Lack of Clinical Utility of Labeled White Blood Cell Scintigraphy in Patients with Fever of Unknown Origin

Background Labeled white blood cell scintigraphy (WBCS) has been used for over 40 years to localize an infection source in patients with fever of unknown origin (FUO). It continues to be in widespread use for such patients in modern times, despite the tremendous advances in modern radiological imaging and laboratory medicine. Methods We critically evaluated the clinical contribution of WBCS performed in 132 patients with FUO at 7 hospitals from mid-2015 to the end of 2019. For each patient, all radiographic and laboratory results, and all electronic clinical notes, were carefully evaluated as many days prior to and following the scan as necessary to arrive at a final diagnosis. Results Although 50 WBCS (38%) showed positive findings, the majority of these were false positive (FP). Of the 19 true positive (TP) scans, most were already known or about to become known by tests already ordered at the time of the scan. Only 2 TP scans (1.5%) contributed to the final diagnosis, and these did so only indirectly. FP scans led to 7 unnecessary procedures. Conclusions In FUO patients for whom an infection source is not discovered following an appropriate radiographic and laboratory workup, WBCS is not a useful procedure.

Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients

Mortality prediction for intensive care unit (ICU) patients is crucial for improving outcomes and efficient utilization of resources. Accessibility of electronic health records (EHR) has enabled data-driven predictive modeling using machine learning. However, very few studies rely solely on unstructured clinical notes from the EHR for mortality prediction. In this work, we propose a framework to predict short, mid, and long-term mortality in adult ICU patients using unstructured clinical notes from the MIMIC III database, natural language processing (NLP), and machine learning (ML) models. Depending on the statistical description of the patients’ length of stay, we define the short-term as 48-hour and 4-day period, the mid-term as 7-day and 10-day period, and the long-term as 15-day and 30-day period after admission. We found that by only using clinical notes within the 24 hours of admission, our framework can achieve a high area under the receiver operating characteristics (AU-ROC) score for short, mid and long-term mortality prediction tasks. The test AU-ROC scores are 0.87, 0.83, 0.83, 0.82, 0.82, and 0.82 for 48-hour, 4-day, 7-day, 10-day, 15-day, and 30-day period mortality prediction, respectively. We also provide a comparative study among three types of feature extraction techniques from NLP: frequency-based technique, fixed embedding-based technique, and dynamic embedding-based technique. Lastly, we provide an interpretation of the NLP-based predictive models using feature-importance scores.

The Food and Drug Administration Biologics Effectiveness and Safety Initiative Facilitates Detection of Vaccine Administrations From Unstructured Data in Medical Records Through Natural Language Processing

Introduction: The Food and Drug Administration Center for Biologics Evaluation and Research conducts post-market surveillance of biologic products to ensure their safety and effectiveness. Studies have found that common vaccine exposures may be missing from structured data elements of electronic health records (EHRs), instead being captured in clinical notes. This impacts monitoring of adverse events following immunizations (AEFIs). For example, COVID-19 vaccines have been regularly administered outside of traditional medical settings. We developed a natural language processing (NLP) algorithm to mine unstructured clinical notes for vaccinations not captured in structured EHR data.Methods: A random sample of 1,000 influenza vaccine administrations, representing 995 unique patients, was extracted from a large U.S. EHR database. NLP techniques were used to detect administrations from the clinical notes in the training dataset [80% (N = 797) of patients]. The algorithm was applied to the validation dataset [20% (N = 198) of patients] to assess performance. Full medical charts for 28 randomly selected administration events in the validation dataset were reviewed by clinicians. The NLP algorithm was then applied across the entire dataset (N = 995) to quantify the number of additional events identified.Results: A total of 3,199 administrations were identified in the structured data and clinical notes combined. Of these, 2,740 (85.7%) were identified in the structured data, while the NLP algorithm identified 1,183 (37.0%) administrations in clinical notes; 459 were not also captured in the structured data. This represents a 16.8% increase in the identification of vaccine administrations compared to using structured data alone. The validation of 28 vaccine administrations confirmed 27 (96.4%) as “definite” vaccine administrations; 18 (64.3%) had evidence of a vaccination event in the structured data, while 10 (35.7%) were found solely in the unstructured notes.Discussion: We demonstrated the utility of an NLP algorithm to identify vaccine administrations not captured in structured EHR data. NLP techniques have the potential to improve detection of vaccine administrations not otherwise reported without increasing the analysis burden on physicians or practitioners. Future applications could include refining estimates of vaccine coverage and detecting other exposures, population characteristics, and outcomes not reliably captured in structured EHR data.

Identifying Heart Failure Symptoms and Poor Self-Management in Home Healthcare: A Natural Language Processing Study

The goal of this natural language processing (NLP) study was to identify patients in home healthcare with heart failure symptoms and poor self-management (SM). The preliminary lists of symptoms and poor SM status were identified, NLP algorithms were used to refine the lists, and NLP performance was evaluated using 2.3 million home healthcare clinical notes. The overall precision to identify patients with heart failure symptoms and poor SM status was 0.86. The feasibility of methods was demonstrated to identify patients with heart failure symptoms and poor SM documented in home healthcare notes. This study facilitates utilizing key symptom information and patients’ SM status from unstructured data in electronic health records. The results of this study can be applied to better individualize symptom management to support heart failure patients’ quality-of-life.

Sharing Clinical Notes in a Canadian Mental Health Setting: Recommendations from Applying the Consolidated Framework for Intervention Research

During the COVID-19 pandemic, the OpenNotes movement presents an optimal solution for virtual engagement through the sharing of clinical notes within mental health care settings. Therefore, we conducted interviews to discover how mental health clinicians interact with patients using OpenNotes. We integrated The Consolidated Framework for Intervention Research to establish implementation recommendations. As both challenges and opportunities were identified, future research should address challenges to foster patient and clinician engagement in sharing clinical notes.

Management of Prelabour Rupture of Membranes at Term, at Northland District Health Board.

<p>Background Prelabour rupture of membranes at term (PROM) is a subject of interest to women and maternity care providers alike. Management of PROM varies internationally, and regionally within New Zealand, despite the presence of interprofessional consensus statements. Northland District Health Board (NDHB) policy differs from most maternity care facilities by enabling expectant management of labour for women at low risk of transmission of Group β Streptococcus to their baby to extend to 96 hours from time of rupture of membranes. This study aimed to explore whether the NDHB policy was applied in practice and safely served the needs of women and babies in this DHB. Methods A retrospective quantitative clinical notes review was conducted of files in a one-year sample. The clinical notes of 123 women who had duration from ROM to birth at term of 18 hours or more were reviewed. Statistical comparisons using percentages, means and odds-ratios were made to a one-year sample of all other births at term at NDHB facilities, and with birth data from the New Zealand College of Midwives Clinical Outcomes Research Database (COMCORD). Findings Variables including demographic data, antenatal and intrapartum care given, time factors and outcomes themselves were reviewed. Few variables impacted outcomes within the PROM sample, though use of intravenous oxytocin was associated with increased epidural use and increased incidence of instrumental birth. Wāhine Māori had an increased incidence of vaginal births but some variables and outcomes highlighted inequities, including reduced antenatal screening, a higher incidence of maternal smoking, severe postpartum haemorrhage, and admission to Special Care Baby Units. Duration splits at 48 and 96 hours were applied to identify whether time increased risks for women or babies, but duration did not appear to be a factor which increased risk. The phenomenon of PROM itself increased risk for women and babies, increasing rates of labour induction, augmentation, epidural use, operative births, postpartum haemorrhage, admission to Special Care Baby Units and decreased exclusive breastfeeding at discharge. Conclusions The NDHB PROM policy appeared to be applied consistently and did not appear to increase risk for women and babies. Risks were increased for all women with PROM, with some inequitable outcomes for wahine Māori and pēpi. This research provides a comparison which is informative for clinical practice, education, and future research, and supports women’s involvement in decision-making.</p>

Management of Prelabour Rupture of Membranes at Term, at Northland District Health Board.

<p>Background Prelabour rupture of membranes at term (PROM) is a subject of interest to women and maternity care providers alike. Management of PROM varies internationally, and regionally within New Zealand, despite the presence of interprofessional consensus statements. Northland District Health Board (NDHB) policy differs from most maternity care facilities by enabling expectant management of labour for women at low risk of transmission of Group β Streptococcus to their baby to extend to 96 hours from time of rupture of membranes. This study aimed to explore whether the NDHB policy was applied in practice and safely served the needs of women and babies in this DHB. Methods A retrospective quantitative clinical notes review was conducted of files in a one-year sample. The clinical notes of 123 women who had duration from ROM to birth at term of 18 hours or more were reviewed. Statistical comparisons using percentages, means and odds-ratios were made to a one-year sample of all other births at term at NDHB facilities, and with birth data from the New Zealand College of Midwives Clinical Outcomes Research Database (COMCORD). Findings Variables including demographic data, antenatal and intrapartum care given, time factors and outcomes themselves were reviewed. Few variables impacted outcomes within the PROM sample, though use of intravenous oxytocin was associated with increased epidural use and increased incidence of instrumental birth. Wāhine Māori had an increased incidence of vaginal births but some variables and outcomes highlighted inequities, including reduced antenatal screening, a higher incidence of maternal smoking, severe postpartum haemorrhage, and admission to Special Care Baby Units. Duration splits at 48 and 96 hours were applied to identify whether time increased risks for women or babies, but duration did not appear to be a factor which increased risk. The phenomenon of PROM itself increased risk for women and babies, increasing rates of labour induction, augmentation, epidural use, operative births, postpartum haemorrhage, admission to Special Care Baby Units and decreased exclusive breastfeeding at discharge. Conclusions The NDHB PROM policy appeared to be applied consistently and did not appear to increase risk for women and babies. Risks were increased for all women with PROM, with some inequitable outcomes for wahine Māori and pēpi. This research provides a comparison which is informative for clinical practice, education, and future research, and supports women’s involvement in decision-making.</p>

The Violin in Music Therapy: How do I use the violin in music therapy with people who have intellectual disabilities or neurological conditions?

<p>In this research I explored my use of the violin in music therapy with people who have intellectual disability and neurological conditions. I am interested in this topic because the violin is my primary instrument and I wanted to learn more about its therapeutic potential. My research methodology was Secondary Analysis of Qualitative Data, and the data were my clinical notes and research journal. Findings were generated through thematic analysis of the data. Five themes emerged. Specifically, I found that the violin’s voice-like timbre was helpful in fostering connections and encouraging emotional and communicative expression. Similarly, the ability to physically share the instrument, and to play it while mobile, also fostered connections between me and my participants. Because of my expertise on the violin I was able to utilize a vast variety of performance techniques both with familiar music and within improvisations that elicited meaningful musical moments. My relationship with the violin has developed and changed throughout this process and the violin has become a part of my identity as a music therapist. I anticipate that findings will interest other music therapists, and perhaps encourage them to use alternative instruments within their practice.</p>