Identification of delirium from real-world electronic health record clinical notes.

Introduction: We tested the ability of our natural language processing (NLP) algorithm to identify delirium episodes in a large-scale study using real-world clinical notes. Methods: We used the Rochester Epidemiology Project to identify persons ≥ 65 years who were hospitalized between 2011 and 2017. We identified all persons with an International Classification of Diseases code for delirium within ±14 days of a hospitalization. We independently applied our NLP algorithm to all clinical notes for this same population. We calculated rates using number of delirium episodes as the numerator and number of hospitalizations as the denominator. Rates were estimated overall, by demographic characteristics, and by year of episode, and differences were tested using Poisson regression. Results: In total, 14,255 persons had 37,554 hospitalizations between 2011 and 2017. The code-based delirium rate was 3.02 per 100 hospitalizations (95% CI: 2.85, 3.20). The NLP-based rate was 7.36 per 100 (95% CI: 7.09, 7.64). Rates increased with age (both p < 0.0001). Code-based rates were higher in men compared to women (p = 0.03), but NLP-based rates were similar by sex (p = 0.89). Code-based rates were similar by race and ethnicity, but NLP-based rates were higher in the White population compared to the Black and Asian populations (p = 0.001). Both types of rates increased significantly over time (both p values < 0.001). Conclusions: The NLP algorithm identified more delirium episodes compared to the ICD code method. However, NLP may still underestimate delirium cases because of limitations in real-world clinical notes, including incomplete documentation, practice changes over time, and missing clinical notes in some time periods.

Patient Perspectives on Integrating Risk Prediction Into Kidney Care: Opinion Piece.

Although Chronic Kidney Disease is common, only a relatively small proportion of individuals will reach kidney failure requiring dialysis or transplantation. Validated risk equations using routine laboratory tests have been developed that can easily be used at the bedside to help clinicians accurately predict the risk of kidney failure in their patient population, in turn informing patient-centered conversations, guiding appropriate nephrology referrals, improving the timing of dialysis treatment planning, and identifying individuals who are most likely to benefit from interventions. In this article, individuals living with kidney disease share why access to individualized prediction of kidney failure risk can help patients manage their disease and why it should be considered an essential component of kidney care.

Telehealth versus face-to-face visits: A comprehensive outpatient perspective-based cohort study of patients with kidney disease.

BACKGROUND: Telenephrology has become an important health care delivery modality during the COVID-19 pandemic. However, little is known about patient perspectives on the quality of care provided via telenephrology compared to face-to-face visits. We aimed to use objective data to study patients' perspectives on outpatient nephrology care received via telenephrology (phone and video) versus face-to-face visits. METHODS: We retrospectively studied adults who received care in the outpatient Nephrology & Hypertension division at Mayo Clinic, Rochester, from March to July 2020. We used a standardized survey methodology to evaluate patient satisfaction. The primary outcome was the percent of patients who responded with a score of good (4) or very good (5) on a 5-point Likert scale on survey questions that asked their perspectives on access to their nephrologist, relationship with care provider, their opinions on the telenephrology technology, and their overall assessment of the care received. Wilcoxon rank sum tests and chi-square tests were used as appropriate to compare telenephrology versus face-to-face visits. RESULTS: 3,486 of the patient encounters were face-to-face, 808 phone and 317 video visits. 443 patients responded to satisfaction surveys, and 21% of these had telenephrology encounters. Established patients made up 79.6% of telenephrology visits and 60.9% of face-to-face visits. There was no significant difference in patient perceived access to health care, satisfaction with their care provider, or overall quality of care between patients cared for via telenephrology versus face-to-face. Patient satisfaction was also equally high. CONCLUSIONS: Patient satisfaction was equally high amongst those patients seen face-to-face or via telenephrology.

Risk Prediction Model for 6-Month Mortality for Patients Discharged to Skilled Nursing Facilities.

OBJECTIVE: Hospitalized patients discharged to skilled nursing facilities (SNFs) for post-acute care are at high risk for adverse outcomes. Yet, absence of effective prognostic tools hinders optimal care planning and decision making. Our objective was to develop and validate a risk prediction model for 6-month all-cause death among hospitalized patients discharged to SNFs. DESIGN: Retrospective cohort study. SETTING AND PARTICIPANTS: Patients discharged from 1 of 2 hospitals to 1 of 10 SNFs for post-acute care in an integrated health care delivery system between January 1, 2009, and December 31, 2016. METHODS: Gradient-boosting machine modeling was used to predict all-cause death within 180 days of hospital discharge with use of patient demographic characteristics, comorbidities, pattern of prior health care use, and clinical parameters from the index hospitalization. Area under the receiver operating characteristic curve (AUC) was assessed for out-of-sample observations under 10-fold cross-validation. RESULTS: We identified 9803 unique patients with 11,647 hospital-to-SNF discharges [mean (SD) age, 80.72 (9.71) years; female sex, 61.4%]. These discharges involved 9803 patients alive at 180 days and 1844 patients who died between day 1 and day 180 of discharge. Age, comorbid burden, health care use in prior 6 months, abnormal laboratory parameters, and mobility status during hospital stay were the most important predictors of 6-month death (model AUC, 0.82). CONCLUSION AND IMPLICATIONS: We derived a robust prediction model with parameters available at discharge to SNFs to calculate risk of death within 6 months. This work may be useful to guide other clinicians wishing to develop mortality prediction instruments specific to their post-acute SNF populations.

Ascertainment of Delirium Status Using Natural Language Processing From Electronic Health Records.

BACKGROUND: Delirium is underdiagnosed in clinical practice and is not routinely coded for billing. Manual chart review can be used to identify the occurrence of delirium; however, it is labor-intensive and impractical for large-scale studies. Natural language processing (NLP) has the capability to process raw text in electronic health records (EHRs) and determine the meaning of the information. We developed and validated NLP algorithms to automatically identify the occurrence of delirium from EHRs. METHODS: This study used a randomly selected cohort from the population-based Mayo Clinic Biobank (N = 300, age ≥65). We adopted the standardized evidence-based framework confusion assessment method (CAM) to develop and evaluate NLP algorithms to identify the occurrence of delirium using clinical notes in EHRs. Two NLP algorithms were developed based on CAM criteria: one based on the original CAM (NLP-CAM; delirium vs no delirium) and another based on our modified CAM (NLP-mCAM; definite, possible, and no delirium). The sensitivity, specificity, and accuracy were used for concordance in delirium status between NLP algorithms and manual chart review as the gold standard. The prevalence of delirium cases was examined using International Classification of Diseases, 9th Revision (ICD-9), NLP-CAM, and NLP-mCAM. RESULTS: NLP-CAM demonstrated a sensitivity, specificity, and accuracy of 0.919, 1.000, and 0.967, respectively. NLP-mCAM demonstrated sensitivity, specificity, and accuracy of 0.827, 0.913, and 0.827, respectively. The prevalence analysis of delirium showed that the NLP-CAM algorithm identified 12 651 (9.4%) delirium patients, the NLP-mCAM algorithm identified 20 611 (15.3%) definite delirium cases, and 10 762 (8.0%) possible cases. CONCLUSIONS: NLP algorithms based on the standardized evidence-based CAM framework demonstrated high performance in delineating delirium status in an expeditious and cost-effective manner.

Provider Perspectives and Clinical Outcomes with Inpatient Telenephrology.

BACKGROUND AND OBJECTIVES: Despite the dramatic increase in the provision of virtual nephrology care, only anecdotal reports of outcomes without comparators to usual care exist in the literature. This study aimed to provide objective determination of clinical noninferiority of hybrid (telenephrology plus face-to-face) versus standard (face-to-face) inpatient nephrology care. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: This retrospective study compares objective outcomes in patients who received inpatient hybrid care versus standard nephrology care at two Mayo Clinic Health System community hospitals. Outcomes were then additionally compared with those patients receiving care at another Mayo Clinic Health System site where only standard care is available. Hospitalized adults who had nephrology consults from March 1, 2020 to February 28, 2021 were considered. Regression was used to assess 30-day mortality, length of hospitalization, readmissions, odds of being prescribed dialysis, and hospital transfers. Sensitivity analysis was performed using patients who had ≥50% of their care encounters via telenephrology. Structured surveys were used to understand the perspectives of non-nephrology hospital providers and telenephrologists. RESULTS: In total, 850 patients were included. Measured outcomes that included the number of hospital transfers (odds ratio, 1.19; 95% confidence interval, 0.37 to 3.82) and 30-day readmissions (odds ratio, 0.97; 95% confidence interval, 0.84 to 1.06), among others, did not differ significantly between controls and patients in the general cohort. Telenephrologists (n=11) preferred video consults (82%) to phone for communication. More than half (64%) of telenephrologists spent less time on telenephrology compared with standard care. Non-nephrology hospital providers (n=21) were very satisfied (48%) and satisfied (29%) with telenephrology response time and felt telenephrology was as safe as standard care (67%), while providing them enough information to make patient care decisions (76%). CONCLUSIONS: Outcomes for in-hospital nephrology consults were not significantly different comparing hybrid care versus standard care. Non-nephrology hospital providers and telenephrologists had favorable opinions of telenephrology and most perceived it is as safe and effective as standard care. PODCAST: This article contains a podcast at https://www.asn-online.org/media/podcast/CJASN/2022_04_11_CJN13441021.mp3.

A hybrid model to identify fall occurrence from electronic health records.

INTRODUCTION: Falls are a leading cause of unintentional injury in the elderly. Electronic health records (EHRs) offer the unique opportunity to develop models that can identify fall events. However, identifying fall events in clinical notes requires advanced natural language processing (NLP) to simultaneously address multiple issues because the word "fall" is a typical homonym. METHODS: We implemented a context-aware language model, Bidirectional Encoder Representations from Transformers (BERT) to identify falls from the EHR text and further fused the BERT model into a hybrid architecture coupled with post-hoc heuristic rules to enhance the performance. The models were evaluated on real world EHR data and were compared to conventional rule-based and deep learning models (CNN and Bi-LSTM). To better understand the ability of each approach to identify falls, we further categorize fall-related concepts (i.e., risk of fall, prevention of fall, homonym) and performed a detailed error analysis. RESULTS: The hybrid model achieved the highest f1-score on sentence (0.971), document (0.985), and patient (0.954) level. At the sentence level (basic data unit in the model), the hybrid model had 0.954, 1.000, 0.988, and 0.999 in sensitivity, specificity, positive predictive value, and negative predictive value, respectively. The error analysis showed that that machine learning-based approaches demonstrated higher performance than a rule-based approach in challenging cases that required contextual understanding. The context-aware language model (BERT) slightly outperformed the word embedding approach trained on Bi-LSTM. No single model yielded the best performance for all fall-related semantic categories. CONCLUSION: A context-aware language model (BERT) was able to identify challenging fall events that requires context understanding in EHR free text. The hybrid model combined with post-hoc rules allowed a custom fix on the BERT outcomes and further improved the performance of fall detection.

Telehealth Use and Hospital Readmission Rates in Long-term Care Facilities in Southeastern Minnesota During the COVID-19 Pandemic.

Objective: To determine whether the length of a telehealth visit predicted the risk of hospital readmission at 30 days in skilled nursing facilities (SNFs) in southeastern Minnesota during the coronavirus disease 2019 pandemic. Patients and Methods: This was a retrospective cohort study conducted in SNFs located in southeastern Minnesota from March 1, 2020 through July 15, 2020. The primary outcomes included hospitalization within 30 days of a video visit, and the secondary outcome was the number of provider video visits during the stay at an SNF. The primary predictor was the duration of video visits, and we collected the data regarding other known predictors of hospitalization. We used the χ2 test for categorical variables and multivariate conditional logistic regression. Results: We included 722 patients (mean age, 82.8 years [SD, 10.8 years]). Of those, 76 SNF residents (10.5%) were rehospitalized within 30 days. The average length of a video visit was 34.0 minutes (SD, 22.7 minutes) in admitted residents compared with 30.0 minutes (SD, 15.9 minutes) in nonadmitted residents. After full adjustment, there was no difference in the video visit duration between admitted and nonadmitted residents (odds ratio, 1.01; 95% CI, 0.99-1.03). The number of subsequent provider video visits was 2.26 (SD, 1.9) in admitted residents vs 1.58 (SD, 1.6), which was significant after adjustment (odds ratio, 1.17; 95% CI, 1.02-1.34). Conclusion: There was no difference in the length of video visits for hospitalized SNF residents vs those who were not hospitalized within 30 days of a video visit. There were more visits in residents with hospital readmission. This may reflect the acuity of care for patients requiring a hospital stay. More research is needed to determine the ideal use of telehealth during the coronavirus disease 2019 pandemic in the postacute and long-term care environment.

The Impact of Frailty on Technique Failure and Mortality in Patients on Home Dialysis.

Background:Patients on home dialysis therapies experience technique failure, which is associated with morbidity and mortality. Reasons for technique failure are complex, and often related to functional decline in the patient or caregiver. Frailty is associated with an increased risk of adverse health outcomes. We investigated the impact of frailty on technique failure and mortality in a prospective cohort of patients on home dialysis therapies.Methods:We collected objective (Fried criteria and Short Physical Performance Battery [SPPB]), and subjective (physician and nurse impression) measures of frailty from 109 prevalent home dialysis patients. Our primary outcome was a composite of technique failure, defined as a permanent unplanned transition (> 30 days in duration) to facility-based hemodialysis or all-cause death. The association between different frailty assessment tools and the primary composite outcome was evaluated using Cox models.Results:Fried criteria and physician impression was associated with a greater than 2-fold increase in risk of our composite outcome (HR: 2.10 [95% CI 1.09 - 3.99], 2.15 [95% CI 1.15 - 4.00, respectively] in adjusted analyses. Weakness and weight loss subdomains of the Fried criteria were both associated with an increased risk of our composite outcome in adjusted analyses (HR: 2.16 [95% CI 1.23 - 3.78], 2.69 [95% CI 1.39 - 5.40], respectively).Conclusions:Objective and subjective measures of frailty are associated with a more than 2-fold higher risk of technique failure or death in patients undergoing home dialysis. Assessing frailty as part of the clinical evaluation for home dialysis therapies may be useful for prognostication and clinical management.

Impact of a palliative care consult service.

Established hospital palliative care consult services (PCCS) have been associated with reduced costs and length of stay, decreased symptom burden, and increased satisfaction with care. Using a retrospective case-control design, we analyzed administrative data of patients seen by PCCS while hospitalized at the Rochester, Minnesota Mayo Clinic hospitals from 2003 to 2008. The PCCS patients were matched to 3:1. A total of 1477 patients seen by the PCCS were matched with 4431 patients not seen. Costs for patients seen and discharged alive were US $35,449 (95% confidence interval [CI] US $34,157-US $36,686) compared to US $37,447 (95% CI US $36,734-US $38,126), without PCCS consultation. Costs for PCCS patients that died during hospitalization were US $54,940 (95% CI US $51,483-US $58,576) and non-PCCS patients were US $79,660 (95% CI US $76,614-US $83,398).