Artificial Intelligence in Clinical Decision Support: a Focused Literature Survey

Montani, Stefania; Striani, Manuel

doi:10.1055/s-0039-1677911

Cited by 81 publications

(57 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We distinguished between knowledge-based approaches (including prior knowledge from experts, literature, ontologies) and data-driven approaches [5] to categorize the diagnosis-supporting models. Knowledge-based approaches ranged from simple decision trees created by experts based on their knowledge of a disease to more sophisticated models using disease and phenotype ontologies to support diagnosis.…”

Section: Developed Modelsmentioning

confidence: 99%

“…In 2019, Montani and Striani [5] reviewed clinical decision support tools using artificial intelligence (AI). They considered two categories of AI: knowledge-based AI, using a "top-down" fashion based on human knowledge, and data-driven AI, using a "bottom-up" fashion to generate knowledge from a large amount of data.…”

Section: Introductionmentioning

confidence: 99%

“…Knowledge-based AI aims to model expert knowledge with artifacts such as ontologies and rules and operationalize it in terms of software or algorithms for reasoning and solving problems, whereas in the case of data-driven systems, models allowing classification and prediction are derived from the processing of data provided to the system. Montani and Striani [5] identified 13 studies proposing decision support dealing with diagnosis. Among these, 11 were exclusively knowledgebased systems, and 2 adopted knowledge-based methods in combination with data-driven methods.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Diagnosis support systems for rare diseases: a scoping review

Faviez

Chen

Garcelon

et al. 2020

Orphanet J Rare Dis

View full text Add to dashboard Cite

Introduction: Rare diseases affect approximately 350 million people worldwide. Delayed diagnosis is frequent due to lack of knowledge of most clinicians and a small number of expert centers. Consequently, computerized diagnosis support systems have been developed to address these issues, with many relying on rare disease expertise and taking advantage of the increasing volume of generated and accessible health-related data. Our objective is to perform a review of all initiatives aiming to support the diagnosis of rare diseases. Methods: A scoping review was conducted based on methods proposed by Arksey and O'Malley. A charting form for relevant study analysis was developed and used to categorize data. Results: Sixty-eight studies were retained at the end of the charting process. Diagnosis targets varied from 1 rare disease to all rare diseases. Material used for diagnosis support consisted mostly of phenotype concepts, images or fluids. Fifty-seven percent of the studies used expert knowledge. Two-thirds of the studies relied on machine learning algorithms, and one-third used simple similarities. Manual algorithms were encountered as well. Most of the studies presented satisfying performance of evaluation by comparison with references or with external validation. Fourteen studies provided online tools, most of which aimed to support the diagnosis of all rare diseases by considering queries based on phenotype concepts. Conclusion: Numerous solutions relying on different materials and use of various methodologies are emerging with satisfying preliminary results. However, the variability of approaches and evaluation processes complicates the comparison of results. Efforts should be made to adequately validate these tools and guarantee reproducibility and explicability.

show abstract

Section: Developed Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Diagnosis support systems for rare diseases: a scoping review

Faviez

Chen

Garcelon

et al. 2020

Orphanet J Rare Dis

View full text Add to dashboard Cite

show abstract

“…First, Bayesian models are transparent as they provide model details represented by complete probability distributions about estimated model parameters, statistical metrics, such as AUC values, and predictions [24,25]. This yields transparency, allowing clinical users of a model to understand the decision rules and better grasp the predicted results in order to embody them into their clinical reasoning and clinical action safely [26,27].…”

Section: Introductionmentioning

confidence: 99%

Predicting the Amputation Risk for Patients with Diabetic Foot Ulceration – A Bayesian Decision Support Tool

Hüsers

Hafer²,

Heggemann³

et al. 2020

Preprint

View full text Add to dashboard Cite

Abstract Background: Diabetes mellitus is a major global health issue with a growing prevalence. In this context, the number of diabetic complications is also on the rise, such as diabetic foot ulcers (DFU), which are closely linked to the risk of lower extremity amputation (LEA). Statistical prediction tools may support clinicians to initiate early tertiary LEA prevention for DFU patients. Thus, we designed Bayesian prediction models, as they produce transparent decision rules, quantify uncertainty intuitively and acknowledge prior available scientific knowledge.Method: A logistic regression using observational collected according to the standardised PEDIS classification was utilised to compute the six-month amputation risk of DFU patients for two types of LEA: 1.) any-amputation and 2.) major-amputation. Being able to incorporate information which is available before the analysis, the Bayesian models were fitted following a twofold strategy. First, the designed prediction models waive the available information and, second, we incorporated the a priori available scientific knowledge into our models. Then, we evaluated each model with respect to the effect of the predictors and validity of the models. Next, we compared the performance of both models with respect to the incorporation of prior knowledge.Results: This study included 237 patients. The mean age was 65.9 (SD 12.3), and 83.5 per cent were male. Concerning the outcome, 31.6% underwent any- and 12.2% underwent a major-amputation procedure. The risk factors of perfusion, ulcer extent and depth revealed an impact on the outcomes, whereas the infection status and sensation did not. The major-amputation model using prior information outperformed the uninformed counterpart (AUC 0.765 vs AUC 0.790, Cohen’s d 2.21). In contrast, the models predicting any-amputation performed similarly (0.793 vs 0.790, Cohen’s d 0.22).Conclusions: Both of the Bayesian amputation risk models showed acceptable prognostic values, and the major-amputation model benefitted from incorporating a priori information from a previous study. Thus, PEDIS serves as a valid foundation for a clinical decision support tool for the prediction of the amputation risk in DFU patients. Furthermore, we demonstrated the use of the available prior scientific information within a Bayesian framework to establish chains of knowledge.

show abstract

“…Such diagnostic technology will be developed and progressed through the collaboration of clinicians and information technology companies in the near future. Another problem to be addressed before applying AI-based diagnostic system to the actual clinical scenes is the lack of interpretability and explainability, which is termed as "black box" nature of AI technologies (Cath 2018;Chang et al 2019;Montani and Striani 2019;Yang and Bang 2019). Such uncertainty regarding how the AI-based diagnosis has been reached would lead to another problem; namely, it is necessary to clarify who should be responsible when the AI tool makes harmful diagnoses and patients face harmful events based on the misdiagnosis (Petersen et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Application of Large Electronic Medical Database for Detecting Undiagnosed Patients in the General Population

Ishii

Akaishi

Fujimori

et al. 2019

Tohoku J. Exp. Med.

View full text Add to dashboard Cite

Clinical application of accumulated medical big data is a hot topic in medical informatics. Not only for suggesting possible diagnoses in each individual, large medical database can be possibly used for detecting undiagnosed patients in the general population. In this study, we tried to develop a computerized system of detecting overlooked undiagnosed patients with rare chronic diseases in the community population by utilizing the uniformed national medical insurance record database. A cumulative total of 489,823 hospital visits at one tertiary medical center were collected for this project. As the target disease, we selected esophagogastric junction outflow obstruction (EGJOO), including achalasia, which is known to be easily overlooked without performing a barium swallow test. Patient selection software automatically picked out 17,814 individuals with the given suspected diagnoses that could be misdiagnosed in patients with the target disease, from which the software further picked out 526 individuals who underwent upper endoscopy but did not undergo barium swallow test. Of them, the hospital medical records suggested that 39 people still suffered from prolonged symptoms lasting for more than 6 months after the first hospital visit. Among them, 16 individuals agreed to undergo the barium swallow test. One of them was confirmed to suffer from EGJOO, possibly based on some undiagnosed connective tissue diseases. An automated computerized detection system with uniform big medical data would realize more efficient and less expensive screening system for undiagnosed chronic diseases in the general population based on symptoms and previously performed examinations in each individual.

show abstract

Artificial Intelligence in Clinical Decision Support: a Focused Literature Survey

Cited by 81 publications

References 84 publications

Diagnosis support systems for rare diseases: a scoping review

Diagnosis support systems for rare diseases: a scoping review

Predicting the Amputation Risk for Patients with Diabetic Foot Ulceration – A Bayesian Decision Support Tool

Application of Large Electronic Medical Database for Detecting Undiagnosed Patients in the General Population

Contact Info

Product

Resources

About