[Motivation and description of Bayes' model of diagnostic medical decision (author's transl)].
Explore the source record for details and available documents.
Decision Making↗
SEARCH · Search PubMed
Results for “diagnostic model”
Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
[A few remarks on the problems of linear models of diagnostic judgment formation].
Explore the source record for details and available documents.
Humans↗
Role of IFIT1 and IFIT3 in systemic lupus erythematosus: modeling a diagnosis and exploring immune regulation.
Systemic lupus erythematosus (SLE) is a complex autoimmune disorder characterized by multi-organ involvement and a protracted clinical course. Current diagnostic strategies, which rely heavily on clinical symptoms and serology, are often insufficient for early detection. Therefore, highly accurate diagnostic biomarkers are urgently needed to facilitate early intervention and optimize personalized treatment strategies. D atasets GSE61635 and GSE135779 were integrated to identify differentially expressed genes. Weighted gene co-expression network analysis (WGCNA) was performed to isolate the module with the strongest clinical relevance. Mendelian randomization and single‑cell RNA‑seq were used to identify key disease‑relevant genes. A diagnostic model was then constructed, and gene set variation analysis (GSVA), along with gene set enrichment analysis (GSEA), was conducted to elucidate the underlying molecular pathways. IFIT1 and IFIT3 were identified as 2 core genes highly expressed in monocytes and T cells of SLE patients. Functional enrichment analysis revealed that these genes were enriched in immune-related pathways, metabolic pathways related to inflammation and genomic stability. The diagnostic model showed good accuracy, with an area under the curve (AUC) of 0.974 on the training set and 0.912 on the validation set. IFIT1 and IFIT3 represent promising biomarkers for diagnosing SLE and appear to mediate key immune and metabolic disturbances. Furthermore, the developed model serves as an accurate and reliable instrument for early diagnosis and personalized therapy. Large-scale clinical studies are warranted to further validate these findings and evaluate their clinical application.
Humans↗
Knowledge representation and sharing using visual semantic modeling for diagnostic medical image databases.
Information technology offers great opportunities for supporting radiologists' expertise in decision support and training. However, this task is challenging due to difficulties in articulating and modeling visual patterns of abnormalities in a computational way. To address these issues, well established approaches to content management and image retrieval have been studied and applied to assist physicians in diagnoses. Unfortunately, most of the studies lack the flexibility of sharing both explicit and tacit knowledge involved in the decision making process, while adapting to each individual's opinion. In this paper, we propose a knowledge repository and exchange framework for diagnostic image databases called "evolutionary system for semantic exchange of information in collaborative environments" (Essence). This framework uses semantic methods to describe visual abnormalities, and offers a solution for tacit knowledge elicitation and exchange in the medical domain. Also, our approach provides a computational and visual mechanism for associating synonymous semantics of visual abnormalities. We conducted several experiments to demonstrate the system's capability of matching synonym terms, and the benefit of using tacit knowledge in improving the meaningfulness of semantic queries.
Artificial Intelligence↗
Application of tissue Doppler to interpretation of exercise echocardiography: diagnostics of ischemia localization in patients with ischemic heart disease.
UNLABELLED: Development of optimal methods for the objective non-invasive diagnosis of coronary artery disease remains a challenge for imaging techniques in stress tests. AIM: The aim of this study was to obtain quantitative diagnostic criteria TDI which could detect significant coronary artery disease during exercise echocardiography. METHODS AND RESULTS: We evaluated regional systolic and diastolic myocardial functions of 123 patients by pulsed wave tissue Doppler imaging (TDI) in eight segments of left ventricle during exercise stress testing. Diagnostic criteria were obtained by comparing TDI and coronary angiography data. Best cut-points of velocity parameters allowed developing two diagnostic models for the detection of left anterior descending (LAD) and circumflex (LCx) artery diseases. The accuracy of the TDI diagnostic model for LAD-disease was 86.2% and for LCx-disease 78.3%. There were no criteria for the detection of RCA disease in this study. CONCLUSION: So TDI is a very accurate method for the detection of LAD- and LCx-disease during exercise stress echocardiography.
Chi-Square Distribution↗
[Medical diagnosis].
The diagnostic process holds a firm position in medical practice, but is often claimed to be part of the "art of medicine", partially beyond reach of rational and logical analysis. Research in clinical cognition, decision analysis and artificial intelligence have, however, elucidated essential parts of medical diagnosis. A characteristic feature of diagnosis is the manner in which uncertainties are handled. Early generation of hypotheses about the nature of the condition present seems to be useful method. Similarly, probabilistic, causal and deterministic reasoning can be illustrated by diagnostic models which have found favor during recent years. A certain type of cognitive process (heuristic) is employed when assessing information of probabilistic nature. The diagnostic models are partial and concern the parts of the process, which may be represented verbally and consciously. This raises the question of how the clinician actually draws upon experience (background knowledge), which preconditions shape the generation of applicable diagnostic hypotheses and how the diagnostic capability of the individual physician can be facilitated.
Clinical Competence↗
Evolutionary fuzzy modeling human diagnostic decisions.
Fuzzy CoCo is a methodology, combining fuzzy logic and evolutionary computation, for constructing systems able to accurately predict the outcome of a human decision-making process, while providing an understandable explanation of the underlying reasoning. Fuzzy logic provides a formal framework for constructing systems exhibiting both good numeric performance (accuracy) and linguistic representation (interpretability). However, fuzzy modeling--meaning the construction of fuzzy systems--is an arduous task, demanding the identification of many parameters. To solve it, we use evolutionary computation techniques (specifically cooperative coevolution), which are widely used to search for adequate solutions in complex spaces. We have successfully applied the algorithm to model the decision processes involved in two breast cancer diagnostic problems, the WBCD problem and the Catalonia mammography interpretation problem, obtaining systems both of high performance and high interpretability. For the Catalonia problem, an evolved system was embedded within a Web-based tool-called COBRA-for aiding radiologists in mammography interpretation.
Breast Neoplasms↗
Fine mapping and SNP analysis of positional candidates at the preeclampsia susceptibility locus (PREG1) on chromosome 2.
Genome scans in Icelandic, Australian and New Zealand, and Finnish families have localized putative susceptibility loci for preeclampsia/ eclampsia to chromosome 2. The locus mapped in the Australian and New Zealand study (designated PREG1) was thought to be the same locus as that identified in the Icelandic study. In both these studies, two distinct quantitative trait locus (QTL) regions were evident on chromosome 2. Here, we describe our fine mapping of the PREG1 locus and a genetic analysis of two positional candidate genes. Twenty-five additional microsatellite markers were genotyped within the 74-cM linkage region defined by the combined Icelandic and Australian and New Zealand genome scans. The overall position and shape of the localization evidence obtained using nonparametric multipoint analysis did not change from that seen previously in our 10-cM resolution genome scan; two peaks were displayed, one on chromosome 2p at marker D2S388 (107.46 cM) and the other on chromosome 2q at 151.5 cM at marker D2S2313. Using the robust two-point linkage analysis implemented in the Analyze program, all 25 markers gave positive LOD scores with significant evidence of linkage being seen at marker D2S2313 (151.5 cM), achieving a LOD score of 3.37 under a strict diagnostic model. Suggestive evidence of linkage was seen at marker D2S388 (107.46 cM) with a LOD score of 2.22 under the general diagnostic model. Two candidate genes beneath the peak on chromosome 2p were selected for further analysis using public single nucleotide polymorphisms (SNPs) within these genes. Maximum LOD scores were obtained for an SNP in TACR1 (LOD = 3.5) and for an SNP in TCF7L1 (LOD = 3.33), both achieving genome-wide significance. However, no evidence of association was seen with any of the markers tested. These data strongly support the presence of a susceptibility gene on chromosome 2p11-12 and substantiate the possibility of a second locus on chromosome 2q23.
Australia↗
Methods for multi-category cancer diagnosis from gene expression data: a comprehensive evaluation to inform decision support system development.
Cancer diagnosis is a major clinical applications area of gene expression microarray technology. We are seeking to develop a system for cancer diagnostic model creation based on microarray data. In order to equip the system with the optimal combination of data modeling methods, we performed a comprehensive evaluation of several major classification algorithms, gene selection methods, and cross-validation designs using 11 datasets spanning 74 diagnostic categories (41 cancer types and 12 normal tissue types). The Multi-Category Support Vector Machine techniques by Crammer and Singer, Weston and Watkins, and one-versus-rest were found to be the best methods and they outperform other learning algorithms such as K-Nearest Neighbors and Neural Networks often to a remarkable degree. Gene selection techniques are shown to significantly improve classification performance. These results guided the development of a software system that fully automates cancer diagnostic model construction with quality on par with or better than previously published results derived by expert human analysts.
Algorithms↗
Diagnostic concepts, multimodal and multiaxial approaches in psychotherapy and psychosomatics.
Basic questions concerning diagnostic models in psychoanalytic psychotherapy and psychosomatics are discussed in this paper. Against the background of the different areas in psychodynamic-oriented diagnoses, the advantages and disadvantages of descriptive multiaxial diagnostical models like DSM-III-R and ICD-10 are examined. These conceptual reflections have been built on the findings from participation in Germany of a great number of psychotherapeutic/psychosomatic institutions in the field trials for the assessment of the Diagnostic Criteria for Research of ICD-10, chapter V. Some of the most important issues this study has raised are discussed.
Conversion Disorder↗
A new gene (DYX3) for dyslexia is located on chromosome 2.
Developmental dyslexia is a specific reading disability affecting children and adults who otherwise possess normal intelligence, cognitive skills, and adequate schooling. Difficulties in spelling and reading may persist through adult life. Possible localisations of genes for dyslexia have been reported on chromosomes 15 (DYX1), 6p21.3-23 (DYX2), and 1p over the last 15 years. Only the localisation to 6p21.3-23 has been clearly confirmed and a genome search has not previously been carried out. We have investigated a large Norwegian family in which dyslexia is inherited as an autosomal dominant trait. A genome wide search for linkage with an average 20 cM marker density was initiated in 36 of the 80 family members. The linkage analysis was performed under three different diagnostic models. Linkage analysis in the family identified a region in 2p15-p16 which cosegregated with dyslexia. Maximum lod scores of 3.54, 2.92, and 4.32 for the three different diagnostic models were obtained. These results were confirmed by a non-parametric multipoint GENEHUNTER analysis in which the most likely placement of the gene was in a 4 cM interval between markers D2S2352 and D2S1337. Localisation of a gene for dyslexia to 2p15-16, together with the confirmed linkage to 6p21.3-23, constitute strong evidence for genetic heterogeneity in dyslexia. Since no gene for dyslexia has been isolated, little is known about the molecular processes involved. The isolation and molecular characterisation of this newly reported gene on chromosome 2 (DYX3) and DYX1 will thus provide new and exciting insights into the processes involved in reading and spelling.
Adult↗
SELDI-TOF-MS: the proteomics and bioinformatics approaches in the diagnosis of breast cancer.
Breast cancer has never had any good serum tumor markers. Therefore, we developed and evaluated a proteomics approach to searching for new biomarkers and building diagnostic models. SELDI-TOF-MS ProteinChip was used to detect the serum protein patterns of 49 breast cancer patients, 51 patients with benign breast diseases, and 33 healthy women. The diagnostic models were developed and validated using bioinformatics tools such as artificial neural networks and discriminant analysis. In total, four models were built and their sensitivities and specificities were satisfactory. The abilities of these models to diagnose stage I breast cancer were not worse than for stages II-IV (P>0.05). Four candidate biomarkers of breast cancer were found. The high sensitivity and specificity achieved by this method show great potential for the early detection of breast cancer and facilitation of discovering new and improved biomarkers.
Adult↗
Drug-free treatment selection for chemical abusers: a diagnostic-based model.
The frequent treatment failures of patients with alcohol and drug-abuse disorders are often attributable to poor treatment choice. The absence from the literature of clinically relevant criteria for serving this population is noted. Four categories of patients are identified, and a diagnostic framework for the selection of drug-free treatments is proposed.
Alcoholism↗
Construction of a molecular diagnostic system for neurogenic rosacea by combining transcriptome sequencing and machine learning.
Patients with neurogenic rosacea (NR) frequently demonstrate pronounced neurological manifestations, often unresponsive to conventional therapeutic approaches. A molecular-level understanding and diagnosis of this patient cohort could significantly guide clinical interventions. In this study, we amalgamated our sequencing data (n = 46) with a publicly accessible database (n = 38) to perform an unsupervised cluster analysis of the integrated dataset. The eighty-four rosacea patients were partitioned into two distinct clusters. Neurovascular biomarkers were found to be elevated in cluster 1 compared to cluster 2. Pathways in cluster 1 were predominantly involved in neurotransmitter synthesis, transmission, and functionality, whereas cluster 2 pathways were centered on inflammation-related processes. Differential gene expression analysis and WGCNA were employed to delineate the characteristic gene sets of the two clusters. Subsequently, a diagnostic model was constructed from the identified gene sets using linear regression methodologies. The model's C index, comprising genes PNPLA3, CUX2, PLIN2, and HMGCR, achieved a remarkable value of 0.9683, with an area under the curve (AUC) for the training cohort's nomogram of 0.9376. Clinical characteristics from our dataset (n = 46) were assessed by three seasoned dermatologists, forming the NR validation cohort (NR, n = 18; non-neurogenic rosacea, n = 28). Upon application of our model to NR diagnosis, the model's AUC value reached 0.9023. Finally, potential therapeutic candidates for both patient groups were predicted via the Connectivity Map. In summation, this study unveiled two clusters with unique molecular phenotypes within rosacea, leading to the development of a precise diagnostic model instrumental in NR diagnosis.
Humans↗
[Personality and personality disorders I. Universality and sensitivity of dimensional personality models as diagnostic systems for personality disorders].
OBJECTIVE: A dimensional diagnostic system for personality disorders (PD) postulates continuous transitions from normal to disordered personalities (continuity hypothesis) and universal validity of basic personality dimensions (universal hypothesis). In the present study three dimensional personality models that claim to provide a systematic representation of the overall domain of personality disorders were compared: the Big-Five model proposed by Costa and McCrae, the psychobiological model proposed by Cloninger and colleagues, and the "Dimensional Assessment of Personal Pathology (DAPP)" model proposed by Livesley and colleagues. METHOD: The "Six Factor Test" (SFT) measuring the Big-Five factors of personality, the "Temperament and Character Inventory (TCI)" measuring 4 temperament and 3 character dimensions, and the DAPP measuring 18 basic traits and 4 second ordered factors were administered to general population subjects (n = 156), and a clinical sample (n = 220) including a subsample of 69 patients with at least one diagnosis of DSM-IV PD. Group comparisons, regression analyses, and facet theoretical analyses were conducted. RESULTS: The nonmetric similarity analyses of the three personality models show a nearly identical radex-representation of the second ordered factors in the non-clinical and clinical sample reflecting an universal validity of 4 basic personality dimensions and confirming the universal hypothesis. In comparison with the BIG-Five concept and the psychobiological model the DAPP model seems to be more sensitive to differentiate PD patients from controls with a reclassification rate of 94.5 %. CONCLUSIONS: The Big-Five model, the DAPP and the TCI represent a substantially similar domain despite their different conceptualization. However, the DAPP was more sensitive to differences between PD patients and controls, offered a more comprehensive account of PD, and could differentiate the two groups more effectively.
Character↗
Genome-wide linkage scan in a large bipolar disorder sample from the National Institute of Mental Health genetics initiative suggests putative loci for bipolar disorder, psychosis, suicide, and panic disorder.
We conducted a 9-cM genome scan in a large bipolar pedigree sample from the National Institute of Mental Health genetics initiative (1060 individuals from 154 multiplex families). We performed parametric and nonparametric analyses using both standard diagnostic models and comorbid conditions thought to identify phenotypic subtypes: psychosis, suicidal behavior, and panic disorder. Our strongest linkage signals (genome-wide significance) were observed on chromosomes 10q25, 10p12, 16q24, 16p13, and 16p12 using standard diagnostic models, and on 6q25 (suicidal behavior), 7q21 (panic disorder) and 16p12 (psychosis) using phenotypic subtypes. Several other regions were suggestive of linkage, including 1p13 (psychosis), 1p21 (psychosis), 1q44, 2q24 (suicidal behavior), 2p25 (psychosis), 4p16 (psychosis, suicidal behavior), 5p15, 6p25 (psychosis), 8p22 (psychosis), 8q24, 10q21, 10q25 (suicidal behavior), 10p11 (psychosis), 13q32 and 19p13 (psychosis). Over half the implicated regions were identified using phenotypic subtypes. Several regions - 1p, 1q, 6q, 8p, 13q and 16p - have been previously reported to be linked to bipolar disorder. Our results suggest that dissection of the disease phenotype can enrich the harvest of linkage signals and expedite the search for susceptibility genes. This is the first large-scale linkage scan of bipolar disorder to analyze simultaneously bipolar disorder, psychosis, suicidal behavior, and panic disorder.
Bipolar Disorder↗
Distinguishing the benign and malignant adnexal mass: an external validation of prognostic models.
OBJECTIVE: Because external validation of the present models has not been reported, the purpose of the present study was to assess existing diagnostic models that are used to distinguish malignant from benign masses. METHODS: We tested the performance of existing models in a prospectively assembled data set of 170 patients with an adnexal mass. Twenty-one models that have been reported previously were assessed. The models were based on combinations of ultrasound findings, color Doppler tests, CA-125 measurement, age, and/or menopausal status. For each model, we constructed ROC curves and calculated an area under the ROC curve. RESULTS: Of the 170 adnexal masses that were operated on, 30 (18%) were malignant. The area under the ROC curve of 21 models that were externally validated varied between 0.69 and 0.90. We found the performance of the existing models to be inferior to the performance reported in the initial studies. Even models that incorporated multiple diagnostic tools and that were developed using logistic regression models or neural networks had an area under the ROC curve of 0.86 at maximum. In the case where we focused on almost perfect sensitivity, the highest specificities varied between 0.45 and 0.60. CONCLUSION: Although diagnostic models might be of value in the preoperative assessment of the adnexal mass, their diagnostic performance is not as good as that reported in the original publications.
Adnexal Diseases↗
Regional response of myocardial acceleration during isovolumic contraction during dobutamine stress echocardiography: a color tissue Doppler study and comparison with angiocardiographic findings.
BACKGROUND: Color tissue Doppler imaging permits noninvasive quantitation of regional wall motion. In experimental studies, a new marker, the slope of the isovolumic contraction wave, isovolumic acceleration (IVA) was more insensitive to ventricular loading conditions than myocardial velocities. This study compared the regional response IVA to dobutamine stress echocardiography to angiographic findings. METHODS: The Myocardial Doppler in Stress Echocardiography (MYDISE) study prospectively recruited 149 consecutive patients with chest pain for dobutamine stress tissue Doppler echocardiography prior to coronary angiography. This color tissue Doppler database was analyzed for IVA in 1,192 basal and mid segments at rest and again at peak stress. Angiographic findings were compared to IVA and peak systolic velocities (PSV) in corresponding cardiac segments. The diagnostic accuracy of IVA to predict coronary artery stenosis was determined using cut-off values for three representative segments and with the MYDISE diagnostic model including eight segments. RESULTS: Regional IVA increased in a dose-dependent manner during dobutamine infusion. The response was blunted in the supply territory of stenosed coronary artery branches. IVA performed slightly better than PSV as single marker for coronary artery stenosis. A diagnostic model incorporating IVA and PSV was 85-95% accurate (area under receiver operating characterstic curves). CONCLUSIONS: Regional changes of isovolumic acceleration during dobutamine stress echocardiography reflect regional wall motion and can be used to predict coronary artery stenosis with similar accuracy as a model based on systolic myocardial velocities. As a single marker, IVA performed better than myocardial velocities.
Acceleration↗