Citation: Michalowski, M., Rao, M., Wilk, S., Michalowski, W., & Carrier, M. (2023). Using graph rewriting to operationalize medical knowledge for the revision of concurrently applied clinical practice guidelines. Artificial intelligence in medicine, 140, 102550. https://doi.org/10.1016/j.artmed.2023.102550
USING GRAPH REWRITING TO OPERATIONALIZE MEDICAL KNOWLEDGE FOR THE REVISION OF CONCURRENTLY APPLIED CLINICAL PRACTICE GUIDELINES
Clinical practice guidelines (CPGs) are patient management tools that synthesize medical knowledge into an actionable format. CPGs are disease specific with limited applicability to the management of complex patients suffering from multimorbidity. For the management of these patients, CPGs need to be augmented with secondary medical knowledge coming from a variety of knowledge repositories. The operationalization of this knowledge is key to increasing CPGs' uptake in clinical practice. In this work, we propose an approach to operationalizing secondary medical knowledge inspired by graph rewriting. We assume that the CPGs can be represented as task network models, and provide an approach for representing and applying codified medical knowledge to a specific patient encounter. We formally define revisions that model and mitigate adverse interactions between CPGs and we use a vocabulary of terms to instantiate these revisions. We demonstrate the application of our approach using synthetic and clinical examples. We conclude by identifying areas for future work with the vision of developing a theory of mitigation that will facilitate the development of comprehensive decision support for the management of multimorbid patients.
Citation:Zolnoori, M., Zolnour, A., & Topaz, M. (2023). ADscreen: A speech processing-based screening system for automatic identification of patients with Alzheimer's disease and related dementia. Artificial Intelligence in Medicine, 143, 102624. https://doi.org/10.1016/j.artmed.2023.102624.
ADSCREEN: A SPEECH PROCESSING-BASED SCREENING SYSTEM FOR AUTOMATIC IDENTIFICATION OF PATIENTS WITH ALZHEIMER'S DISEASE AND RELATED DEMENTIA
This innovative study presents ADscreen, a cutting-edge speech processing algorithm designed to automatically identify patients with Alzheimer's disease and related dementias (ADRD). The algorithm is built on five core components that analyze both acoustic and linguistic aspects of patients' speech. A total of five major machine learning architectures were used, integrating data from acoustic, linguistic, and contextual word embedding vectors. Performance metrics demonstrated an F1-score of 89.55 and AUC-ROC of 93.89 for the test dataset, indicating the algorithm's high level of accuracy. The study emphasizes the potential of ADscreen to be incorporated into clinical workflows, serving as a crucial tool for the timely diagnosis and care of patients with cognitive impairments.
Citation:Topaz, M., Song, J., Davoudi, A., McDonald, M., Taylor, J., Sittig, S., & Bowles, K. (2023). Home Health Care Clinicians' Use of Judgment Language for Black and Hispanic Patients: Natural Language Processing Study. JMIR nursing, 6, e42552. https://doi.org/10.2196/42552.
Home Health Care Clinicians' Use of Judgment Language for Black and Hispanic Patients: Natural Language Processing Study
This retrospective observational cohort study investigated racial differences in judgment language usage in clinical notes and the relationship between judgment language and time spent on home visits in home health care. Data from 45,384 patients who received home health care services in 2019 were analyzed using a natural language processing algorithm. Results showed that 38% of patients had judgment language in their clinical notes, with the highest usage in Hispanic patients, followed by Black, White, and Asian patients. Black and Hispanic patients were 14% more likely to have judgment language in their notes compared to White patients. Additionally, the use of judgment language reduced the length of home health care visits by 21 minutes. The study highlights the need for further research on the impact of judgment language on care quality and the implementation of policy, education, and clinical practice improvements to address biases.
Citation: Hobensack M, Song J, Scharp D, Bowles KH, Topaz M. Machine learning applied to electronic health record data in home healthcare: A scoping review. Int J Med Inform. 2023 Feb;170:104978. doi: 10.1016/j.ijmedinf.2022.104978. Epub 2022 Dec 30. PMID: 36592572; PMCID: PMC9869861.
This study aimed to synthesize and evaluate the use of machine learning to predict adverse outcomes, such as hospitalization or mortality, in home healthcare using electronic health record data. The study analyzed 20 studies and found that tree-based algorithms were most commonly used, while psychological predictors were frequently excluded. Most of the studies demonstrated high or unclear risk of bias. The authors concluded that machine learning algorithms should be considered for inclusion in clinical decision support systems in home healthcare and that a more comprehensive approach to risk prediction, including psychological and interpersonal characteristics, is needed. To facilitate the widespread adoption of machine learning in this setting, stakeholders should encourage standardization.
This special issue of the Journal of Nursing Management edited by NAIL members Peltonen and Topaz focuses on the use of AI in nursing and healthcare, exploring its implications for nursing management. The articles included in this issue cover a range of topics, including relevant AI technologies for nursing, ethical issues related to artificial intelligence in healthcare, the role of AI in assessing and improving the quality of care, and the use of AI to support nursing education and training. The articles provide valuable insights and evidence on the impact and potential applications of AI in nursing and healthcare, as well as highlighting some of the ethical considerations and challenges that need to be addressed.
Citation: Von Gerich H, Moen H, Block LJ, Chu CH, DeForest H, Hobensack M, Michalowski M, Mitchell J, Nibber R, Olalia MA, Pruinelli L, Ronquillo CE, Topaz M, Peltonen LM. Artificial Intelligence -based technologies in nursing: A scoping literature review of the evidence. Int J Nurs Stud. 2022 Mar;127:104153.
Artificial Intelligence -based technologies in nursing: A scoping literature review of the evidence
Citation: Ronquillo CE, Peltonen LM, Pruinelli L, Chu CH, Bakken S, Beduschi A, Cato K, Hardiker N, Junger A, Michalowski M, Nyrup R, Rahimi S, Reed DN, Salakoski T, Salanterä S, Walton N, Weber P, Wiegand T, Topaz M. Artificial intelligence in nursing: Priorities and opportunities from an international invitational think-tank of the Nursing and Artificial Intelligence Leadership Collaborative. J Adv Nurs. 2021 Sep;77(9):3707-3717. doi: 10.1111/jan.14855. Epub 2021 May 18. PMID: 34003504; PMCID: PMC7612744.
Artificial intelligence in nursing: Priorities and opportunities from an international invitational think-tank of the Nursing and Artificial Intelligence Leadership Collaborative
A Clinical Decision Support System Design Framework for Nursing Practice
As nurses increasingly engage in decision-making for patients, a unique opportunity exists to translate research into practice using clinical decision support systems (CDSSs). While research has shown that CDSS has led to improvements in patient outcomes and nursing workflow, the success rate of CDSS implementation in nursing is low. Further, the majority of CDSS for nursing are not designed to support the care of patients with comorbidity. The aim of the study is to conceptualize an evidence-based CDSS supporting complex patient care for nursing. We conceptualized the CDSS through extracting scientific findings of CDSS design and development. To describe the CDSS, we developed a conceptual framework comprising the key components of the CDSS and the relationships between the components. We instantiated the framework in the context of a hypothetical clinical case. The proposed framework provides a common architecture for CDSS development and bridges CDSS research findings and development.
Toward an Augmented Nursing-Artificial Intelligence Future
How can artificial intelligence (AI) augment and elevate what is known and delivered by nurses on a daily basis? Is AI replacing nursing? How do nurses guide the decisions made by AI used in practice? Those are several questions populating nurses' thoughts currently, mostly resulting from a lack of understanding of what AI is and how it can and will impact their work. AI is already embedded in nurses' daily life as algorithms (ie, sepsis monitoring systems) and smart systems (eg, smart beds and intravenous pumps), just to cite a couple of examples of AI applications. Frequently, we as nurses do not recognize them as such. AI applications are being incorporated into clinical care, and in many situations, awareness of their impact is uncertain due to a lack of understanding on how they are developed.
Citation: Pruinelli L. Nursing and Data: Powering Nursing Leaders for Big Data Science. Rev Bras Enferm. 2021 Jul 14;74(4):e740401. English, Portuguese, Spanish. doi: 10.1590/0034-7167.2021740401. PMID: 34287564.