Medicine encompasses rare disorders with diverse and overlapping clinical manifestations that necessitate use of differential diagnostic approach. An example is amyotrophic lateral sclerosis (ALS), a heterogeneous disease characterized by a progressive degeneration of upper and lower motor neurons that can lead to a variety of symptoms [1]. There are a number of disorders with different treatment options and prognostic outcomes that can mimic amyotrophic lateral sclerosis [2,3]. Yet, in the absence of a specific biomarker for the disease, ALS remains a clinical diagnosis [4]. Although diagnostic errors may have disastrous consequences, over 40% of patients with amyotrophic lateral sclerosis are initially diagnosed incorrectly [5].
Case reports can provide clinicians with a rich representation of the spectrum a disorder can manifest throughout its clinical course, and thereby serve as a valuable source of guidance for clinicians in face of challenging cases [6]. Clinicians may use case reports during the formulation of differential diagnosis to identify and differentiate potential causes that can account for the patient's symptoms. However, retrieval of pertinent information from narrative texts that comprise case reports through manual inspection of individual reports can be a prohibitively time-consuming task for busy clinicians.
Advancements in natural language processing may greatly increase the clinical utility of case reports by facilitating information extraction from text. One of the recent breakthroughs in natural language processing was the introduction of transformer-based natural language models in 2017 [7]. Among the many language processing tasks with potential clinical utility that transformer-based models have excelled at is that of semantic classification [8]. The sentence embeddings in the form of fixed-length vectors innately facilitate the text comparison process, and similarities between texts can be trivially obtained by applying distance metrics directly to the embeddings [9].
However, mere vector similarity between the text embeddings has limited applicability in the clinical context. Clinical reasoning involves attending to key differentiating elements to draw possible explanations for a given clinical presentation in accordance with contemporary clinical criteria [10]. The text similarity methods that do not distinguish features of importance from the rest and do not offer any explanations are difficult to be used in clinical context.
Although language models can be fine-tuned for individual target tasks to overcome such limitations, it is not possible to develop models for every subfield of medicine. Medicine is a rapidly evolving field comprised of distinct sub-fields each with vastly different terminologies and focuses. At present the performance of the transformer models can be measured only empirically, and studies show that fine tuning of general language models such as BERT does not necessarily improve their performance on target tasks [11].
In this paper, it is demonstrated that feature extraction using vector difference between Universal Sentence Encoder (USE) embeddings can not only augment semantic classification with interpretability but also improve the classification accuracy.