Spinal specific lexicon for sentiment analysis of adult spinal deformity patient interviews correlate with SRS22, SF36, and ODI scores: a pilot study of 25 patients

Classic health-related quality of life (HRQOL) metrics are cumbersome, time intensive, and carry biases based on the subject’s native language, educational level, and cultural values. Natural language processing (NLP) converts text into quantitative metrics. Sentiment analysis enables subject matter experts to construct domain specific lexicons to assign a value that is either negative (-1) or positive (1) to certain words. The growth of tele-health provides opportunities to apply sentiment analysis to transcripts of adult spinal deformity patient visits to derive a novel and less biased HRQOL metric. Here, we demonstrate the feasibility of constructing a spine specific lexicon for sentiment analysis to derive a HRQOL metric for an adult spinal deformity patient from the transcript of their preoperative tele-health visit. We ask 7 open ended questions about the spinal conditions, treatment and quality of life of twenty five (25) adult patients during tele-health visits. We analyze the Pearson correlation among our sentiment analysis HRQOL metric and established HRQOL metrics (SRS22, SF36, and ODI). The results show statistically significant correlations between (0.43 – 0.74) between our sentiment analysis metric and the conventional metrics. This provides evidence that applying NLP techniques to patient transcripts can yield effective HRQOL metrics. These materials, and source code support this study.

传统的与健康相关的生命质量（HRQOL）指标繁琐复杂，耗时费力，且受受试者母语、教育水平和文化价值观的影响而存在偏见。自然语言处理（NLP）技术将文本转换为量化指标。情感分析使领域专家能够构建特定领域的词汇表，对某些词语赋予负（-1）或正（1）的数值。远程医疗的兴起为将情感分析应用于成年脊柱畸形患者的就诊记录提供了机遇，以推导出一种新颖且较少受偏见的HRQOL指标。在本研究中，我们展示了构建脊柱专用词汇表进行情感分析，以从患者术前远程医疗就诊记录中推导出成年脊柱畸形患者HRQOL指标的可能性。我们对25名成年患者在远程医疗就诊期间关于脊柱状况、治疗和生命质量进行了7个开放式问题的调查。我们分析了我们的情感分析HRQOL指标与已建立HRQOL指标（SRS22、SF36和ODI）之间的皮尔逊相关系数。结果显示，我们的情感分析指标与常规指标之间存在统计学上显著的关联性，相关系数介于0.43至0.74之间。这为将NLP技术应用于患者记录以推导有效HRQOL指标提供了证据。这些材料和源代码支持本研究的进行。