Development of a Risk Tool to Support Discussions of Care for Older Adults Admitted to the ICU With Pneumonia

2018 ◽  
Vol 35 (9) ◽  
pp. 1201-1206
Author(s):  
Nikhil Satchidanand ◽  
Timothy J. Servoss ◽  
Ranjit Singh ◽  
Angela M. Bosinski ◽  
Penny Tirpak ◽  
...  
Keyword(s):  
New York ◽  
Palliative Care ◽  
Care Delivery ◽  
External Validation ◽  
Mortality Prediction ◽  
Receiver Operating Curve ◽  
Mortality Data ◽  
Chronic Obstructive ◽  
Hospital System ◽  
Predicted Probability

Background: Early, data-driven discussion surrounding palliative care can improve care delivery and patient experience. Objective: To develop a 30-day mortality prediction tool for older patients in intensive care unit (ICU) with pneumonia that will initiate palliative care earlier in hospital course. Design: Retrospective Electronic Health Record (EHR) review. Setting: Four urban and suburban hospitals in a Western New York hospital system. Participants: A total of 1237 consecutive patients (>75 years) admitted to the ICU with pneumonia from July 2011 to December 2014. Measurements: Data abstracted included demographics, insurance type, comorbidities, and clinical factors. Thirty-day mortality was also determined. Logistic regression identified predictors of 30-day mortality. Area under the receiver operating curve (ROC) was calculated to quantify the degree to which the model accurately classified participants. Using the coordinates of the ROC, a predicted probability was identified to indicate high risk. Results: A total of 1237 patients were included with 30-day mortality data available for 100% of patients. The mortality rate equaled 14.3%. Age >85 years, having active cancer, Congestive Heart Failure (CHF), Chronic Obstructive Pulmonary Disease (COPD), sepsis, and being on a vasopressor all predicted mortality. Using the derived index, with a predicted probability of mortality >0.146 as a cutoff, sensitivity equaled 70.6% and specificity equaled 65.6%. The area under the ROC was 0.735. Conclusion: Our risk tool can help care teams make more informed decisions among care options by identifying a patient group for whom a careful review of goals of care is indicated both during and after hospitalization. External validation and further refinement of the index with a larger sample will improve prognostic value.

scholarly journals Vital signs assessed in initial clinical encounters predict COVID-19 mortality in an NYC hospital system

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Elza Rechtman ◽  
Paul Curtin ◽  
Esmeralda Navarro ◽  
Sharon Nirenberg ◽  
Megan K. Horton
Keyword(s):  
Machine Learning ◽  
New York ◽  
Clinical Decision Making ◽  
Care Delivery ◽  
Vital Signs ◽  
Clinical Decision ◽  
Rapid Identification ◽  
Gradient Boosting ◽  
Hospital System ◽  
Response Strategies

AbstractTimely and effective clinical decision-making for COVID-19 requires rapid identification of risk factors for disease outcomes. Our objective was to identify characteristics available immediately upon first clinical evaluation related COVID-19 mortality. We conducted a retrospective study of 8770 laboratory-confirmed cases of SARS-CoV-2 from a network of 53 facilities in New-York City. We analysed 3 classes of variables; demographic, clinical, and comorbid factors, in a two-tiered analysis that included traditional regression strategies and machine learning. COVID-19 mortality was 12.7%. Logistic regression identified older age (OR, 1.69 [95% CI 1.66–1.92]), male sex (OR, 1.57 [95% CI 1.30–1.90]), higher BMI (OR, 1.03 [95% CI 1.102–1.05]), higher heart rate (OR, 1.01 [95% CI 1.00–1.01]), higher respiratory rate (OR, 1.05 [95% CI 1.03–1.07]), lower oxygen saturation (OR, 0.94 [95% CI 0.93–0.96]), and chronic kidney disease (OR, 1.53 [95% CI 1.20–1.95]) were associated with COVID-19 mortality. Using gradient-boosting machine learning, these factors predicted COVID-19 related mortality (AUC = 0.86) following cross-validation in a training set. Immediate, objective and culturally generalizable measures accessible upon clinical presentation are effective predictors of COVID-19 outcome. These findings may inform rapid response strategies to optimize health care delivery in parts of the world who have not yet confronted this epidemic, as well as in those forecasting a possible second outbreak.

Longer Duration of Palliative Care in Patients With COPD Is Associated With Death Outside the Hospital

2019 ◽  
pp. 082585971985148
Author(s):  
Valeri Kraskovsky ◽  
Jaclyn Schneider ◽  
M. Jeffery Mador ◽  
Karin A. Provost
Keyword(s):  
New York ◽  
Palliative Care ◽  
Disease Burden ◽  
Airflow Obstruction ◽  
Symptom Burden ◽  
Retrospective Chart Review ◽  
Forced Expiratory Volume ◽  
Chronic Obstructive ◽  
Comorbid Disease ◽  
Obstructive Pulmonary Disease

Background: Patients with advanced chronic obstructive pulmonary disease (COPD) have a significant symptom burden despite maximal medical therapy, yet few are referred for concomitant palliative care. Objective: To evaluate the utilization and impact of palliative care on the location of death and to identify clinical variables associated with palliative care contact. Design: Retrospective chart review from 2010 to 2016 at the VA Western New York Healthcare System using ICD-9/10 diagnosis of COPD. Palliative care contact was identified by Z51.5 or stop code 353. Results: Only 0.5% to 2% of living patients received palliative care, increasing abruptly at death (6%). Lower diffusion capacity for carbon monoxide (DLCO) (greater emphysema) was associated with palliative care contact, independent of comorbid disease burden or age. Initial outpatient contact was associated with a longer duration of palliative care ( P = .003) and death in a home-like setting. Outpatient palliative care was associated with more severe airflow obstruction (forced expiratory volume in 1 second, percent predicted [FEV1%]), whereas greater disease exacerbation frequency was associated with inpatient contact. COPD patients not referred to palliative care had a greater comorbid disease burden, similar FEV1%, fewer disease exacerbations, and a greater DLCO. Conclusion: Few patients with COPD received palliative care, similar to national trends. Initial outpatient palliative contact had the longest duration of care and death in the preferred home environment. The extent of emphysema (DLCO reduction) and more frequent disease exacerbations identified in patients were more likely to receive palliative care. Our study begins to define the benefits of palliative care in advanced COPD and confirms underutilization in the years before death, where a prolonged impact on the quality of life may be realized.

scholarly journals Can predicting COVID-19 mortality in a European cohort using only demographic and comorbidity data surpass age-based prediction: An externally validated study

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0249920
Author(s):  
Avishek Chatterjee ◽  
Guangyao Wu ◽  
Sergey Primakov ◽  
Cary Oberije ◽  
Henry Woodruff ◽  
...  
Keyword(s):  
Feature Selection ◽  
External Validation ◽  
Mortality Prediction ◽  
Chronic Obstructive ◽  
Selection Methods ◽  
Obstructive Pulmonary Disease ◽  
Training Cohort ◽  
Mortality Prediction Model ◽  
Validation Set ◽  
Vaccine Distribution

Objective To establish whether one can build a mortality prediction model for COVID-19 patients based solely on demographics and comorbidity data that outperforms age alone. Such a model could be a precursor to implementing smart lockdowns and vaccine distribution strategies. Methods The training cohort comprised 2337 COVID-19 inpatients from nine hospitals in The Netherlands. The clinical outcome was death within 21 days of being discharged. The features were derived from electronic health records collected during admission. Three feature selection methods were used: LASSO, univariate using a novel metric, and pairwise (age being half of each pair). 478 patients from Belgium were used to test the model. All modeling attempts were compared against an age-only model. Results In the training cohort, the mortality group’s median age was 77 years (interquartile range = 70–83), higher than the non-mortality group (median = 65, IQR = 55–75). The incidence of former/active smokers, male gender, hypertension, diabetes, dementia, cancer, chronic obstructive pulmonary disease, chronic cardiac disease, chronic neurological disease, and chronic kidney disease was higher in the mortality group. All stated differences were statistically significant after Bonferroni correction. LASSO selected eight features, novel univariate chose five, and pairwise chose none. No model was able to surpass an age-only model in the external validation set, where age had an AUC of 0.85 and a balanced accuracy of 0.77. Conclusion When applied to an external validation set, we found that an age-only mortality model outperformed all modeling attempts (curated on www.covid19risk.ai) using three feature selection methods on 22 demographic and comorbid features.

scholarly journals Vital signs assessed in initial clinical encounters predict COVID-19 mortality in an NYC hospital system

2020 ◽  
Author(s):  
Elza Rechtman ◽  
Paul Curtin ◽  
Esmeralda Navarro ◽  
Sharon Nirenberg ◽  
Megan K Horton
Keyword(s):  
Machine Learning ◽  
New York ◽  
Clinical Decision Making ◽  
Care Delivery ◽  
Vital Signs ◽  
Clinical Decision ◽  
Rapid Identification ◽  
Gradient Boosting ◽  
Hospital System ◽  
Response Strategies

Abstract Timely and effective clinical decision-making for COVID-19 requires rapid identification of risk factors for disease outcomes. Our objective was to identify characteristics available immediately upon first clinical evaluation related COVID-19 mortality. We conducted a retrospective study of 8770 laboratory-confirmed cases of SARS-CoV-2 from a network of 53 facilities in New-York City. We analysed 3 classes of variables; demographic, clinical, and comorbid factors, in a two-tiered analysis that included traditional regression strategies and machine learning. COVID-19 mortality was 12.7%. Logistic regression identified older age (OR, 1.69 [95%CI, 1.66-1.92]), male sex (OR, 1.57 [95%CI, 1.30-1.90]), higher BMI (OR, 1.03 [95%CI, 1.102-1.05]), higher heart rate (OR, 1.01 [95%CI, 1.00-1.01]), higher respiratory rate (OR, 1.05 [95%CI, 1.03-1.07]), lower oxygen saturation (OR, 0.94 [95%CI, 0.93-0.96]), and chronic kidney disease (OR, 1.53 [95%CI, 1.20-1.95]) were associated with COVID-19 mortality. Using gradient-boosting machine learning, these factors predicted COVID-19 related mortality (AUC=0.86) following cross-validation in a training set. Immediate, objective and culturally generalizable measures accessible upon clinical presentation are effective predictors of COVID-19 outcome. These findings may inform rapid response strategies to optimize health care delivery in parts of the world who have not yet confronted this epidemic, as well as in those forecasting a possible second outbreak.

scholarly journals Electrocardiogram-based mortality prediction in patients with COVID-19 using machine learning

EP Europace ◽  
2021 ◽  
Vol 23 (Supplement_3) ◽  
Author(s):  
H Bleijendaal ◽  
RR Van Der Leur ◽  
K Taha ◽  
T Mast ◽  
JMIH Gho ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
The Netherlands ◽  
Hospital Mortality ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Prediction Models ◽  
External Validation ◽  
Mortality Prediction ◽  
Receiver Operating Curve

Abstract Funding Acknowledgements Type of funding sources: Public hospital(s). Main funding source(s): The Netherlands Organisation for Health Research and Development (ZonMw) University of Amsterdam Research Priority Area Medical Integromics OnBehalf CAPACITY-COVID19 Registry Background The electrocardiogram (ECG) is an easy to assess, widely available and inexpensive tool that is frequently used during the work-up of hospitalized COVID-19 patients. So far, no study has been conducted to evaluate if ECG-based machine learning models are able to predict all-cause in-hospital mortality in COVID-19 patients. Purpose With this study, we aim to evaluate the value of using the ECG to predict in-hospital all-cause mortality of COVID-19 patients by analyzing the ECG at hospital admission, comparing a logistic regression based approach and a DNN based approach. Secondly, we aim to identify specific ECG features associated with mortality in patients diagnosed with COVID-19.  Methods and results We studied 882 patients admitted with COVID-19 across seven hospitals in the Netherlands. Raw-format 12-lead ECGs recorded after admission (<72 hours) were collected, manually assessed, and annotated using pre-defined ECG features. Using data from five out of seven centers (n = 634), two mortality prediction models were developed: (a) a logistic regression model using manually annotated ECG features, and (b) a pre-trained deep neural network (DNN) using the raw ECG waveforms. Data from two other centers (n = 248) were used for external validation. Performance of both prediction models was similar, with a mean area under the receiver operating curve of 0.69 [95%CI 0.55–0.82] for the logistic regression model and 0.71 [95%CI 0.59–0.81] for the DNN in the external validation cohort. After adjustment for age and sex, ventricular rate (OR 1.13 [95% CI 1.01–1.27] per 10 ms increase), right bundle branch block (3.26 [95% CI 1.15–9.50]), ST-depression (2.78 [95% CI 1.03–7.70]) and low QRS voltages (3.09 [95% CI 1.02-9.38]) remained as significant predictors for mortality. Conclusion This study shows that ECG-based prediction models at admission may be a valuable addition to the initial risk stratification in admitted COVID-19 patients. The DNN model showed similar performance to the logistic regression that needs time-consuming manual annotation. Several ECG features associated with mortality were identified. Figure 1:  Overview of methods, using and example case: (left) logistic regression and (right) deep learning. This specific case had a high probability of in-hospital mortality (above the threshold of 30%). Follow-up of this case showed that the patient had died during admission. Abstract Figure. Overview of ML methods used

scholarly journals Emergency Medicine Palliative Care Access (EMPallA): protocol for a multicentre randomised controlled trial comparing the effectiveness of specialty outpatient versus nurse-led telephonic palliative care of older adults with advanced illness

BMJ Open ◽  
2019 ◽  
Vol 9 (1) ◽  
pp. e025692 ◽  
Author(s):  
Corita R Grudzen ◽  
Deborah J Shim ◽  
Abigail M Schmucker ◽  
Jeanne Cho ◽  
Keith S Goldfeld
Keyword(s):  
Quality Of Life ◽  
Older Adults ◽  
Palliative Care ◽  
Randomised Controlled Trial ◽  
Case Management ◽  
Controlled Trial ◽  
Chronic Obstructive ◽  
Randomised Controlled ◽  
End Stage

IntroductionEmergency department (ED)-initiated palliative care has been shown to improve patient-centred outcomes in older adults with serious, life-limiting illnesses. However, the optimal modality for providing such interventions is unknown. This study aims to compare nurse-led telephonic case management to specialty outpatient palliative care for older adults with serious, life-limiting illness on: (1) quality of life in patients; (2) healthcare utilisation; (3) loneliness and symptom burden and (4) caregiver strain, caregiver quality of life and bereavement.Methods and analysisThis is a protocol for a pragmatic, multicentre, parallel, two-arm randomised controlled trial in ED patients comparing two established models of palliative care: nurse-led telephonic case management and specialty, outpatient palliative care. We will enrol 1350 patients aged 50+ years and 675 of their caregivers across nine EDs. Eligible patients: (1) have advanced cancer (metastatic solid tumour) or end-stage organ failure (New York Heart Association class III or IV heart failure, end-stage renal disease with glomerular filtration rate <15 mL/min/m2, or global initiative for chronic obstructive lung disease stage III, IV or oxygen-dependent chronic obstructive pulmonary disease); (2) speak English; (3) are scheduled for ED discharge or observation status; (4) reside locally; (5) have a working telephone and (6) are insured. Patients will be excluded if they: (1) have dementia; (2) have received hospice care or two or more palliative care visits in the last 6 months or (3) reside in a long-term care facility. We will use patient-level block randomisation, stratified by ED site and disease. Effectiveness will be compared by measuring the impact of each intervention on the specified outcomes. The primary outcome will measure change in patient quality of life.Ethics and disseminationInstitutional Review Board approval was obtained at all study sites. Trial results will be submitted for publication in a peer-reviewed journal.Trial registration numberNCT03325985; Pre-results.

scholarly journals QOLP-03. NEURO-ONCOLOGY PALLIATIVE CARE SURVEY OF PHYSICIANS IN SUB-SAHARAN AFRICA

2020 ◽  
Vol 22 (Supplement_2) ◽  
pp. ii175-ii175
Author(s):  
Ramya Tadipatri ◽  
Amir Azadi ◽  
Madison Cowdrey ◽  
Samuel Fongue ◽  
Paul Smith ◽  
...  
Keyword(s):  
Palliative Care ◽  
Care Delivery ◽  
Cultural Beliefs ◽  
Oral Feeding ◽  
Statistical Testing ◽  
Sub Saharan Africa ◽  
Neurological Deficits ◽  
Survey Study ◽  
Prior Training ◽  
Sub Saharan

Abstract BACKGROUND Early access to palliative care is a critical component of treating patients with advanced cancer, particularly for glioblastoma patients who have low rates of survival despite optimal therapies. Additionally, there are unique considerations for primary brain tumor patients given the need for management of headaches, seizures, and focal neurological deficits. METHODS We conducted a survey of 109 physicians in Sub-Saharan Africa in order to determine level of understanding and skill in providing palliative care, types of palliative care therapies provided, role of cultural beliefs, availability of resources, and challenges faced. Demographic data including age, gender, and prior training was collected and analyzed using ANOVA statistical testing. RESULTS Among the participants, 48% felt comfortable in providing palliative care consultations, 62% have not had prior training, 52% believed that palliative care is only appropriate when there is irreversible deterioration, 62% expressed having access to palliative care, 49% do not have access to liquid opioid agents, 50% stated that cultural beliefs held by the patient or family prevented them from receiving, palliative care, and 23% stated that their own beliefs affected palliative care delivery. Older providers (age &gt; 30) had a clearer understanding of palliative care (p = 0.004), were more comfortable providing consultation (p = 0.052), and were more likely to address mental health (p &lt; 0.001). CONCLUSIONS Palliative care delivery to glioblastoma patients in Sub-Saharan Africa is often delayed until late in the disease course. Barriers to adequate palliative care treatment identified in this survey study include lack of training, limited access to liquid opioid agents, and cultural beliefs. Challenges most often identified by participants were pain management and end-of-life communication skills, but also included patient spirituality and psychological support, anxiety and depression, terminal dyspnea, ethics, and intravenous hydration and non-oral feeding.

scholarly journals 96 Estimation of palliative care needs of people experiencing homelessness using mortality data and cause-of-death

2021 ◽  
Author(s):  
Aoibheann Conneely ◽  
Jo-Hanna Ivers ◽  
Joe Barry ◽  
Elaine Dunne ◽  
Norma O’Leary ◽  
...  
Keyword(s):  
Palliative Care ◽  
Cause Of Death ◽  
Mortality Data ◽  
Care Needs ◽  
Palliative Care Needs

scholarly journals Preprocedural SARS-CoV-2 Testing to Sustain Medically Needed Health Care Delivery During the COVID-19 Pandemic: A Prospective Observational Study

2021 ◽  
Vol 8 (2) ◽  
Author(s):  
Ghady Haidar ◽  
Ashley Ayres ◽  
Wendy C King ◽  
Mackenzie McDonald ◽  
Alan Wells ◽  
...  
Keyword(s):  
Health Care ◽  
New York ◽  
Prospective Observational Study ◽  
Care Delivery ◽  
Community Hospitals ◽  
Symptom Screening ◽  
Academic Hospitals ◽  
Hospital Patients ◽  
Polymerase Chain ◽  
A Prospective Study

Abstract Background We implemented a preprocedural severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) screening initiative designed to sustain health care during a time when the extent of SARS-CoV-2 infection was unknown. Methods This was a prospective study of patients undergoing procedures at 3 academic hospitals in Pittsburgh, Pennsylvania (April 21–June 11), and 19 community hospitals across Middle/Western Pennsylvania and Southwestern New York (May 1–June 11). Patients at academic hospitals underwent symptom screening ≤7 days preprocedure, then SARS-CoV-2 nasopharyngeal polymerase chain reaction (PCR) testing 1–4 days preprocedure. A subset also underwent day-of-procedure testing. Community hospital patients underwent testing per local protocols. We report SARS-CoV-2 PCR positivity rates, impact, and barriers to testing encountered through June 11. PCR positivity rates of optional preprocedural SARS-CoV-2 testing for 2 consecutive periods following the screening initiative are also reported. Results Of 5881 eligible academic hospital patients, 2415 (41.1%) were tested (April 21–June 11). Lack of interest, distance, self-isolation, and nursing home/incarceration status were barriers. There were 11 PCR-positive patients (10 asymptomatic) among 10 539 patients tested (0.10%; 95% CI, 0.05%–0.19%): 3/2415 (0.12%; 95% CI, 0.02%–0.36%) and 8/8124 (0.10%; 95% CI, 0.04%–0.19%) at academic and community hospitals, respectively. Procedures were performed as scheduled in 40% (4/10) of asymptomatic PCR-positive patients. Positivity increased during subsequent coronavirus disease 2019 (COVID-19) surges: 54/34 948 (0.15%; 95% CI, 0.12%–0.20%) and 101/24 741 (0.41%; 95% CI, 0.33%–0.50%) PCR-positive patients from June 12–September 10 and September 11–December 15, respectively (P &lt; .0001). Conclusions Implementing preprocedural PCR testing was complex and revealed low infection rates (0.24% overall), which increased during COVID-19 surges. Additional studies are needed to define the COVID-19 prevalence threshold at which universal preprocedural screening is warranted.

Sign in / Sign up

Export Citation Format

Share Document