Case-base maintenance of a personalised and adaptive CBR bolus insulin recommender system for type 1 diabetes

Torrent-Fontbona, Ferran; Meléndez, Joaquím; López, Beatriz

doi:10.1016/j.eswa.2018.12.036

Cited by 16 publications

(6 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Starting with the fully personalized paradigm, we use three representatives: 1) A state-ofthe-art method for estimating Individualized Treatment Effects (ITE) called CFRnet [31]; 2) A state-of-the-art deep-learning model explicitly designed for depression treatment selection called Vulcan [32]; and 3) A classic Case Based Reasoning (CBR) approach [33]. We discuss these representatives next and contrast them with our approach.…”

Section: Related Work In Machine-assisted Treatment Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Treatment selection using prototyping in latent-space with application to depression treatment

et al. 2021

View full text Add to dashboard Cite

Machine-assisted treatment selection commonly follows one of two paradigms: a fully personalized paradigm which ignores any possible clustering of patients; or a sub-grouping paradigm which ignores personal differences within the identified groups. While both paradigms have shown promising results, each of them suffers from important limitations. In this article, we propose a novel deep learning-based treatment selection approach that is shown to strike a balance between the two paradigms using latent-space prototyping. Our approach is specifically tailored for domains in which effective prototypes and sub-groups of patients are assumed to exist, but groupings relevant to the training objective are not observable in the non-latent space. In an extensive evaluation, using both synthetic and Major Depressive Disorder (MDD) real-world clinical data describing 4754 MDD patients from clinical trials for depression treatment, we show that our approach favorably compares with state-of-the-art approaches. Specifically, the model produced an 8% absolute and 23% relative improvement over random treatment allocation. This is potentially clinically significant, given the large number of patients with MDD. Therefore, the model can bring about a much desired leap forward in the way depression is treated today.

show abstract

Section: Related Work In Machine-assisted Treatment Selectionmentioning

confidence: 99%

“…Nevertheless, several researchers have investigated RS that utilize the CBR approach for treatment selection (e.g. [33]) which relies on the idea of detecting similarities between patients. These have also been applied for mental health treatment selection [40].…”

Section: Related Work In Machine-assisted Treatment Selectionmentioning

confidence: 99%

Treatment selection using prototyping in latent-space with application to depression treatment

et al. 2021

View full text Add to dashboard Cite

show abstract

“…At present, CBR has been widely used in AI, and it has become a new methodology of problem solving and learning [10]. With the gradual maturity of theories and methods, the applications of CBR have been extended to various fields, including medical treatment [11,12,13,14,15], planning [16,17], assessment [18,19], forecast [20,21], game [22], recommendation system [23], management [24] and so on [25,26].…”

Section: Introductionmentioning

confidence: 99%

A hybrid retrieval strategy for case-based reasoning using soft likelihood functions

et al. 2022

View full text Add to dashboard Cite

Case-based reasoning (CBR) is the retrieval of one or more similar cases from an existing case base for the problem to be solved according to the characteristics of the new problem. The core idea of CBR is that similar cases have similar solutions, so whether the CBR system can play a powerful advantage depends on the quality of case retrieval strategy. At present, the commonly used case retrieval algorithm is based on the mean operator method, which is very hard, and a certain local similarity is low will affect the overall result. In order to calculate the global similarity of cases from a new and softer point of view, this paper introduces the soft likelihood functions into case retrieval, combines the soft likelihood functions with KNN, and proposes a hybrid retrieval strategy.The core of the retrieval strategy is to define the global similarity through SLFs, aggregate the local similarity and characteristic similarity together, and also take the attitude characteristics of decision makers into consideration. Through simulation experiments on real data sets, the accuracy rate is more than 81%, which verifies the effectiveness of the retrieval strategy.

show abstract

“…Gu et al [ 30 ] proposed a CBR to improve the accuracy of breast cancer recurrence prediction, and Bentaiba-Lagrid et al [ 31 ] reported an approach to classify mammography mass and thyroid diseases. Torrent-Fontbona et al [ 32 ] developed a CBR, using a numerical solution as an output rather than predetermined class labels to quantify the bolus insulin dosage. CBR has also been recently used for medical image processing applications, e.g., to improve kidney tumor segmentation as reported by Marie et al [ 33 ].…”

Section: Introductionmentioning

confidence: 99%

Similarity measures and attribute selection for case-based reasoning in transcatheter aortic valve implantation

et al. 2020

View full text Add to dashboard Cite

In a clinical decision support system, the purpose of case-based reasoning is to help clinicians make convenient decisions for diagnoses or interventional gestures. Past experience, which is represented by a case-base of previous patients, is exploited to solve similar current problems using four steps-retrieve, reuse, revise, and retain. The proposed casebased reasoning has been focused on transcatheter aortic valve implantation to respond to clinical issues pertaining vascular access and prosthesis choices. The computation of a relevant similarity measure is an essential processing step employed to obtain a set of retrieved cases from a case-base. A hierarchical similarity measure that is based on a clinical decision tree is proposed to better integrate the clinical knowledge, especially in terms of case representation, case selection and attributes weighting. A case-base of 138 patients is used to evaluate the case-based reasoning performance, and retrieve-and reuse-based criteria have been considered. The sensitivity for the vascular access and the prosthesis choice is found to 0.88 and 0.94, respectively, with the use of the hierarchical similarity measure as opposed to 0.53 and 0.79 for the standard similarity measure. Ninety percent of the suggested solutions are correctly classified for the proposed metric when four cases are retrieved. Using a dedicated similarity measure, with relevant and weighted attributes selected through a clinical decision tree, the set of retrieved cases, and consequently, the decision suggested by the case-based reasoning are substantially improved over state-ofthe-art similarity measures.

show abstract

Case-base maintenance of a personalised and adaptive CBR bolus insulin recommender system for type 1 diabetes

Cited by 16 publications

References 48 publications

Treatment selection using prototyping in latent-space with application to depression treatment

Treatment selection using prototyping in latent-space with application to depression treatment

A hybrid retrieval strategy for case-based reasoning using soft likelihood functions

Similarity measures and attribute selection for case-based reasoning in transcatheter aortic valve implantation

Contact Info

Product

Resources

About