Machine Learning Identifies Variation in Timing of Palliative Care Consultations Among Traumatic Brain Injury Patients

Background and Objective Timely palliative care involvement offers demonstrable benefits for traumatic brain injury (TBI) patients; however, palliative care consultations (PCCs) are used inconsistently during TBI management. This study aimed to employ advanced machine learning techniques to elucidate the primary drivers of PCC timing variability for TBI patients. Methods Data on admission, hospital course, and outcomes were collected for a cohort of 232 TBI patients who received both PCCs and neurosurgical consultations during the same hospitalization. Principal Component Analysis (PCA) and K-means clustering were used to identify patient phenotypes, which were then compared using Kaplan-Meier analysis. An extreme gradient boosting model (XGBoost) was employed to determine drivers of PCC timing, with model interpretation performed using SHapley Additive exPlanations (SHAP). Results Cluster A (n = 86) consisted mainly of older (median [IQR] = 87 [78, 94] years), White females with mild TBIs and demonstrated the shortest time-to-PCC (2.5 [1.0, 7.0] days). Cluster B (n = 108) also sustained mild TBIs but comprised moderately younger (81 [75, 86] years) married White males with later PCC (5.0 [3.0, 10.8] days). Cluster C (n = 38) represented much younger (46.5 [29.5, 59.8] years), more severely injured, non-White patients with the latest PCC initiation (9.0 [4.2, 17.0] days). The clusters did not differ by discharge disposition (p = 0.4) or frequency inpatient mortality (p > 0.9); however, Kaplan-Meier analysis revealed a significant difference in the time from admission to PCC (p < 0.001), despite no differences in time from admission to mortality (p = 0.18). SHAP analysis of the XGBoost model identified age, sex, and race as the most influential drivers of PCC timing. Conclusions This study highlights crucial disparities in PCC timing for TBI patients and underscores the need for targeted strategies to ensure timely and equitable palliative care integration for this vulnerable population.

The Relevance of State Laws Regulating Opioid Prescribing for People Living With Serious Illness

CONTEXT

Opioids are commonly used to relieve symptoms such as pain and dyspnea in people living with serious illness. In recent years, 36 states enacted limitations for opioid prescriptions to mitigate the impact of the opioid overdose crisis. Palliative care clinicians have been vocal about the unintended consequences of opioid policies, yet little is known about how state policies apply to opioid prescribing in non-cancer-related serious illness.

OBJECTIVE

To summarize current state-level limitations to opioid prescribing and exemptions relevant to people living with non-cancer-related serious illness.

METHODS

Investigators searched publicly available laws ("[state] + opioid legislation") to extract information on opioid prescribing and exemptions. Laws were examined for application to palliative care, hospice, non-cancer-related serious illness, and language about specific symptoms was documented when applicable (e.g., pain, dyspnea).

RESULTS

Most state laws focused on acute pain and/or initial opioid prescriptions. Thirty-three of the thirty-six states with opioid-limiting legislation exempt situations applicable to people living with non-cancer-related serious illness. Three states did not have any exemptions relevant to people living with non-cancer-related serious illness.

DISCUSSION

The results indicate that while most states recognize the importance of timely opioid access for palliation of pain, clinically relevant exemptions for people living with non-cancer-related serious illness may be lacking. When present, language describing palliative care, hospice, and terminal illness exemptions is often broad and may generate confusion between primary and specialty palliative care.

"I'm Dealing With That": Illness Concerns of African American and White Cancer Patients While Undergoing Active Cancer Treatments

BACKGROUND

National oncology guidelines recommend early integration of palliative care for patients with cancer. However, drivers for this integration remain understudied. Understanding illness concerns at the time of cancer treatment may help facilitate integration earlier in the cancer illness trajectory.

OBJECTIVE

To describe cancer patients' concerns while undergoing cancer treatment, and determine if concerns differ among African Americans and Whites.

METHODS

A 1-time, semi-structured qualitative interview was conducted with a purposive subsample of cancer patients participating in a larger study of illness concerns. Eligible patients were undergoing cancer treatments and had self-reported moderate-to-severe pain in the last week. Analysis encompassed a qualitative descriptive approach with inductive thematic analysis.

RESULTS

Participants (16 African American, 16 White) had a median age of 53 and were predominantly females (72%) with stage III/IV cancer (53%). Illness concerns were largely consistent across participants and converged on 3 themes: symptom experience (pain, options to manage pain), cancer care delivery (communication, care coordination and care transitions), and practical concerns (access to community and health system resources, financial toxicity).

CONCLUSIONS

The findings extend the scope of factors that could be utilized to integrate palliative care earlier in the cancer illness trajectory, moving beyond the symptoms- and prognosis-based triggers that typify current referrals to also consider diverse logistical concerns. Using this larger set of concerns aids anticipatory risk mitigation and planning (e.g. care transitions, financial toxicity), helps patients receive a larger complement of support services, and builds cancer patients' capacity toward a more patient-centered treatment and care experience.