scholarly journals Common pre-diagnostic features in individuals with different rare diseases represent a key for diagnostic support with computerized pattern recognition? (Preprint)

2018 ◽  
Author(s):  
Lorenz Grigull ◽  
Sandra Mehmecke ◽  
Ann-Katrin Rother ◽  
Susanne Bloess ◽  
Christian Klemann ◽  
...  
Keyword(s):  
Data Mining ◽  
Pattern Recognition ◽  
Rare Diseases ◽  
Correct Diagnosis ◽  
Diagnostic Delay ◽  
Fusion Algorithm ◽  
Diagnostic Features ◽  
Support Tool ◽  
Answer Pattern ◽  
Diagnostic Support

BACKGROUND Different rare diseases (RD) obviously result in substantial clinical appearances and diagnostic challenges for health professionals. However, we hypothesized that there are consistencies and shared phenomena among all individuals affected by (different) RD during the time before the diagnosis could be established. OBJECTIVE We aimed to identify communalities between different RD and developed a machine learning diagnostic support tool for RD. METHODS 20 interviews with affected individuals with different RD focusing on the time before their final diagnosis was established were performed and qualitatively analyzed. Out of these pre-diagnostic experiences we distilled key phenomena and created a questionnaire which was then distributed among individuals with the established diagnosis of i.) RD, ii.) common non-rare diseases (NRO) iii.) common chronic diseases (CD), iv.), psychosomatic or somatoform diseases (PSY), individuals. Finally, four combined single data mining methods and a fusion algorithm were trained to distinguish the different answer patterns of the questionnaires. RESULTS The questionnaire contained 53 questions. At the end of the campaign a total sum of 1763 questionnaires (758 RD, 149 CD, 48 PSY, 200 NRO, 34 healthy individuals and 574 not evaluable questionnaires) were collected. Based on 3 independent data sets the 10-fold stratified cross-validation method for the answer-pattern recognition resulted in sensitivity values of 88.9% to detect the answer pattern of a RD, 86.6% for NRO, 87.7% for CD and 84.2% for PSY. CONCLUSIONS Despite of being so different, patients with RD share surprisingly similar pre-diagnosis experiences. These communalities were qualitatively explored and successfully used to develop a questionnaire. Mathematical algorithms learned to distinguish these different answer-patterns. Such a questionnaire-based diagnostic support tool might aid professional medical users to raise suspicion for a RD and it could help to shorten the way to the correct diagnosis. Our questionnaire- and data-mining based approach was successfully able to detect unique patterns in individuals affected by a broad range of different rare diseases. Therefore, this approach may shorten the often observed diagnostic delay in RD.

scholarly journals Common pre-diagnostic features in individuals with different rare diseases represent a key for diagnostic support with computerized pattern recognition?

PLoS ONE ◽  
2019 ◽  
Vol 14 (10) ◽  
pp. e0222637 ◽  
Author(s):  
Lorenz Grigull ◽  
Sandra Mehmecke ◽  
Ann-Katrin Rother ◽  
Susanne Blöß ◽  
Christian Klemann ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Rare Diseases ◽  
Diagnostic Features ◽  
Diagnostic Support

scholarly journals Diagnosis Behaviors of Physicians and Non-Physicians When Supported by an Electronic Differential Diagnosis Aid

2019 ◽  
Vol 63 (1) ◽  
pp. 68-72
Author(s):  
Makenzie Pryor ◽  
Doug Ebert ◽  
Vicky Byrne ◽  
Khalaeb Richardson ◽  
Qua Jones ◽  
...  
Keyword(s):  
Decision Aid ◽  
Correct Diagnosis ◽  
Patient Simulation ◽  
Diagnosis And Treatment ◽  
Medical Decision ◽  
Medical Procedures ◽  
Limited Information ◽  
Support Tool ◽  
Patient Diagnosis ◽  
Diagnostic Support

The present study examined a diagnostic medical decision aid developed to help inexperienced operators to diagnose and treat a simulated patient. Diagnosis and treatment accuracy using the tool were assessed and compared across both physicians and non-physicians. Initial analysis revealed more accurate diagnostic and treatment choices for non-physicians, but upon further investigation, physicians were found to have recognized signs for another diagnosis and correctly diagnosed and treated based on the limited information in the patient simulation. This fit with other noted behaviors, such as non-physicians opening the diagnostic support tool within the aid more often than physicians, and frequently returning to the tool during the task. In general, non-physicians were supported in choosing the correct diagnosis and treatment by the aid, while physicians disregarded the aid’s recommendations to make decisions based on their own expertise. These results have implications for the development of future decision support aids for non-physicians performing medical procedures.

scholarly journals POS1137 IDENTIFYING ADULT HYPOPHOSPHATASIA IN THE RHEUMATOLOGY UNIT

2021 ◽  
Vol 80 (Suppl 1) ◽  
pp. 848.1-848
Author(s):  
J. Feurstein ◽  
M. Behanova ◽  
J. Haschka ◽  
K. Roetzer ◽  
G. Uyanik ◽  
...  
Keyword(s):  
Burden Of Illness ◽  
Trabecular Bone Score ◽  
Correct Diagnosis ◽  
Diagnostic Delay ◽  
Official Journal ◽  
Mineral Density ◽  
Mineral Research ◽  
Clinical Factor ◽  
Logistic Regression Models ◽  
Rheumatology Unit

Background:The most frequent manifestation in adult Hypophosphatasia (HPP) is musculoskeletal pain.1,2 The unspecific nature of its clinical presentation may prevent correct diagnosis.3Objectives:Identifying adult hypophosphatasia in the rheumatology unit.Methods:Over a period of 10 years 9,522 patients were screened in a rheumatological outpatient unit. Serum ALP levels ≤ 40 U/l were found in 524 patients. After screening for secondary causes, 73 patients were invited for clinical evaluation. Genetic testing was performed in 23 patients with suspected HPP. Logistic regression models were used to estimate the association of each clinical factor with HPP.Results:Mutations in the ALPL gene were observed in 57% of genetically screened patients. Arthralgia, fractures and pain were the leading symptoms in HPP patients. Chondrocalcinosis (OR 29.12; 95% CI 2.02-1593.52) and dental disease (OR 8.33; 95% CI 0.93-143.40) were associated with HPP independent of BMI. Onset of symptoms in HPP was at 35.1 (14.3) years, with a mean duration from symptoms to diagnosis of 14.4 (8.1) years. Bone mineral density (BMD) and trabecular bone score (TBS) as well as bone turnover markers were not indicative for HPP.Conclusion:HPP can mimic joint diseases.4 Thus, in patients with uncertain rheumatologic complaints and low ALP, HPP should be considered as potential diagnosis.References:[1]Durrough C, Colazo JM, Simmons J, et al. Characterization of physical, functional, and cognitive performance in 15 adults with hypophosphatasia. Bone 2021;142:115695.[2]Seefried L, Kishnani PS, Moseley S, et al. Pharmacodynamics of asfotase alfa in adults with pediatric-onset hypophosphatasia. Bone 2021;142:115664.[3]Högler W, Langman C, Gomes da Silva H, et al. Diagnostic delay is common among patients with hypophosphatasia: initial findings from a longitudinal, prospective, global registry. BMC musculoskeletal disorders 2019;20(1):80.[4]Seefried L, Dahir K, Petryk A, et al. Burden of Illness in Adults With Hypophosphatasia: Data From the Global Hypophosphatasia Patient Registry. Journal of bone and mineral research: the official journal of the American Society for Bone and Mineral Research 2020;35(11):2171-78.Disclosure of Interests:None declared.

Pattern recognition and data mining techniques to identify factors in wafer processing and control determining overlay error

2015 ◽  
Author(s):  
Auguste Lam ◽  
Alexander Ypma ◽  
Maxime Gatefait ◽  
David Deckers ◽  
Arne Koopman ◽  
...  
Keyword(s):  
Data Mining ◽  
Pattern Recognition ◽  
Data Mining Techniques ◽  
Wafer Processing ◽  
And Control

Feasibility of streamlining an interactive Bayesian-based diagnostic support tool designed for clinical practice

2016 ◽  
Author(s):  
Po-Hao Chen ◽  
Emmanuel Botzolakis ◽  
Suyash Mohan ◽  
R. N. Bryan ◽  
Tessa Cook
Keyword(s):  
Clinical Practice ◽  
Support Tool ◽  
Diagnostic Support

A structured model for evaluating countermeasures at highway–railway grade crossings

2005 ◽  
Vol 32 (4) ◽  
pp. 627-635 ◽  
Author(s):  
Young-Jin Park ◽  
Frank F Saccomanno
Keyword(s):  
Data Mining ◽  
Statistical Models ◽  
Decision Support Tool ◽  
Cost Effective ◽  
Expected Number ◽  
Structured Model ◽  
Support Tool ◽  
Data Mining Techniques ◽  
Use Of Data ◽  
Grade Crossings

Various countermeasures can be introduced to reduce collisions at highway–railway grade crossings. These countermeasures may take different forms, such as passive and (or) active driver warning devices, supplementary traffic controls (four quadrant barriers, wayside horn, closed circuit television (CCTV) monitoring, etc.), illumination, signage and highway speed limit, etc. In this research, we present a structured model that makes use of data mining techniques to estimate the effect of changes in countermeasures on the expected number of collisions at a given crossing. This model serves as a decision-support tool for the evaluation and development of cost-effective and practicable safety program at highway–railway grade crossings. The use of data mining techniques helps to resolve many of the problems associated with conventional statistical models used to predict the expected number of collisions for a given type of crossing. Statistical models introduce biases that limit their ability to fully represent the relationship between selected countermeasures and resultant collisions for a mix of crossing attributes. This paper makes use of Canadian inventory and collision data to illustrate the potential merits of the proposed model to provide decision support.Key words: highway–railway grade crossing, collision prediction model, countermeasures, Poisson regression.

Sign in / Sign up

Export Citation Format

Share Document