Meconnaissance in Headache Disorders: Does the ICHD3 Inherently Allows for Misrecognition in Cases of Multiple Headaches?
Zhang, P.
Show abstract
BackgroundIn clinical circumstances with more than one headache disorders, misrecognition can occur if each headache disorder is not separately and individually evaluated. For example, consider the case of a patient with baseline tension type headaches lasting hours who now develops cluster headaches with nausea. Merging the characteristics of both disorders may yield the illusion of migraine. Do these types of misrecognitions occur necessarily because of ICHD3 criteria? Are there combinations of ICHD3 criteria, if any, which necessarily yield this type of misrecognition? ObjectiveThis work seeks to determine whether new, unintended diagnosis, can be arrived when one merges two ICHD3 diagnoses. MethodsWe translated ICHD3 primary headache disorders, as well as headache phenotypes closely mimicking ICHD3 criteria, as numerical data using prime encoding method. We then model the encoding of two concurrent diagnoses in an individual by multiplying all pairing of ICHD3 encoding. We then diagnose the result algorithmically to see which pairings, if any, generate "new"/" illusionary" diagnoses. ResultsA total of 117,526 phenotypes were generated. After duplicate pairing of diagnoses were removed, we derived a total of 72 pairings of unique ICHD3 diagnoses that yield a "new" diagnosis. Thirty-seven (51%) of these pairings were not judged to be "illusionary": they simply arise from our models idiosyncrasy of encoding chronic migraine without encoding migraine with or without aura explicitly. Of the rest, 23 pairings involve combining paroxysmal hemicrania with either a longer or shorter duration headache. We further generalize the condition under which the above "illusionary" diagnosis occurs as a mathematical observation. ConclusionMisrecognition arises naturally if diagnostic criteria consist solely of characteristics from another headache disorder or a combination of two headache disorders. Specifically, combining headaches with different duration and/or frequency are most likely to yield these "illusionary" diagnoses.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Matrix and Graphical Representation of the Primary Headache Syndromes in the International Classification of Headache Disorders (ICHD3): A Basis for Automated Diagnosis and Analysis of Criteria. 97%
- Safe Non-opioid and Non-barbiturate containing Acute Medication Combinations in Headache: An Exhaustive Approach Based on DrugBank Database 92%
- Seizure Forecasting Using a Novel Sub-Scalp Ultra-Long Term EEG Monitoring System 88%
Similar papers in this journal
- Sociodemographically Differential Patterns of Chronic Pain Progression Revealed by Analyzing the All of Us Research Program Data 90%
- Machine-learning-based prediction of disability progression in multiple sclerosis: an observational, international, multi-center study 88%
- Identification of predictive patient characteristics for assessing the probability of COVID-19 in-hospital mortality 88%
Similar papers in this journal
- Scoping Review and Interpretation of Myofascial Pain/Fibromyalgia Syndrome: An Attempt to Assemble a Medical Puzzle 89%
- Imbalanced Machine Learning Classification Models For Removal Biosimilar Drugs And Increased Activity In Patients With Rheumatic Diseases 89%
- Predicting epileptic seizures using nonnegative matrix factorization 89%
Similar papers in this journal
- L-arginine and aged garlic extract for the prevention of migraine: a study protocol for a randomised, double-blind, placebo-controlled, phase-II trial (LARGE trial) 90%
- Machine Learning Analysis of Motor Evoked Potential Time Series to Predict Disability Progression in Multiple Sclerosis 90%
- Exploring Comorbidity Networks in Mild Traumatic Brain Injury Subjects through Graph Theory: A Traumatic Brain Injury Model Systems Study 87%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.