DR.BENCH: Diagnostic Reasoning Benchmark for Clinical Natural Language Processing

The meaningful use of electronic health records (EHR) continues to progress in the digital era with clinical decision support systems augmented by artificial intelligence. A priority in improving provider experience is to overcome information overload and reduce the cognitive burden so fewer medical errors and cognitive biases are introduced during patient care. One major type of medical error is diagnostic error due to systematic or predictable errors in judgement that rely on heuristics. The potential for clinical natural language processing (cNLP) to model diagnostic reasoning in humans with forward reasoning from data to diagnosis and potentially reduce cognitive burden and medical error has not been investigated. Existing tasks to advance the science in cNLP have largely focused on information extraction and named entity recognition through classification tasks. We introduce a novel suite of tasks coined as Diagnostic Reasoning Benchmarks, Dr.Bench, as a new benchmark for developing and evaluating cNLP models with clinical diagnostic reasoning ability. The suite includes six tasks from ten publicly available datasets addressing clinical text understanding, medical knowledge reasoning, and diagnosis generation. DR.BENCH is the first clinical suite of tasks designed to be a natural language generation framework to evaluate pre-trained language models for diagnostic reasoning. The goal of DR. BENCH is to advance the science in cNLP to support downstream applications in computerized diagnostic decision support and improve the efficiency and accuracy of healthcare providers during patient care. We fine-tune and evaluate the state-of-the-art generative models on DR.BENCH. Experiments show that with domain adaptation pre-training on medical knowledge, the model demonstrated opportunities for improvement when evaluated in DR. BENCH. We share DR. BENCH as a publicly available GitLab repository with a systematic approach to load and evaluate models for the cNLP community. We also discuss the carbon footprint produced during the experiments and encourage future work on DR.BENCH to report the carbon footprint.

Diagnosing Trigeminal Neuralgia Based on Clinical Diagnostic Reasoning in an Elderly Patient

When pain adversely affects a patient's activities its diagnosis needs to be fast and accurate to allow effective treatment to be commenced as soon as possible. Difficulties may be found in achieving this, however, in elderly patients with age-associated cognitive decline, as they may not be capable of properly understanding or recalling their symptoms. The present case concerns a 77-year-old woman who presented with the chief complaint of pain in the right mandible persisting throughout the day, and severe enough to necessitate her lying down in bed all day long. The use of open-ended questions followed by a structured interview focused on pain with closed-ended questions revealed that she experienced paroxysms of pain throughout the day and that she was afraid of its occurrence. Based on these findings, the diagnosis was trigeminal neuralgia. Carbamazepine decreased the pain with no side effects. The patient continued taking carbamazepine for 3 months, during which time she was closely monitored for adverse reactions. No side effects, such as drowsiness or dizziness, were observed, however, and the pain subsided completely with no recurrence, even after cessation of carbamazepine.

Impact of Removable Partial Dental Prostheses on the Oral Health-Related Quality of Life of a South African Cohort with Varied Distributions of Missing Posterior Teeth

PURPOSE

To determine the impact of removable partial dental prostheses on satisfying the daily functioning and quality of life (QoL) of adult patients with different distributions of missing posterior teeth.

MATERIALS AND METHODS

A cross-sectional interventional study was carried out on 80 patients having variously distributed posteriorly shortened and interrupted arches. Treatment comprised provision of partial dentures by senior dental students, supervised by senior clinical teachers who had knowledge of the potential benefits of the shortened dental arch (SDA) concept. The Oral Impacts on Daily Performance Index was completed before and 6 months after prosthetic treatment across groups comprising Kennedy Classes I, II, and III arches. Analysis included descriptive statistics and associations and comparisons between variables.

RESULTS

Mean age of patients was 57.4 years (SD = 13.1), many were retired (72.2%), and a majority were females (60%). Most patients lived in urban areas (95%), and were largely unemployed (63.3%). At pretreatment, only 31.3% of patients reported having good dental health and satisfaction with their current oral state, while 82.5% said they had a great need for treatment. The negative oral impacts that were most frequently experienced were those of eating (67.5%), smiling (50%), and being emotionally disturbed (63.8%). Post-treatment, 76.3% indicated good oral health and satisfaction with no significant differences between the 3 Kennedy groups. Any further negative impacts were reported mostly for Kennedy Classes I and II.

CONCLUSIONS

Overall, significant reductions of negative impacts were observed following treatment with dentures, across the 3 Kennedy groups, with respect to improved function, satisfaction, and oral health-related QoL. The findings confirm the reliance by partially dentate patients in all 3 Kennedy groups on dentures for improved oral health, although the possible benefits of the SDA concept as an alternative treatment option was not specifically explored.