Prognosis Prediction Models and their Clinical Utility in Palliative Care

Abstract

Prognosis prediction is a clinically relevant issue to facilitate optimal decision-making for both physicians and patients with cancer. Many previous studies revealed that prognosis prediction based on the physician's intuition and/or clinical experience is inaccurate and often optimistic, which means that there is a tendency to overestimate patient survival in daily clinical practice. In recent decades, many eforts have been made to develop prognosis prediction models which aid physicians to make more accurate prognosis prediction. In this chapter, we review the representative prognosis prediction models in palliative care and related studies. In addition, we refer to several prognosis prediction models developed by unique methods (for instance, case-crossover design or machine learning). Finally, we focus on the possible clinical utility of prognosis prediction models. In fact, no previous studies have clearly demonstrated whether the application of such prognosis prediction models truly beneits patient care in daily clinical practice.Therefore, we will discuss how the application of prognosis prediction models could beneit patients under palliative care.

Applicability of Machine Learning towards development of Patient Centered Decision Support System to Palliative Care Settings

“…Hence predicting the prognosis is vital for improved end of life care. Clinical Prediction of survival is based on the specific clinician and is a subjective opinion and hence it is important to develop objective prognosis prediction models using prognostic factors which include symptom and laboratory data [11].…”

“…Healthcare data that is routinely collected provides increasing opportunities for valuable insights to be obtained using Artificial Intelligence techniques and data driven methods [74]. Research studies have shown that incorporating AI into health care has helped provide for less aggressive care in ICU admissions, administering a ventilator or resuscitation procedure at end of life [11][75] [76] [77]. Applications of Machine Learning in pain care research are limited due to the availability of data.…”

Communication with Families in the Last Days of a Patient’s Life and Optimal Delivery of a Death Pronouncement

“…Several userfriendly clinical tools have been developed in previous studies, such as the palliative prognostic score, the palliative prognostic index, and prognostic in palliative care study predictor models [49][50][51]. Detailed discussion regarding this topic is described elsewhere [52].…”