Wardrope Alistair, Ferrar Melloney, Goodacre Steve, Habershon Daniel, Heaton Timothy J, Howell Stephen J, Reuber Markus
Department of Neurology, Sheffield Teaching Hospitals NHS Foundation Trust, Royal Hallamshire Hospital, Sheffield, United Kingdom.
Division of Neuroscience, Royal Hallamshire Hospital, University of Sheffield, Sheffield, United Kingdom.
Neurol Clin Pract. 2025 Apr;15(2):e200448. doi: 10.1212/CPJ.0000000000200448. Epub 2025 Feb 25.
The aim of this study was to develop and validate a machine-learning classifier based on patient and witness questionnaires to support differential diagnosis of transient loss of consciousness (TLOC) at first presentation.
We prospectively recruited patients newly presenting with TLOC to an emergency department, an acute medical unit, and a first seizure or syncope clinic. We invited participants to complete an online questionnaire, either at home or at time of initial assessment. Two expert raters determined the cause of participants' TLOC after 6-month follow-up. We used independent development and validation samples to train a random forest classifier to predict diagnosis from participants' questionnaire responses and validate classifier performance. We compared classifier performance against penalized linear regression and referrer diagnosis.
We included 178 participants in the final analysis, of whom 46 identified a witness able to complete an additional witness questionnaire. Given low witness recruitment, we developed a classifier based on patient answers only. A classifier trained on 9 items correctly identified 63 of 78 diagnoses (80.8%) (95% CI 70.0-88.5), an increase over the accuracy of initial assessing clinicians who were only able to diagnose 70.5% correctly. Within this, 96% (87.0%-99.4%) of those expertly rated as having syncope were correctly classified by the classifier (classifier sensitivity); 40% (20%-63.6%) of those expertly rated after follow-up as having either epilepsy or functional/dissociative seizures were similarly classified as being nonsyncope (classifier specificity).
A machine-learning classifier for differential diagnosis of TLOC has comparable performance in differentiating between 3 main causes of primary TLOC as the current standard of care but is insufficiently accurate in its current form to warrant incorporation into routine care. A system including information from witnesses might improve classification performance.
本研究旨在开发并验证一种基于患者及目击者问卷的机器学习分类器，以辅助首次就诊时短暂意识丧失（TLOC）的鉴别诊断。
我们前瞻性招募了因TLOC首次到急诊科、急性内科病房及首次癫痫或晕厥门诊就诊的患者。我们邀请参与者在家中或初次评估时完成一份在线问卷。两名专家评估者在6个月随访后确定参与者TLOC的病因。我们使用独立的开发样本和验证样本训练随机森林分类器，以根据参与者的问卷回答预测诊断并验证分类器性能。我们将分类器性能与惩罚线性回归及转诊诊断进行比较。
最终分析纳入了178名参与者，其中46名确定有目击者能够完成一份额外的目击者问卷。鉴于目击者招募率较低，我们仅基于患者答案开发了一种分类器。基于9个项目训练的分类器正确识别了78例诊断中的63例（80.8%）（95%可信区间70.0 - 88.5），高于初始评估临床医生仅能正确诊断70.5%的准确率。其中，被专家评定为晕厥的患者中有96%（87.0% - 99.4%）被分类器正确分类（分类器敏感性）；随访后被专家评定为患有癫痫或功能性/分离性发作的患者中，有40%（20% - 63.6%）同样被分类为非晕厥（分类器特异性）。
用于TLOC鉴别诊断的机器学习分类器在区分原发性TLOC的3种主要病因方面与当前护理标准具有相当的性能，但以其目前的形式准确性不足，无法保证纳入常规护理。包含目击者信息的系统可能会提高分类性能。
