An Intelligent Systems Approach to Primary Headache Diagnosis

Keight, Robert; Aljaaf, Ahmed J.; Al‐Jumeily, Dhiya; Hussain, Abir Jaafar; Özge, Aynur; Mallucci, Conor

doi:10.1007/978-3-319-63312-1_6

Cited by 16 publications

(7 citation statements)

References 21 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This finding supports a complex, distributed underlying mode of causation in chronic migraine, and suggests that neither the pursuit of a unitary causal mechanism, nor the evaluation of treatment effects within conventional randomised controlled trials is likely to be productive. Rather, deeper characterisation of patient heterogeneity is likely to be needed, through modelling richer additional features, such as imaging, physiological and genetic data [12][13][14][15][16][17][18] at larger data scales, illuminating the wide causal field of factors that clearly underpins this complex disorder.…”

Section: Discussionmentioning

confidence: 99%

Machine prescription for chronic migraine

Stubberud

Gray

Tronvik

et al. 2021

Preprint

View full text Add to dashboard Cite

Responsive to treatment individually, chronic migraine remains strikingly resistant collectively, incurring the second-highest population burden of disability worldwide. A heterogeneity of responsiveness, requiring prolonged—currently heuristic— individual evaluation of available treatments, may reflect a diversity of causal mechanisms, or the failure to identify the most important, single causal factor. Distinguishing between these possibilities, now possible through the application of complex modelling to large-scale data, is critical to determining the optimal approach to identifying new interventions in migraine and making the best use of existing ones.Examining a richly phenotyped cohort of 1446 consecutive unselected patients with chronic migraine, here we use causal multitask Gaussian process models to estimate individual treatment effects across ten classes of preventatives. Such modelling enables us to quantify the accessibility of heterogeneous responsiveness to high-dimensional modelling, to infer the likely scale of the underlying causal diversity. We calculate the treatment effects in the overall population, and the conditional treatment effects among those modelled to respond and compare the true response rates between these two groups. Identifying a difference in response rates between the groups supports a diversity of causal mechanisms. Moreover, we propose a data-driven machine prescription policy, estimating the time-to-response when sequentially trialing preventatives by individualized treatment effects and compare it to expert guideline sequences. All model performances are quantified out-of-sample.We identify significantly higher true response rates among individuals modelled to respond, compared to the overall population (mean difference of 0.034; 95% CI 0.003 to 0.065; p=0.033), supporting significant heterogeneity of responsiveness and diverse causal mechanisms. The machine prescription policy yields an estimated 35% reduction in time-to-response (3.750 months; 95% CI 3.507 to 3.993; p<0.0001) compared with expert guidelines, with no substantive increase in expense per patient.We conclude that the highly distributed mode of causation in chronic migraine necessitates high-dimensional modelling for optimal management. Machine prescription should be considered an essential clinical decision-support tool in the future management of chronic migraine.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine prescription for chronic migraine

Stubberud

Gray

Tronvik

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence (AI) with machine learning (ML) has shown great potential in building automatic predictors in the field of migraine but detectors for MO are still in their infancy [21]. In fact, many AI models have been applied for nearly 10 years to implement medical decision support systems for the diagnosis of migraine and for predicting migraine treatment outcomes [14][15][16][17][18][19][20][21][22][23].…”

Section: Literature Surveymentioning

confidence: 99%

Knowledge Data Analysis on Migraine Headaches by Using Optimal Classifiers

Kannan¹,

Thangarasu²

2022

INDJCSE

View full text Add to dashboard Cite

Machine learning (ML) is largely used to develop automatic predictors in migraine classification but automatic predictors for medication overuse (MO) in migraine are still in their infancy. This research work finds Naïve Bayes and Naïve Bayes Updateable classifier of statistical learning are producing an efficient results compare with functional learning models. In Statistical learning Naïve Bayes and Naïve Bayes Updateable algorithms are having same as well as highest efficient outcome which is 93.50% of accuracy; In Functional learning, Quadratic Discriminant Analysis is having 93% of accuracy which is highest efficient outcome compare with other functional models. In Statistical learning Naïve Bayes and Naïve Bayes Updateable algorithms are having same as well as highest efficient outcome which is 0.93 of PPV; In Functional learning, Quadratic Discriminant Analysis is having highest PPV which is 0.93 of PPV. In Statistical learning Naïve Bayes and Naïve Bayes Updateable algorithms are having same as well as highest efficient outcome which is 0.94 of TPR; In Functional learning, Quadratic Discriminant Analysis is having highest TPR which is 0.93 of TPR compare with other functional learning. In Statistical learning Naïve Bayes and Naïve Bayes Updateable algorithms are having same as well as highest efficient outcome which is 0.99 of AUCROC; In Functional learning, Quadratic Discriminant Analysis and Multi-Layer Perceptron are having highest AUCROC and same AUCROC value which is 0.97 of AUCROC compare with other functional learning. In Statistical learning Naïve Bayes and Naïve Bayes Updateable algorithms are having same as well as highest efficient outcome which is 0.97 of AUCPRC; In Functional learning, Quadratic Discriminant Analysis is having highest AUCPRC value which is 0.93 of AUCPRC Compare with other functional learning. In Statistical learning Naïve Bayes and Naïve Bayes Updateable algorithms are having same as well as highest efficient outcome which is 0.93 of F1-Score;. In Functional learning, Quadratic Discriminant Analysis is having highest F1-Score value which is 0.93 of F1-Score value Compare with other functional learning. In Statistical learning Naïve Bayes and Naïve Bayes Updateable algorithms are having same as well as highest efficient outcome which is 0.89 of k value; In Functional learning, Quadratic Discriminant Analysis is having highest k value which is 0.88 of k value Compare with other functional learning. In Statistical learning, Naïve Bayes and Naïve Bayes Updateable algorithms are having same as well as highest efficient outcome which is 0.90 of phi coefficient value; In Functional learning, Quadratic Discriminant Analysis is having highest phi coefficient value which is 0.88 of phi coefficient value Compare with other functional learning. This work finds that statistical learning models produce better outcome with lowest errors compare with functional model

show abstract

“…Medical decision-making involves making clinical decisions that focus on diagnosis and treatment and refers to a doctor's preferred behavior when considering a patient's conditions in daily medical practice, which is a process to maximize the avoidance of clinical mistakes. Modern computing platforms provide support for big data processing [108]. The big datadriven paradigm has prompted a large shift in traditional clinical auxiliary decision-making methods.…”

Section: A Medical Decision-making Process and Evolution Mechanismmentioning

confidence: 99%

A Survey on Multimodal Data-Driven Smart Healthcare Systems: Approaches and Applications

Cai

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Multimodal data-driven approach has emerged as an important driving force for smart healthcare systems with applications ranging from disease analysis to triage, diagnosis and treatment. Smart healthcare system necessitates new demands for data management and decision-making, which has inspired the rapid development of medical services using artificial intelligence and new transformations in the healthcare industry. In this paper, we provide a comprehensive survey of existing techniques which include not only state-of-the-art methods but also the most recent trends in the field. In particular, this review focuses on the types of decision-making processes used in smart healthcare systems. Firstly, approaches that utilize multimodal association mining with fine-grained data semantics in smart healthcare systems are introduced. We review the smart healthcare-oriented semantic perception, semantic alignment, entity association mining, and discuss the pros and cons of these approaches. Secondly, we discuss approaches for multimodal data fusion and cross-border association that have been employed in developing smart healthcare systems. Finally, we focus specifically on the use of the panoramic decision framework, interactive decision making, and intelligent decision support systems. We introduce how smart healthcare systems can be applied to and benefit a wide variety of fields, including knowledge discovery and privacy protection.

show abstract

An Intelligent Systems Approach to Primary Headache Diagnosis

Cited by 16 publications

References 21 publications

Machine prescription for chronic migraine

Machine prescription for chronic migraine

Knowledge Data Analysis on Migraine Headaches by Using Optimal Classifiers

A Survey on Multimodal Data-Driven Smart Healthcare Systems: Approaches and Applications

Contact Info

Product

Resources

About