzed notes for all birthing people > 20 weeks' gestation admitted for labor and birth at two hospitals during 2017. We then employed text preprocessing techniques, specifically using TF-IDF values as inputs, and tested machine learning classification algorithms to identify stigmatizing and power/privilege language in clinical notes. The algorithms assessed included Decision Trees, Random Forest, and Support Vector Machines. Additionally, we applied a feature importance evaluation method (InfoGain) to discern words that are highly correlated with these language categories. RESULTS: For marginalizing language, Decision Trees yielded the best classification with an F-score of 0.73. For power/privilege language, Support Vector Machines performed optimally, achieving an F-score of 0.91. These results demonstrate the effectiveness of the selected machine learning methods in classifying language categories in clinical notes. CONCLUSION: We identified well-performing machine learning methods to automatically detect stigmatizing language in clinical notes. To our knowledge, this is the first study to use NLP performance metrics to evaluate the performance of machine learning methods in discerning stigmatizing language. Future studies should delve deeper into refining and evaluating NLP methods, incorporating the latest algorithms rooted in deep learning.

A risk identification model for detection of patients at risk of antidepressant discontinuation.

Purpose: Between 30 and 68% of patients prematurely discontinue their antidepressant treatment, posing significant risks to patient safety and healthcare outcomes. Online healthcare forums have the potential to offer a rich and unique source of data, revealing dimensions of antidepressant discontinuation that may not be captured by conventional data sources. Methods: We analyzed 891 patient narratives from the online healthcare forum, "askapatient.com," utilizing content analysis to create PsyRisk-a corpus highlighting the risk factors associated with antidepressant discontinuation. Leveraging PsyRisk, alongside PsyTAR [a publicly available corpus of adverse drug reactions (ADRs) related to antidepressants], we developed a machine learning-driven algorithm for proactive identification of patients at risk of abrupt antidepressant discontinuation. Results: From the analyzed 891 patients, 232 reported antidepressant discontinuation. Among these patients, 92% experienced ADRs, and 72% found these reactions distressful, negatively affecting their daily activities. Approximately 26% of patients perceived the antidepressants as ineffective. Most reported ADRs were physiological (61%, 411/673), followed by cognitive (30%, 197/673), and psychological (28%, 188/673) ADRs. In our study, we employed a nested cross-validation strategy with an outer 5-fold cross-validation for model selection, and an inner 5-fold cross-validation for hyperparameter tuning. The performance of our risk identification algorithm, as assessed through this robust validation technique, yielded an AUC-ROC of 90.77 and an F1-score of 83.33. The most significant contributors to abrupt discontinuation were high perceived distress from ADRs and perceived ineffectiveness of the antidepressants. Conclusion: The risk factors identified and the risk identification algorithm developed in this study have substantial potential for clinical application. They could assist healthcare professionals in identifying and managing patients with depression who are at risk of prematurely discontinuing their antidepressant treatment.

Electronic Health Records as Information Source in Assessment of the Effectiveness of Delivered Care - A Pilot Study.

Effectiveness is a key element of high quality health services. The aim of this pilot study was to explore the potential of electronic health records (EHR) as an information source for assessing the effectiveness of nursing care by investigating the appearance of nursing processes in the documentation of care. Deductive and inductive content analysis were used in a manual annotation of ten patients' EHRs. The analysis resulted in the identification of 229 documented nursing processes. The results indicate that EHRs can be used in decision support systems for assessing effectiveness of nursing care, however, future work is needed to verify these findings in a larger data set and extend to other dimensions related to care quality.

A qualitative analysis of stigmatizing language in birth admission clinical notes.

The presence of stigmatizing language in the electronic health record (EHR) has been used to measure implicit biases that underlie health inequities. The purpose of this study was to identify the presence of stigmatizing language in the clinical notes of pregnant people during the birth admission. We conducted a qualitative analysis on N = 1117 birth admission EHR notes from two urban hospitals in 2017. We identified stigmatizing language categories, such as Disapproval (39.3%), Questioning patient credibility (37.7%), Difficult patient (21.3%), Stereotyping (1.6%), and Unilateral decisions (1.6%) in 61 notes (5.4%). We also defined a new stigmatizing language category indicating Power/privilege. This was present in 37 notes (3.3%) and signaled approval of social status, upholding a hierarchy of bias. The stigmatizing language was most frequently identified in birth admission triage notes (16%) and least frequently in social work initial assessments (13.7%). We found that clinicians from various disciplines recorded stigmatizing language in the medical records of birthing people. This language was used to question birthing people's credibility and convey disapproval of decision-making abilities for themselves or their newborns. We reported a Power/privilege language bias in the inconsistent documentation of traits considered favorable for patient outcomes (e.g., employment status). Future work on stigmatizing language may inform tailored interventions to improve perinatal outcomes for all birthing people and their families.

Identifying nursing sensitive indicators from electronic health records in acute cardiac care-Towards intelligent automated assessment of care quality.

AIM: The aim of this study is to explore the potential of using electronic health records for assessment of nursing care quality through nursing-sensitive indicators in acute cardiac care. BACKGROUND: Nursing care quality is a multifaceted phenomenon, making a holistic assessment of it difficult. Quality assessment systems in acute cardiac care units could benefit from big data-based solutions that automatically extract and help interpret data from electronic health records. METHODS: This is a deductive descriptive study that followed the theory of value-added analysis. A random sample from electronic health records of 230 patients was analysed for selected indicators. The data included documentation in structured and free-text format. RESULTS: One thousand six hundred seventy-six expressions were extracted and divided into (1) established and (2) unestablished expressions, providing positive, neutral and negative descriptions related to care quality. CONCLUSIONS: Electronic health records provide a potential source of information for information systems to support assessment of care quality. More research is warranted to develop, test and evaluate the effectiveness of such tools in practice. IMPLICATIONS FOR NURSING MANAGEMENT: Knowledge-based health care management would benefit from the development and implementation of advanced information systems, which use continuously generated already available real-time big data for improved data access and interpretation to better support nursing management in quality assessment.

Text Classification Model Explainability for Keyword Extraction - Towards Keyword-Based Summarization of Nursing Care Episodes.

Tools to automate the summarization of nursing entries in electronic health records (EHR) have the potential to support healthcare professionals to obtain a rapid overview of a patient's situation when time is limited. This study explores a keyword-based text summarization method for the nursing text that is based on machine learning model explainability for text classification models. This study aims to extract keywords and phrases that provide an intuitive overview of the content in multiple nursing entries in EHRs written during individual patients' care episodes. The proposed keyword extraction method is used to generate keyword summaries from 40 patients' care episodes and its performance is compared to a baseline method based on word embeddings combined with the PageRank method. The two methods were assessed with manual evaluation by three domain experts. The results indicate that it is possible to generate representative keyword summaries from nursing entries in EHRs and our method outperformed the baseline method.

Towards Automated Screening of Literature on Artificial Intelligence in Nursing.

We evaluate the performance of multiple text classification methods used to automate the screening of article abstracts in terms of their relevance to a topic of interest. The aim is to develop a system that can be first trained on a set of manually screened article abstracts before using it to identify additional articles on the same topic. Here the focus is on articles related to the topic "artificial intelligence in nursing". Eight text classification methods are tested, as well as two simple ensemble systems. The results indicate that it is feasible to use text classification technology to support the manual screening process of article abstracts when conducting a literature review. The best results are achieved by an ensemble system, which achieves a F1-score of 0.41, with a sensitivity of 0.54 and a specificity of 0.96. Future work directions are discussed.

Using machine learning to predict subsequent events after EMS non-conveyance decisions.

BACKGROUND: Predictors of subsequent events after Emergency Medical Services (EMS) non-conveyance decisions are still unclear, though patient safety is the priority in prehospital emergency care. The aim of this study was to find out whether machine learning can be used in this context and to identify the predictors of subsequent events based on narrative texts of electronic patient care records (ePCR). METHODS: This was a prospective cohort study of EMS patients in Finland. The data was collected from three different regions between June 1 and November 30, 2018. Machine learning, in form of text classification, and manual evaluation were used to predict subsequent events from the clinical notes after a non-conveyance mission. RESULTS: FastText-model (AUC 0.654) performed best in prediction of subsequent events after EMS non-conveyance missions (n = 11,846). The model and manual analyses showed that many of the subsequent events were planned before, EMS guided the patients to visit primary health care facilities or ED next or following days after non-conveyance. The most frequent signs and symptoms as subsequent event predictors were musculoskeletal-, infection-related and non-specific complaints. 1 in 5 the EMS documentation was inadequate and many of these led to a subsequent event. CONCLUSION: Machine learning can be used to predict subsequent events after EMS non-conveyance missions. From the patient safety perspective, it is notable that subsequent event does not necessarily mean that patient safety is compromised. There were a number of subsequent visits to primary health care or EDs, which were planned before by EMS. This demonstrates the appropriate use of limited resources to avoid unnecessary conveyance to the ED. However, further studies are needed without planned subsequent events to find out the harmful subsequent events, where EMS non-conveyance puts patient safety at risk.

Clustering Nursing Sentences - Comparing Three Sentence Embedding Methods.

In health sciences, high-quality text embeddings may augment qualitative data analysis of large amounts of text by enabling, e.g., searching and clustering of health information. This study aimed to evaluate three different sentence-level embedding methods in clustering sentences in nursing narratives from individual patients' hospital care episodes. Two of these embeddings are generated from language models based on the BERT framework, and the third on the Sent2Vec method. These embedding methods were used to cluster sentences from 20 patient care episodes and the results were manually evaluated. Findings suggest that the best clusters were produced by the embeddings from a BERT model fine-tuned for the proxy task of predicting subject headings for nursing text.

Artificial Intelligence -based technologies in nursing: A scoping literature review of the evidence.

BACKGROUND: Research on technologies based on artificial intelligence in healthcare has increased during the last decade, with applications showing great potential in assisting and improving care. However, introducing these technologies into nursing can raise concerns related to data bias in the context of training algorithms and potential implications for certain populations. Little evidence exists in the extant literature regarding the efficacious application of many artificial intelligence -based health technologies used in healthcare. OBJECTIVES: To synthesize currently available state-of the-art research in artificial intelligence -based technologies applied in nursing practice. DESIGN: Scoping review METHODS: PubMed, CINAHL, Web of Science and IEEE Xplore were searched for relevant articles with queries that combine names and terms related to nursing, artificial intelligence and machine learning methods. Included studies focused on developing or validating artificial intelligence -based technologies with a clear description of their impacts on nursing. We excluded non-experimental studies and research targeted at robotics, nursing management and technologies used in nursing research and education. RESULTS: A total of 7610 articles published between January 2010 and March 2021 were revealed, with 93 articles included in this review. Most studies explored the technology development (n = 55, 59.1%) and formation (testing) (n = 28, 30.1%) phases, followed by implementation (n = 9, 9.7%) and operational (n = 1, 1.1%) phases. The vast majority (73.1%) of studies provided evidence with a descriptive design (level VI) while only a small portion (4.3%) were randomised controlled trials (level II). The study aims, settings and methods were poorly described in the articles, and discussion of ethical considerations were lacking in 36.6% of studies. Additionally, one-third of papers (33.3%) were reported without the involvement of nurses. CONCLUSIONS: Contemporary research on applications of artificial intelligence -based technologies in nursing mainly cover the earlier stages of technology development, leaving scarce evidence of the impact of these technologies and implementation aspects into practice. The content of research reported is varied. Therefore, guidelines on research reporting and implementing artificial intelligence -based technologies in nursing are needed. Furthermore, integrating basic knowledge of artificial intelligence -related technologies and their applications in nursing education is imperative, and interventions to increase the inclusion of nurses throughout the technology research and development process is needed.

Neural Network and Random Forest Models in Protein Function Prediction.

Over the past decade, the demand for automated protein function prediction has increased due to the volume of newly sequenced proteins. In this paper, we address the function prediction task by developing an ensemble system automatically assigning Gene Ontology (GO) terms to the given input protein sequence. We develop an ensemble system which combines the GO predictions made by random forest (RF) and neural network (NN) classifiers. Both RF and NN models rely on features derived from BLAST sequence alignments, taxonomy and protein signature analysis tools. In addition, we report on experiments with a NN model that directly analyzes the amino acid sequence as its sole input, using a convolutional layer. The Swiss-Prot database is used as the training and evaluation data. In the CAFA3 evaluation, which relies on experimental verification of the functional predictions, our submitted ensemble model demonstrates competitive performance ranking among top-10 best-performing systems out of over 100 submitted systems. In this paper, we evaluate and further improve the CAFA3-submitted system. Our machine learning models together with the data pre-processing and feature generation tools are publicly available as an open source software at https://github.com/TurkuNLP/CAFA3.

How GPs can Recognize Persistent Frequent Attenders at Finnish Primary Health Care Using Electronic Patient Records.

INTRODUCTION: The proportion of patients who are frequent attenders (FAs) varies from few percent to almost 30% of all patients. A small group of patients continued to visit GPs year after year. In previous studies, it has been reported that over 15% of all 1-year FAs were persistent frequent attenders (pFAs). OBJECTIVES: This study aimed to identify typical features of pFAs from the textual content in their medical entries, which could help GPs to recognize pFAs easily and facilitated treatment.Methods: A retrospective register study was done, using 10 years of electronic patient records. The data were collected from Finnish primary health care centers and used to analyze chronic symptoms and diagnoses of pFAs and to calculate the inverse document frequency weight (IDF) of words used in the patient records. IDF was used to determine which words, if any, are typical for pFAs. The study group consisted of the 5-year pFAs and control group of 1-year FAs. The main background variables were age, gender, occupation, smoking habits, use of alcohol, and BMI. RESULTS: Out of 4392 frequent attenders, 6.6% were pFAs for 3 years and 1.1% were pFAs for 5 years. Of the pFAs, 65% were female and 35% were male. The study group had significantly more depressive episodes (P = .004), heart failure (P = .019), asthma (P = .032), COPD (P = .036), epilepsy (P = .035), and lumbago (P = .046) compared to the control group. GPs described their 5-year pFAs by words related to lung and breathing issues, but there was no statistical difference to the 1-year FAs' descriptions. CONCLUSION: A typical pFA seems to be a woman, aged about 55 years with depressive episodes, asthma or COPD, and lower back pain. Physicians describe pFAs with ordinary words in patient records. It was not possible to differentiate pFAs from 1-year FAs in this way.

How to Improve Information Technology to Support Healthcare to Address the COVID-19 Pandemic: an International Survey with Health Informatics Experts.

OBJECTIVES: To identify the ways in which healthcare information and communication technologies can be improved to address the challenges raised by the COVID-19 pandemic. METHODS: The study population included health informatics experts who had been involved with the planning, development and deployment of healthcare information and communication technologies in healthcare settings in response to the challenges presented by the COVID-19 pandemic. Data were collected via an online survey. A non-probability convenience sampling strategy was employed. Data were analyzed with content analysis. RESULTS: A total of 65 participants from 16 countries responded to the conducted survey. The four major themes regarding recommended improvements identified from the content analysis included: improved technology availability, improved interoperability, intuitive user interfaces and adoption of standards of care. Respondents also identified several key healthcare information and communication technologies that can help to provide better healthcare to patients during the COVID-19 pandemic, including telehealth, advanced software, electronic health records, remote work technologies (e.g., remote desktop computer access), and clinical decision support tools. CONCLUSIONS: Our results help to identify several important healthcare information and communication technologies, recommended by health informatics experts, which can help to provide better care to patients during the COVID-19 pandemic. The results also highlight the need for improved interoperability, intuitive user interfaces and advocating the adoption of standards of care.

Semantic Clustering to Augment Qualitative Content Analysis in Exploring Reasons for Emergency Department Transfer Delays.

The aim of the study was to explore emergency department transfer delays and to assess the potential of using a semantic clustering approach to augment the content analysis of transfer delay data. Data were collected over a period of 5 months from two hospitals. A set of (unique) phrases describing reasons for transfer delays (n=333) were clustered using the k-means with 1) cluster centroids initiated in an unsupervised fashion and 2) a semi-supervised version where the cluster centroids were initiated with keywords. The unsupervised algorithm clustered 77 % and the semi-supervised 86 % of the phrases to suitable clusters. We chose the better performing approach to augment our content analysis. Three main categories for transfer delays were found as a result. These included 1) insufficient staffing resources, 2) transportation and bed issues, and 3) patient and care related reasons. The findings inform the audit of organisational processes, accuracy of staffing and workflow to reduce transfer delays. Future research should explore implications of semantic clustering approaches to other narrative data sets in health service research.

Assisting nurses in care documentation: from automated sentence classification to coherent document structures with subject headings.

BACKGROUND: Up to 35% of nurses' working time is spent on care documentation. We describe the evaluation of a system aimed at assisting nurses in documenting patient care and potentially reducing the documentation workload. Our goal is to enable nurses to write or dictate nursing notes in a narrative manner without having to manually structure their text under subject headings. In the current care classification standard used in the targeted hospital, there are more than 500 subject headings to choose from, making it challenging and time consuming for nurses to use. METHODS: The task of the presented system is to automatically group sentences into paragraphs and assign subject headings. For classification the system relies on a neural network-based text classification model. The nursing notes are initially classified on sentence level. Subsequently coherent paragraphs are constructed from related sentences. RESULTS: Based on a manual evaluation conducted by a group of three domain experts, we find that in about 69% of the paragraphs formed by the system the topics of the sentences are coherent and the assigned paragraph headings correctly describe the topics. We also show that the use of a paragraph merging step reduces the number of paragraphs produced by 23% without affecting the performance of the system. CONCLUSIONS: The study shows that the presented system produces a coherent and logical structure for freely written nursing narratives and has the potential to reduce the time and effort nurses are currently spending on documenting care in hospitals.

Exploring Unsupervised Query Paraphrasing to Identify Relevant Search Phrases for a Literature Review.

Literature databases have multifaceted search options, but emerging research areas do not have an established terminology and therefore it is difficult to find relevant literature when conducting a review. This study aimed to explore if an unsupervised paraphrasing approach is useful in identifying relevant search phrases for a literature review on an emerging research topic - situational leadership in critical care. Using an initial set of 12 search phrases, the system was used to propose additional phrases, which were manually classified and further used in an expanded PubMed database search. Finally, we assessed the papers found with the expanded search and compared this to the initial search results. As a result, the expanded search more than tripled the search results, from 182 to 673 papers. The expanded search also more than tripled the number of relevant papers, from 12 in the original search to 39 in the expanded search.

Changing role of EMS -analyses of non-conveyed and conveyed patients in Finland.

BACKGROUND: Emergency Medical Services (EMS) and Emergency Departments (ED) have seen increasing attendance rates in the last decades. Currently, EMS are increasingly assessing and treating patients without the need to convey patients to health care facility. The aim of this study was to describe and compare the patient case-mix between conveyed and non-conveyed patients and to analyze factors related to non-conveyance decision making. METHODS: This was a prospective study design of EMS patients in Finland, and data was collected between 1st June and 30th November 2018. Adjusted ICPC2-classification was used as the reason for care. NEWS2-points were collected and analyzed both statistically and with a semi-supervised information extraction method. EMS patients' geographic location and distance to health care facilities were analyzed by urban-rural classification. RESULTS: Of the EMS patients (40,263), 59.8% were over 65 years of age and 46.0% of the patients had zero NEWS2 points. The most common ICPC2 code was weakness/tiredness, general (A04), as seen in 13.5% of all patients. When comparing patients between the non-conveyance and conveyance group, a total of 35,454 EMS patients met the inclusion criteria and 14,874 patients (42.0%) were not conveyed to health care facilities. According the multivariable logistic regression model, the non-conveyance decision was more likely made by ALS units, when the EMS arrival time was in the evening or night and when the distance to the health care facility was 21-40 km. Furthermore, younger patients, female gender, whether the patient had used alcohol and a rural area were also related to the non-conveyance decision. If the patient's NEWS2 score increased by one or two points, the likelihood of conveyance increased. When there was less than 1 h to complete a shift, this did not associate with either non-conveyance or conveyance decisions. CONCLUSIONS: The role of EMS might be changing. This warrants to redesign the chain-of-survival in EMS to include not only high-risk patient groups but also non-critical and general acute patients with non-specific reasons for care. Assessment and on-scene treatment without conveyance can be called the "stretched arm of the emergency department", but should be planned carefully to ensure patient safety.

Supporting the use of standardized nursing terminologies with automatic subject heading prediction: a comparison of sentence-level text classification methods.

OBJECTIVE: This study focuses on the task of automatically assigning standardized (topical) subject headings to free-text sentences in clinical nursing notes. The underlying motivation is to support nurses when they document patient care by developing a computer system that can assist in incorporating suitable subject headings that reflect the documented topics. Central in this study is performance evaluation of several text classification methods to assess the feasibility of developing such a system. MATERIALS AND METHODS: Seven text classification methods are evaluated using a corpus of approximately 0.5 million nursing notes (5.5 million sentences) with 676 unique headings extracted from a Finnish university hospital. Several of these methods are based on artificial neural networks. Evaluation is first done in an automatic manner for all methods, then a manual error analysis is done on a sample. RESULTS: We find that a method based on a bidirectional long short-term memory network performs best with an average recall of 0.5435 when allowed to suggest 1 subject heading per sentence and 0.8954 when allowed to suggest 10 subject headings per sentence. However, other methods achieve comparable results. The manual analysis indicates that the predictions are better than what the automatic evaluation suggests. CONCLUSIONS: The results indicate that several of the tested methods perform well in suggesting the most appropriate subject headings on sentence level. Thus, we find it feasible to develop a text classification system that can support the use of standardized terminologies and save nurses time and effort on care documentation.