Automated Knowledge Modeling for Cancer Clinical Practice Guidelines.

Clinical Practice Guidelines (CPGs) for cancer diseases evolve rapidly due to new evidence generated by active research. Currently, CPGs are primarily published in a document format that is ill-suited for managing this developing knowledge. A knowledge model of the guidelines document suitable for programmatic interaction is required. This work proposes an automated method for extraction of knowledge from National Comprehensive Cancer Network (NCCN) CPGs in Oncology and generating a structured model containing the retrieved knowledge. The proposed method was tested using two versions of NCCN Non-Small Cell Lung Cancer (NSCLC) CPG to demonstrate the effectiveness in faithful extraction and modeling of knowledge. Three enrichment strategies using Cancer staging information, Unified Medical Language System (UMLS) Metathesaurus & National Cancer Institute thesaurus (NCIt) concepts, and Node classification are also presented to enhance the model towards enabling programmatic traversal and querying of cancer care guidelines. The Node classification was performed using a Support Vector Machine (SVM) model, achieving a classification accuracy of 0.81 with 10-fold cross-validation.

Impact of COVID-19 Pandemic on Utilization of the Inpatient Hospice Services (General Inpatient Hospice).

Background: Our institution has been offering the General inpatient hospice (GIP) services within the premises of our hospital since 2013. Our previous data had suggested increased acceptance of hospice and GIP care with this model. We wanted to study the impact of the current COVID-19 pandemic, on utilization of Hospice with this model of care.Objectives: Compare utilization of GIP at HUMC during the first COVID-19 surge, (3/1/2020-6/30/2020) to pre-COVID period (11/1/2019-2/29/2020).Methods: Using a retrospective chart review was done for GIP admissions from 11/2019 to 6/2020 at Hackensack University Medical Center (HUMC), an academic hospital in New Jersey which was approved by HUMC institutional review board. Data was collected for demographics and comorbidities. Descriptive statistics were reported. Results: The primary findings show increased hospice referrals during the study period (3.02%) compared to the pre-covid time period (2.63%), P = .0592. Furthermore, GIP admissions increased from 122/13 440 (.91%) in the pre-covid period to 146/11 480 (1.27%) during covid, P = .0055. There were 54 patients admitted to GIP with COVID-19. Descriptive statistics showed male and female distribution was almost equal (53.70% vs. 46.30%), and mean age of 82 years. In GIP patients with COVID-19, majority patients were white patients, (66.67%) age group of 76-95 years old and had < 3 comorbidities (85.19%), about half were with hypertension, next chronic condition was diabetes.Conclusions: COVID-19 outbreak increased both hospice referral and admission in our model of care. Availability of GIP in the hospital setting may help acceptance and facilitation of these essential end-of-life care services.