A decision support system for primary headache developed through machine learning

The Ethical Stewardship of Artificial Intelligence in Chronic Pain and Headache: A Narrative Review

PURPOSE OF REVIEW

As artificial intelligence (AI) and machine learning (ML) are becoming more pervasive in medicine, understanding their ethical considerations for chronic pain and headache management is crucial for optimizing their safety.

RECENT FINDINGS

We reviewed thirty-eight editorial and original research articles published between 2018 and 2023, focusing on the application of AI and ML to chronic pain or headache. The core medical principles of beneficence, non-maleficence, autonomy, and justice constituted the evaluation framework. The AI applications addressed topics such as pain intensity prediction, diagnostic aides, risk assessment for medication misuse, empowering patients to self-manage their conditions, and optimizing access to care. Virtually all AI applications aligned both positively and negatively with specific medical ethics principles. This review highlights the potential of AI to enhance patient outcomes and physicians' experiences in managing chronic pain and headache. We emphasize the importance of carefully considering the advantages, disadvantages, and unintended consequences of utilizing AI tools in chronic pain and headache, and propose the four core principles of medical ethics as an evaluation framework.

A Cross-Sectional Study on Whether Comprehensively Gathering Information From Medical Records Is Useful for the Collection of Operational Characteristics

This study tests whether comprehensively gathering information from medical records is useful for developing clinical decision support systems using Bayes' theorem. Using a single-center cross-sectional study, we retrospectively extracted medical records of 270 patients aged ≥16 years who visited the emergency room at the Tokyo Metropolitan Tama Medical Center with a chief complaint of experiencing headaches. The medical records of cases were analyzed in this study. We manually extracted diagnoses, unique keywords, and annotated keywords, classifying them as either positive or negative. Cross tables were created, and the proportion of combinations for which the likelihood ratios could be calculated was evaluated. Probability functions for the appearance of new unique keywords were modeled, and theoretical values were calculated. We extracted 623 unique keywords, 26 diagnoses, and 6,904 annotated keywords. Likelihood ratios could be calculated only for 276 combinations (1.70%), of which 24 (0.15%) exhibited significant differences. The power function+constant was the best fit for new unique keywords. The increase in the number of combinations after increasing the number of cases indicated that while it is theoretically possible to comprehensively gather information from medical records in this way, doing so presents difficulties related to human costs. It also does not necessarily solve the fundamental issues with medical informatics or with developing clinical decision support systems. Therefore, we recommend using methods other than comprehensive information gathering with Bayes' theorem as the classifier to develop such systems.

Migraine headache (MH) classification using machine learning methods with data augmentation

Migraine headache, a prevalent and intricate neurovascular disease, presents significant challenges in its clinical identification. Existing techniques that use subjective pain intensity measures are insufficiently accurate to make a reliable diagnosis. Even though headaches are a common condition with poor diagnostic specificity, they have a significant negative influence on the brain, body, and general human function. In this era of deeply intertwined health and technology, machine learning (ML) has emerged as a crucial force in transforming every aspect of healthcare, utilizing advanced facilities ML has shown groundbreaking achievements related to developing classification and automatic predictors. With this, deep learning models, in particular, have proven effective in solving complex problems spanning computer vision and data analytics. Consequently, the integration of ML in healthcare has become vital, especially in developing countries where limited medical resources and lack of awareness prevail, the urgent need to forecast and categorize migraines using artificial intelligence (AI) becomes even more crucial. By training these models on a publicly available dataset, with and without data augmentation. This study focuses on leveraging state-of-the-art ML algorithms, including support vector machine (SVM), K-nearest neighbors (KNN), random forest (RF), decision tree (DST), and deep neural networks (DNN), to predict and classify various types of migraines. The proposed models with data augmentations were trained to classify seven various types of migraine. The proposed models with data augmentations were trained to classify seven various types of migraine. The revealed results show that DNN, SVM, KNN, DST, and RF achieved an accuracy of 99.66%, 94.60%, 97.10%, 88.20%, and 98.50% respectively with data augmentation highlighting the transformative potential of AI in enhancing migraine diagnosis.

The Clinical Relevance of Artificial Intelligence in Migraine

Migraine is a burdensome neurological disorder that still lacks clear and easily accessible diagnostic biomarkers. Furthermore, a straightforward pathway is hard to find for migraineurs' management, so the search for response predictors has become urgent. Nowadays, artificial intelligence (AI) has pervaded almost every aspect of our lives, and medicine has not been missed. Its applications are nearly limitless, and the ability to use machine learning approaches has given researchers a chance to give huge amounts of data new insights. When it comes to migraine, AI may play a fundamental role, helping clinicians and patients in many ways. For example, AI-based models can increase diagnostic accuracy, especially for non-headache specialists, and may help in correctly classifying the different groups of patients. Moreover, AI models analysing brain imaging studies reveal promising results in identifying disease biomarkers. Regarding migraine management, AI applications showed value in identifying outcome measures, the best treatment choices, and therapy response prediction. In the present review, the authors introduce the various and most recent clinical applications of AI regarding migraine.

Verification of a clinical decision support system for the diagnosis of headache disorders based on patient-computer interactions: a multi-center study

BACKGROUND

Although headache disorders are common, the current diagnostic approach is unsatisfactory. Previously, we designed a guideline-based clinical decision support system (CDSS 1.0) for diagnosing headache disorders. However, the system requires doctors to enter electronic information, which may limit widespread use.

METHODS

In this study, we developed the updated CDSS 2.0, which handles clinical information acquisition via human-computer conversations conducted on personal mobile devices in an outpatient setting. We tested CDSS 2.0 at headache clinics in 16 hospitals in 14 provinces of China.

RESULTS

Of the 653 patients recruited, 18.68% (122/652) were suspected by specialists to have secondary headaches. According to "red-flag" responses, all these participants were warned of potential secondary risks by CDSS 2.0. For the remaining 531 patients, we compared the diagnostic accuracy of assessments made using only electronic data firstly. In Comparison A, the system correctly recognized 115/129 (89.15%) cases of migraine without aura (MO), 32/32 (100%) cases of migraine with aura (MA), 10/10 (100%) cases of chronic migraine (CM), 77/95 (81.05%) cases of probable migraine (PM), 11/11 (100%) cases of infrequent episodic tension-type headache (iETTH), 36/45 (80.00%) cases of frequent episodic tension-type headache (fETTH), 23/25 (92.00%) cases of chronic tension-type headache (CTTH), 53/60 (88.33%) cases of probable tension-type headache (PTTH), 8/9 (88.89%) cases of cluster headache (CH), 5/5 (100%) cases of new daily persistent headache (NDPH), and 28/29 (96.55%) cases of medication overuse headache (MOH). In Comparison B, after combining outpatient medical records, the correct recognition rates of MO (76.03%), MA (96.15%), CM (90%), PM (75.29%), iETTH (88.89%), fETTH (72.73%), CTTH (95.65%), PTTH (79.66%), CH (77.78%), NDPH (80%), and MOH (84.85%) were still satisfactory. A patient satisfaction survey indicated that the conversational questionnaire was very well accepted, with high levels of satisfaction reported by 852 patients.

CONCLUSIONS

The CDSS 2.0 achieved high diagnostic accuracy for most primary and some secondary headaches. Human-computer conversation data were well integrated into the diagnostic process, and the system was well accepted by patients. The follow-up process and doctor-client interactions will be future areas of research for the development of CDSS for headaches.

Artificial Intelligence-Aided Headache Classification Based on a Set of Questionnaires: A Short Review

Wielding modern technology in the form of artificial intelligence (AI) or deep learning (DL) can utilize the best possible latest computer application in intricate decision-making and enigmatic problem-solving. It has been recommended in many fields. However, it is a long way from achieving an ambitious genuine intention when it comes to understanding and identifying any headache condition or classification, and using it error-free. No studies hitherto formalized any headache AI models to accurately classify headaches. 

A machine’s job can be arduous when incorporating an emotional dimension in decision making, re-challenging its own diagnosis by keeping a differential at all times, where even experienced neurologists or headache experts sometimes find it demanding to make a precise analysis and formulate a methodical plan. This could be because of spanning clinical presentation at a given moment of time or a change in clinical pattern over time which apparently could be due to intercrossing multiple pathophysiologies.

We did a short literature review on the role of artificial intelligence and machine learning in headache classification. This brings forth a minuscule insight into the vastness of headaches and the perpetual effort and exploration headache may demand from AI when trying to scrutinize its classification. Undoubtedly, AI or DL could better be utilized in identifying the red flags of headache, as it might help our patients at home or the primary care physicians/practicing doctors/non- neurologists in their clinic to triage the headache patients if they need an imperative higher center referral to a neurologist for advanced evaluation. This outlook can limit the burden on a handful of headache specialists by minimizing the referrals to a tertiary care setting.

Machine-learning based approach to predict anti-CGRP response in patients with migraine: multicenter Spanish study

BACKGROUND

To date, several variables have been associated with anti-CGRP receptor or ligand-antibody response with disparate results. Our objective is to determine whether machine learning (ML)-based models can predict 6, 9 and 12 months response to anti-CGRP receptor or ligand therapies among migraine patients.

METHODS

We performed a multicenter analysis of a prospectively collected data cohort of patients with migraine receiving anti-CGRP therapies. Demographic and clinical variables were collected. Response rate defined in the 30% to 50% range -or at least 30%-, in the 50% to 75% range -or at least 50%-, and response rate over 75% reduction in the number of headache days per month at 6, 9 and 12 months. A sequential forward feature selector was used for variable selection and ML-based predictive models response to anti-CGRP therapies at 6, 9 and 12 months, with models' accuracy not less than 70%, were generated.

RESULTS

A total of 712 patients were included, 93% women, aged 48 years (SD=11.7). Eighty-three percent had chronic migraine. ML models using headache days/month, migraine days/month and HIT-6 variables yielded predictions with a F1 score range of 0.70-0.97 and AUC (area under the receiver operating curve) score range of 0.87-0.98. SHAP (SHapley Additive exPlanations) summary plots and dependence plots were generated to evaluate the relevance of the factors associated with the prediction of the above-mentioned response rates.

CONCLUSIONS

According to our study, ML models can predict anti-CGRP response at 6, 9 and 12 months. This study provides a predictive tool to be used in a real-world setting.