Clinician Accuracy When Estimating Survival Duration: The Role of the Patient's Performance Status and Time-Based Prognostic Categories

Selby, Debbie; Chakraborty, Anita; Lilien, Tammy; Stacey, Erica; Zhang, Liying; Myers, Jeff

doi:10.1016/j.jpainsymman.2011.01.012

Cited by 50 publications

(40 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have shown that clinicians are generally over optimistic in their estimates of the prognoses of terminally ill patients [9] [5] [10] [11]. It has also been shown that no subset of clinicians are better at late stage prognostication than than others [12] [13] .…”

Section: Related Workmentioning

confidence: 99%

Improving palliative care with deep learning

Avati

Jung

Harman

et al. 2017

2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

114

102

View full text Add to dashboard Cite

Abstract-Improving the quality of end-of-life care for hospitalized patients is a priority for healthcare organizations. Studies have shown that physicians tend to over-estimate prognoses, which in combination with treatment inertia results in a mismatch between patients wishes and actual care at the end of life . We describe a method to address this problem using Deep Learning and Electronic Health Record (EHR) data, which is currently being piloted, with Institutional Review Board approval, at an academic medical center. The EHR data of admitted patients are automatically evaluated by an algorithm, which brings patients who are likely to benefit from palliative care services to the attention of the Palliative Care team. The algorithm is a Deep Neural Network trained on the EHR data from previous years, to predict all-cause 3-12 month mortality of patients as a proxy for patients that could benefit from palliative care. Our predictions enable the Palliative Care team to take a proactive approach in reaching out to such patients, rather than relying on referrals from treating physicians, or conduct time consuming chart reviews of all patients. We also present a novel interpretation technique which we use to provide explanations of the model's predictions.

show abstract

Section: Related Workmentioning

confidence: 99%

Improving palliative care with deep learning

Avati

Jung

Harman

et al. 2017

2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

114

102

View full text Add to dashboard Cite

show abstract

“…[1][2][3][4][5][6][7] Often, patients are not recognized as actively or imminently dying, 1,[8][9][10][11][12][13][14] and their suffering may be exacerbated by usual medical care, in which intensive or iatrogenically harmful treatments frequently are continued. [15][16][17][18] During this time, palliative care treatment plans can be implemented, in place of or in addition to existing care plans, to reduce suffering and improve end-of-life care.…”

Section: Introductionmentioning

confidence: 99%

Intervention to Improve Care at Life’s End in Inpatient Settings: The BEACON Trial

et al. 2014

View full text Add to dashboard Cite

BACKGROUND: Widespread implementation of palliative care treatment plans could reduce suffering in the last days of life by adopting best practices of traditionally home-based hospice care in inpatient settings. OBJECTIVE: To evaluate the effectiveness of a multimodal intervention strategy to improve processes of end-of-life care in inpatient settings. DESIGN: Implementation trial with an intervention staggered across hospitals using a multiple-baseline, stepped wedge design. PARTICIPANTS: Six Veterans Affairs Medical Centers (VAMCs). INTERVENTION: Staff training was targeted to all hospital providers and focused on identifying actively dying patients and implementing best practices from home-based hospice care, supported with an electronic order set and paper-based educational tools. MAIN MEASURES: Several processes of care were identified as quality endpoints for end-of-life care (last 7 days) and abstracted from electronic medical records of veterans who died before or after intervention (n= 6,066). Primary endpoints were proportion with an order for opioid pain medication at time of death, donot-resuscitate order, location of death, nasogastric tube, intravenous line infusing, and physical restraints. Secondary endpoints were administration of opioids, order/administration of antipsychotics, benzodiazepines, and scopolamine (for death rattle); sublingual administration; advance directives; palliative care consultations; and pastoral care services. Generalized estimating equations were conducted adjusting for longitudinal trends. KEY RESULTS: Significant intervention effects were observed for orders for opioid pain medication (OR:

show abstract

“…5 Fox and coworkers found that a majority of noncancer patients meeting hospice criteria survived beyond the expected 6-month prognosis. 6 On the other hand, one recent study has found that cancer and noncancer patients referred to a palliative care service were equally likely to defy their prognosis, 13 although this latter study used specialist palliative care physicians to assess prognosis.…”

Section: Discussionmentioning

confidence: 97%

“…We measured correlations between LOS and patient characteristics using Pearson's test. To perform multivariable regression analyses, we grouped PPS scores into low (10)(11)(12)(13)(14)(15)(16)(17)(18)(19)(20), medium (30-40) and high (50 + ). 8 We constructed a multivariable regression model for LOS that included age and gender, as well as all factors that correlated with LOS on bivariate analysis with a p < 0.05 (the PPS and prognostic categories as well as a cancer diagnosis).…”

Section: Data Collection and Analysismentioning

confidence: 99%

Survival Duration among Patients with a Noncancer Diagnosis Admitted to a Palliative Care Unit: A Retrospective Study

Downar

Chou²,

Ouellet³

et al. 2012

Journal of Palliative Medicine

View full text Add to dashboard Cite

Noncancer patients have a shorter LOS than cancer patients and a similar likelihood of being discharged alive from a PCU than cancer patients, and the diagnosis of cancer did not correlate with survival in our study population. Our findings demonstrate that noncancer patients are not "oversurviving," and that referring physicians and PCUs should not reject or restrict noncancer referrals out of concern that these patients are having a detrimental impact on PCU bed availability.

show abstract

Clinician Accuracy When Estimating Survival Duration: The Role of the Patient's Performance Status and Time-Based Prognostic Categories

Cited by 50 publications

References 33 publications

Improving palliative care with deep learning

Improving palliative care with deep learning

Intervention to Improve Care at Life’s End in Inpatient Settings: The BEACON Trial

Survival Duration among Patients with a Noncancer Diagnosis Admitted to a Palliative Care Unit: A Retrospective Study

Contact Info

Product

Resources

About