Power and perils of prediction in palliative care

Porter, Amy S.; Harman, Stephanie; Lakin, Joshua R.

doi:10.1016/s0140-6736(20)30318-4

Cited by 12 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Assistive devices [39][40][41] 4. eHealth [42,43] 5. Design and equipment of accommodation spaces customised to the needs of older people [25,[27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42][43][44][45][46] Reumatologia 2021; 59/1 the practical methods of using innovations, arising from the development of artificial intelligence techniques, in everyday life.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Smart homes for the older population: particularly important during the COVID-19 outbreak

Gawrońska¹,

Lorkowski²

2021

Reumatologia

View full text Add to dashboard Cite

Osteoporosis, one of the leading causes of disability in older adults, significantly reduces the quality of life and leads to loss of independence. Dynamic development of “smart” solutions based on artificial intelligence more and more commonly applied in older people’s houses may be an answer to the above issues. The aim of this study is to present selected “smart home” solutions for the diagnosis and prevention of falls in the older population through a literature review. The conducted meta-analysis based on a review of the scientific literature available in English and Polish in the Medline/PubMed, Embase, Scopus, and GBL databases was undertaken from 01.01.2015 to 01.10.2020 with the string search method using key words. According to the authors of this study, the development of new technology based on artificial intelligence allows older people to live independently, which contributes to a higher level of life satisfaction and quality.

show abstract

Section: Resultsmentioning

confidence: 99%

“…In the literature examined, attention is drawn to the wide application of new technology to predict and identify falls. It shows that machine learning algorithms and a predictive approach are perfectly suited to the fall detection systems [29,30]. The algorithms rely on individualized wearable sensors, ambient sensors, e.g.…”

Section: Discussionmentioning

confidence: 99%

Smart homes for the older population: particularly important during the COVID-19 outbreak

Gawrońska¹,

Lorkowski²

2021

Reumatologia

View full text Add to dashboard Cite

show abstract

“…More concerningly, those who do not usually benefit may be further marginalized. [7] Prediction models are often evaluated in biased conditions [41] and rarely compared against routine clinical decisionmaking. [42] Clinical utility metrics -like an intention-to-treat estimator, [10] the NB, [15] or the NNB [16] -allow for patient-centered comparisons of prediction models with more appropriate assumptions.…”

Section: Discussionmentioning

confidence: 99%

“…Conceptually, alerts would suggest discussing GOC, including CPR preferences, if appropriate. [7] The system would generate alerts after midnight for eligible patients admitted the previous day having a predicted risk greater or equal to a certain decisional threshold. Since intervention harm was minimal and time constraints were known to limit GOC discussions, [2,6] we considered the proportion of admissions with an alert, P(Alert), to be the most appropriate criteria for setting model thresholds.…”

Section: Alternative Strategiesmentioning

confidence: 99%

“…[6] Clinical decision support systems (CDSS) that integrate automated prediction models may help increase the prevalence of GOC discussions by generating computerized alerts for patients with a high risk of mortality. [2,7] The rationale is that physicians, when explicitly alerted to the poor prognosis of a patient in their care, will initiate a discussion about GOC if one is appropriate and has not already occurred.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Clinical Utility of Automatable Prediction Models for Improving Palliative and End-Of-Life Care Outcomes: Towards Routine Decision Analysis Before Implementation

Taseen

Éthier

2021

Preprint

View full text Add to dashboard Cite

Objective To evaluate the clinical utility of automatable prediction models for increasing goals-of-care discussions among hospitalized patients at the end-of-life. Materials and Methods We developed three Random Forest (RF) models and updated the Modified Hospital One-year Mortality Risk model: alternative models to predict one-year mortality (proxy for EOL status) using admission-time data. Admissions from July 2011-2016 were used for training and those from July 2017-2018 were used for temporal validation. We simulated alerts for admissions in the validation cohort and modelled alternative scenarios where alerts lead to code status orders (CSOs) in the EHR. We linked actual CSOs and calculated the expected risk difference (eRD), the number needed to benefit (NNB) and the net benefit (NB) of each model for the patient-centered outcome of a CSO among EOL hospitalizations. Results Models had a C-statistic of 0.79-0.86 among unique patients. A CSO was documented during 2599 of 3773 hospitalizations at the EOL (68.9%). At a threshold that identified 10% of eligible admissions, the eRD ranged from 5.4% to 10.7% (NNB 5.4-10.9 alerts). Under usual care, a CSO had a 34% PPV for EOL status. Using this to inform the relative cost of FPs, only two models improved NB over usual care. A RF model with diagnostic predictors had the highest clinical utility by either measure, including in sensitivity analyses. Discussion Automatable prediction models with acceptable temporal validity differed meaningfully in their expected ability to improve patient-centered outcomes over usual care. Conclusion Decision-analysis should precede implementation of automated prediction models for improving palliative and EOL care outcomes.

show abstract

Palliative Care Exposure Relative to Predicted Risk of Six-Month Mortality in Hospitalized Adults

Agarwal¹,

Domenico²,

Balla³

et al. 2022

Journal of Pain and Symptom Management

View full text Add to dashboard Cite

Power and perils of prediction in palliative care

Cited by 12 publications

References 9 publications

Smart homes for the older population: particularly important during the COVID-19 outbreak

Smart homes for the older population: particularly important during the COVID-19 outbreak

Clinical Utility of Automatable Prediction Models for Improving Palliative and End-Of-Life Care Outcomes: Towards Routine Decision Analysis Before Implementation

Palliative Care Exposure Relative to Predicted Risk of Six-Month Mortality in Hospitalized Adults

Contact Info

Product

Resources

About