An abstract is not available for this content so a preview has been provided. As you have access to this content, a full PDF is available via the ‘Save PDF’ action button.
We aimed to create and validate a natural language processing algorithm to extract wound infection-related information from nursing notes. We also estimated wound infection prevalence in homecare settings and described related patient characteristics. In this retrospective cohort study, a natural language processing algorithm was developed and validated against a gold standard testing set. Cases with wound infection were identified using the algorithm and linked to Outcome and Assessment Information Set data to identify related patient characteristics. The final version of the natural language processing vocabulary contained 3914 terms and expressions related to the presence of wound infection. The natural language processing algorithm achieved overall good performance (F-measure = 0.88). The presence of wound infection was documented for 1.03% (n = 602) of patients without wounds, for 5.95% (n = 3232) of patients with wounds, and 19.19% (n = 152) of patients with wound-related hospitalisation or emergency department visits. Diabetes, peripheral vascular disease, and skin ulcer were significantly associated with wound infection among homecare patients. Our findings suggest that nurses frequently document wound infection-related information. The use of natural language processing demonstrated that valuable information can be extracted from nursing notes which can be used to improve our understanding of the care needs of people receiving homecare. By linking findings from clinical nursing notes with additional structured data, we can analyse related patients' characteristics and use them to develop a tailored intervention that may potentially lead to reduced wound infection-related hospitalizations.
Abstract Objectives: The objectives of this study were (1) to develop and validate a simulation model to estimate daily probabilities of healthcare-associated infections (HAIs), length of stay (LOS), and mortality using time varying patient- and unit-level factors including staffing adequacy and (2) to examine whether HAI incidence varies with staffing adequacy. Setting: The study was conducted at 2 tertiary- and quaternary-care hospitals, a pediatric acute care hospital, and a community hospital within a single New York City healthcare network. Patients: All patients discharged from 2012 through 2016 (N = 562,435). Methods: We developed a non-Markovian simulation to estimate daily conditional probabilities of bloodstream, urinary tract, surgical site, and Clostridioides difficile infection, pneumonia, length of stay, and mortality. Staffing adequacy was modeled based on total nurse staffing (care supply) and the Nursing Intensity of Care Index (care demand). We compared model performance with logistic regression, and we generated case studies to illustrate daily changes in infection risk. We also described infection incidence by unit-level staffing and patient care demand on the day of infection. Results: Most model estimates fell within 95% confidence intervals of actual outcomes. The predictive power of the simulation model exceeded that of logistic regression (area under the curve [AUC], 0.852 and 0.816, respectively). HAI incidence was greatest when staffing was lowest and nursing care intensity was highest. Conclusions: This model has potential clinical utility for identifying modifiable conditions in real time, such as low staffing coupled with high care demand.
Abstract Purpose To evaluate the efficacy of next-generation sequencing (NGS) in minimal-residual-disease (MRD) monitoring in Chinese patients with multiple myeloma (MM). Methods This study analyzed 60 Chinese MM patients. During MRD monitoring in these patients’ post-therapy, clonal immunoglobulin heavy chain (IGH) rearrangements were detected via NGS using LymphoTrack assays. MRD monitoring was performed using NGS or next-generation flow cytometry (NGF), and the results were compared. Additionally, the sensitivity and reproducibility of the NGS method were assessed. Results The MRD detection range of the NGS method was 10 –6 –10 –1 , which suggested good linearity, with a Pearson correlation coefficient of 0.985 and a limit of detection of 10 –6 . Intra- and inter-assay reproducibility analyses showed that NGS exhibited 100% reproducibility with low variability in clonal cells. At diagnosis, unique clones were found in 42 patients (70.0%) with clonal IGH rearrangements, which were used as clonality markers for MRD monitoring post-therapy. Comparison of NGS and NGF for MRD monitoring showed 79.1% concordance. No samples that tested MRD-positive via NGF were found negative via NGS, indicating the higher sensitivity of NGS. MRD could be detected using NGS in 6 of 7 samples before autologous hematopoietic stem-cell transplantation, and 5 of them tested negative post-transplantation. In contrast, the NGF method could detect MRD in only 1 sample pre-transplantation. Conclusion Compared with NGF, NGS exhibits higher sensitivity and reproducibility in MRD detection and can be an effective strategy for MRD monitoring in Chinese MM patients.
Abstract Background Certain types of cancer and treatment increase the risk of falls among cancer patients, particularly patients with hematologic cancer undergoing bone marrow transplant (BMT). Nurses are integral to preventing falls and maintaining patient safety. Understanding patients undergoing BMT fall risk factors may help nurses identify high fall risk patients and develop fall prevention interventions. Purpose This systematic review aims to identify risk factors for falls among hospitalized adult patients receiving BMT treatment. Methods Guided by the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses, a systematic review of the literature was conducted by searching databases PubMed and CINAHL. Study quality was evaluated using the Crowe Critical Appraisal Tool form (v1.4). Findings An initial search yielded 829 articles; six were included for final review after removing duplicates and screening for inclusion criteria: specific to patients undergoing BMT, measure fall outcome, in hospital, and original research. The identified risk factors include age of 65 and older, leukemia diagnosis, days of diarrhea, incontinence of urine or stool, increased pulse rate, muscle weakness, hypnotic, anxiolytic medication, recent steroid use, allogenic transplant, and post‐engraftment period. Conclusions Risk factors for falls among patients undergoing BMT are multifactorial and are related to muscle weakness, medication administration, pulse rate, type of transplant, age, engraftment period, and bathroom use. Implications for nursing Nurses providing care to patients undergoing BMT need to assess and increase nurse surveillance on allogeneic transplant patients, specifically those on anxiolytic, hypnotic, and steroid medications. Nurses providing care to patients undergoing BMT should implement more fall prevention strategies in patients undergoing BMT who develop diarrhea and urine or stool incontinence. Identifying specific patients undergoing BMT fall risk factors and applying multifaceted individualized fall prevention strategies has the potential to improve allogeneic transplant patient care and prevent fall‐related complications.
Wound infection is prevalent in home healthcare (HHC) and often leads to hospitalizations. However, none of the previous studies of wounds in HHC have used data from clinical notes. Therefore, the authors created a more accurate description of a patient's condition by extracting risk factors from clinical notes to build predictive models to identify a patient's risk of wound infection in HHC.The structured data (eg, standardized assessments) and unstructured information (eg, narrative-free text charting) were retrospectively reviewed for HHC patients with wounds who were served by a large HHC agency in 2014. Wound infection risk factors were identified through bivariate analysis and stepwise variable selection. Risk predictive performance of three machine learning models (logistic regression, random forest, and artificial neural network) was compared.A total of 754 of 54,316 patients (1.39%) had a hospitalization or ED visit related to wound infection. In the bivariate logistic regression, language describing wound type in the patient's clinical notes was strongly associated with risk (odds ratio, 9.94; P < .05). The areas under the curve were 0.82 in logistic regression, 0.75 in random forest, and 0.78 in artificial neural network. Risk prediction performance of the models improved (by up to 13.2%) after adding risk factors extracted from clinical notes.Logistic regression showed the best risk prediction performance in prediction of wound infection-related hospitalization or ED visits in HHC. The use of data extracted from clinical notes can improve the performance of risk prediction models.
Abstract Background In the U.S., homebound older adults often have multiple chronic conditions thereby increasing their infection risk. For those receiving home health care (HHC), environmental hazards in the home can not only exacerbate infection risk but can also impede effective infection prevention and control (IPC) practices for HHC clinicians, patients and their caregivers. Timely and accurate assessment of environmental risks are crucial. Yet, no tools exist specifically for HHC clinicians to assess infection risk factors in the home environment. To fill this gap, we developed scales to measure clutter and cleanliness in HHC patients’ homes. The clutter and cleanliness rating scale. Methods First, we reviewed existing clutter and cleanliness scales, noting that most validated scales focused on hoarding. We adapted these scales and developed observational items focused on IPC in the home environment. During pilot testing with 15 HHC patients and caregivers from an urban HHC agency, we used a uniform rating scale for both clutter and cleanliness items, which posed challenges due to variable home environments and interviewer biases. Following pilot testing, we refined the scales based on interviewer feedback. To improve coding consistency, interviewers received training using a procedural manual and completed a home observation quiz with example pictures. Results Our revised observational items now have distinct rating scales for cleanliness and clutter. Clutter is rated on percentages of free space to reduce subjectivity, and cleanliness is rated on a scale of visible clean to not clean (Table 1). Even with refinement, there was still difficulty achieving consistent ratings among interviewers, specifically with the middle scale points (mostly and moderately clean; some and moderate clutter). However, after scale revisions and interviewer trainings, home observation quiz responses among interviewers achieved at least 80% consistency. Conclusion Our scales represent the first observational items designed to assess home cleanliness and clutter for IPC purposes. If widely adopted, these scales could enable HHC clinicians to effectively assess environmental hazards, informing patient/caregiver educational needs and enhancing patient safety by reducing infection risks. Disclosures All Authors: No reported disclosures
Background: As the population of older Americans with chronic conditions continues to grow, the role of home health care (HHC) services in improving care transitions between acute care and independent living has become a national priority. Infection prevention and control (IPC) is often a focus of quality improvement initiatives at HHC agencies. In this study, we investigated barriers and facilitators of effective IPC in HHC. Methods: In 2018, we conducted in-depth, telephone interviews with 41 staff from 13 agencies across the United States including administrators, IPC and quality improvement personnel, registered nurses and HHC aides. Interview transcripts were coded in NVivo v 12 software (QSR International), and themes were identified using content analysis. Results: We identified 4 themes: (1) IPC as a priority, (2) uniqueness of home health care, (3) importance of education, and (4) keys to success and innovation. When discussing the top priorities in the agency, participants described IPC as a big part of patient safety and as playing a major role in reducing rates of rehospitalization. Protection of patients and staff was described as a major motivator for compliance with IPC policies and procedures, and agencies placed specific focus on improving hand hygiene, bag technique, and disinfection of equipment. Almost all participants described the uniqueness of providing health care in a patient’s home, which was often talked about as an unpredictable environment due to lack of cleanliness, presence of pets and/or pests, and family dynamics. Furthermore, the intermittent nature of HHC was described as affecting effective implementation of IPC procedures. Education was seen as a tool to improve and overcome patient, caregiver, and families’ lack of compliance with IPC procedures. However, to be effective educators and role models, participants stated that they themselves needed to be properly educated on IPC policies and procedures. Several keys to success and innovation were discussed including (1) agency reputation as a key driver of quality; (2) agency focus on quality and patient satisfaction; (3) using agency infection data to improve the quality of patient care; (4) utilizing all available resources within and outside of the agency, and (5) a coordinated approach to patient care with direct, multimodal communication among all clinical disciplines. Conclusions: This qualitative work identified barriers to effective infection prevention and control in HHC and important facilitators that HHC agencies can use to improve implementation of policies and procedures to improve patient care. Funding: None Disclosures: None
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
