Scholarlink

Background <p>Physician compassion is associated with improvement in a variety of patient outcomes, but it remains unclear which individual physician behaviors affect patients’ experience of compassion.</p> Objective <p>To determine which physician behaviors are most associated with patients’ experience of compassion.</p> Design <p>We conducted a cross-sectional study at two urban academic emergency departments (ED) from September 2023 to May 2024. Participants completed questionnaires with a previously validated 5-item compassion measure and questions about whether the patient’s physician exhibited any of 27 behaviors previously proposed to be associated with compassion.</p> Participants <p>We enrolled adult (age 18&#xa0;years or older) patients presenting to each ED.</p> Main Measures <p>The primary outcome was patient experience of physician compassion using the 5-item compassion measure. We used the machine learning algorithm LASSO to identify the group of actions that best predict the 5-item compassion measure. We performed exploratory analyses using linear regression with interaction terms to test for differences by patient race (White vs Black) and gender.</p> Results <p>A total of 1025 patients completed the questionnaire (717 from site 1; 308 from site 2). The action with the strongest association with greater compassion was “Listen carefully to what you had to say” [β = 5.67 (95% CI 3.36 to 7.98)]. The LASSO algorithm identified nine actions as the best predictors, and this model explained roughly a third of variation in compassion scores: <i>r</i><sup>2</sup> = 0.34 in the derivation cohort and <i>r</i><sup>2</sup> = 0.32 in the validation cohort. Three behaviors had a stronger association with compassion scores among women (compared to men) and five behaviors among Black (compared to White) individuals.</p> Conclusions&#xa0;and Relevance <p>These results show specific physician behaviors are associated with patients’ experience of compassion. Further research is needed to develop interventions to foster these behaviors and test prospectively whether they improve patients’ experience of compassion.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine Learning to Identify Physician Actions Associated with Patient Experience of Compassion

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月21日

查看全文
  • Clifford M. Marks,
  • Patrice Baptista,
  • Cameron Gaines,
  • Christopher W. Jones,
  • Lauren Remboski,
  • Andrew Nyce,
  • Amanda M. Scudder,
  • Adrian D. Haimovich,
  • Nathan I. Shapiro,
  • Stephen Trzeciak,
  • Brian W. Roberts

摘要

Background

Physician compassion is associated with improvement in a variety of patient outcomes, but it remains unclear which individual physician behaviors affect patients’ experience of compassion.

Objective

To determine which physician behaviors are most associated with patients’ experience of compassion.

Design

We conducted a cross-sectional study at two urban academic emergency departments (ED) from September 2023 to May 2024. Participants completed questionnaires with a previously validated 5-item compassion measure and questions about whether the patient’s physician exhibited any of 27 behaviors previously proposed to be associated with compassion.

Participants

We enrolled adult (age 18 years or older) patients presenting to each ED.

Main Measures

The primary outcome was patient experience of physician compassion using the 5-item compassion measure. We used the machine learning algorithm LASSO to identify the group of actions that best predict the 5-item compassion measure. We performed exploratory analyses using linear regression with interaction terms to test for differences by patient race (White vs Black) and gender.

Results

A total of 1025 patients completed the questionnaire (717 from site 1; 308 from site 2). The action with the strongest association with greater compassion was “Listen carefully to what you had to say” [β = 5.67 (95% CI 3.36 to 7.98)]. The LASSO algorithm identified nine actions as the best predictors, and this model explained roughly a third of variation in compassion scores: r2 = 0.34 in the derivation cohort and r2 = 0.32 in the validation cohort. Three behaviors had a stronger association with compassion scores among women (compared to men) and five behaviors among Black (compared to White) individuals.

Conclusions and Relevance

These results show specific physician behaviors are associated with patients’ experience of compassion. Further research is needed to develop interventions to foster these behaviors and test prospectively whether they improve patients’ experience of compassion.