Genetic algorithm
Dotaz
Zobrazit nápovědu
Automatizace a robotizace i v medicíně je vítaným pokrokem pro diagnostiku a léčbu. Aby však tyto metody byly opravdu účinné, nesmí zakrývat diagnostické tápání, alibistickou výkonnost a bezcílné hledání, musí být efektivně indikované. Paradoxně se zaváděním těchto metod např. v molekulární genetice došlo k ocenění významu -ruční a mentální- práce lékaře, který může zajistit, aby indikace těchto moderních metod byly cílené a tedy rychlé a nenákladné. Docenění tak dosáhla spolu s genealogií i genetická dysmorfologie, jako účinná diagnostická metoda genetických syndromů.
Automation and robotics are welcomed progress also in the medicine for the diagnostics and treatment. But, with a view to make these methods really effective, they should not mask a diagnostic fumble, alibistic productivity and aimless searching, they should be effectively indicated. Paradox is, that with an implementation of such methods, e.g. in molecular genetics, an importance of -manual and mental- work of doctor, who can provide aimed, that is fast and inexpensive indications of these modern methods, has been valued. Together with genealogy a genetic dysmorphology has been valued, as an efficient diagnostic method of genetic syndromes.
- MeSH
- algoritmy MeSH
- diagnostické techniky molekulární MeSH
- dítě MeSH
- finanční podpora výzkumu jako téma MeSH
- genetické nemoci vrozené diagnóza etiologie MeSH
- lékařská genetika MeSH
- lidé MeSH
- mutace MeSH
- příznaky a symptomy diagnóza MeSH
- syndrom diagnóza genetika MeSH
- Check Tag
- dítě MeSH
- lidé MeSH
- Publikační typ
- přehledy MeSH
- srovnávací studie MeSH
Diagnostický algoritmus svalových dystrofií se v uplynulé dekádě výrazně změnil, a to zejména díky rozvoji a zvýšení dostupnosti molekulárně genetických a zobrazovacích metod. Aktuálně, kromě podrobně odebrané anamnézy, detailního klinického vyšetření, biochemického a elektrofyziologického testování, přibylo vyšetření svalů magnetickou rezonancí a nové metody molekulárně genetického vyšetření, naopak svalová biopsie přestala být nezbytnou metodou v diagnostice hereditárních myopatií. Rutinní provádění MRI u pacientů se svalovými dystrofiemi umožnilo odhalení a popsání vzorců svalového postižení (pattern of recognition) charakteristických pro určité klinické jednotky. Molekulárně genetická vyšetření pak, jako jediná, umožňují stanovení definitivní diagnózy na základě detekce kauzální mutace. Pro lepší orientaci v běžné ambulantní praxi popisuje článek hlavní kroky vedoucí k odhalení jednotlivých typů svalových dystrofií s ohledem na úroveň dnešních znalostí a zkušeností.
The diagnostics algorithm of muscular dystrophies has changed significantly over the past decade, mainly due to the development and increase of availability of molecular genetics and imaging methods. The golden standard of detailed medical history, attentive clinical examination, biochemical and electrophysiological testing now includes also magnetic resonance imaging and targeted or more extensive molecular genetic examinations, while muscle biopsy ceased to be the first choice method in the diagnostic process of hereditary myopathies. Routine MRI performance in patients with muscle. dystrophies allowed the detection and description of patterns of recognition characteristic for certain clinical units. Molecular genetic examinations as the only one allow definitive diagnosis to be determined by causal mutation detection. For better orientation in common outpatient practice, the article describes the crucial steps leading to the discovery of individual types of muscular dystrophy with respect to the level of today's knowledge and experience.
- MeSH
- biopsie MeSH
- diferenciální diagnóza MeSH
- elektromyografie metody MeSH
- fenotyp MeSH
- genetické testování metody MeSH
- kosterní svaly diagnostické zobrazování MeSH
- kreatinkinasa krev MeSH
- lidé MeSH
- magnetická rezonanční tomografie MeSH
- nemoci svalů diagnostické zobrazování diagnóza metabolismus MeSH
- svalové dystrofie * diagnostické zobrazování diagnóza MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- přehledy MeSH
PURPOSE: Genetic testing in consanguineous families advances the general comprehension of pathophysiological pathways. However, short stature (SS) genetics remain unexplored in a defined consanguineous cohort. This study examines a unique pediatric cohort from Sulaimani, Iraq, aiming to inspire a genetic testing algorithm for similar populations. METHODS: Among 280 SS referrals from 2018-2020, 64 children met inclusion criteria (from consanguineous families; height ≤ -2.25 SD), 51 provided informed consent (30 females; 31 syndromic SS) and underwent investigation, primarily via exome sequencing. Prioritized variants were evaluated by the American College of Medical Genetics and Genomics standards. A comparative analysis was conducted by juxtaposing our findings against published gene panels for SS. RESULTS: A genetic cause of SS was elucidated in 31 of 51 (61%) participants. Pathogenic variants were found in genes involved in the GH-IGF-1 axis (GHR and SOX3), thyroid axis (TSHR), growth plate (CTSK, COL1A2, COL10A1, DYM, FN1, LTBP3, MMP13, NPR2, and SHOX), signal transduction (PTPN11), DNA/RNA replication (DNAJC21, GZF1, and LIG4), cytoskeletal structure (CCDC8, FLNA, and PCNT), transmembrane transport (SLC34A3 and SLC7A7), enzyme coding (CYP27B1, GALNS, and GNPTG), and ciliogenesis (CFAP410). Two additional participants had Silver-Russell syndrome and 1 had del22q.11.21. Syndromic SS was predictive in identifying a monogenic condition. Using a gene panel would yield positive results in only 10% to 33% of cases. CONCLUSION: A tailored testing strategy is essential to increase diagnostic yield in children with SS from consanguineous populations.
- MeSH
- algoritmy MeSH
- dítě MeSH
- genetické testování * metody MeSH
- lidé MeSH
- mladiství MeSH
- mutace genetika MeSH
- nanismus genetika diagnóza MeSH
- pokrevní příbuzenství * MeSH
- poruchy růstu genetika diagnóza MeSH
- předškolní dítě MeSH
- rodokmen MeSH
- sekvenování exomu metody MeSH
- tělesná výška genetika MeSH
- Check Tag
- dítě MeSH
- lidé MeSH
- mladiství MeSH
- mužské pohlaví MeSH
- předškolní dítě MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- Geografické názvy
- Irák MeSH
Objective.The current practices of designing neural networks rely heavily on subjective judgment and heuristic steps, often dictated by the level of expertise possessed by architecture designers. To alleviate these challenges and streamline the design process, we propose an automatic method, a novel approach to enhance the optimization of neural network architectures for processing intracranial electroencephalogram (iEEG) data.Approach.We present a genetic algorithm, which optimizes neural network architecture and signal pre-processing parameters for iEEG classification.Main results.Our method improved the macroF1 score of the state-of-the-art model in two independent datasets, from St. Anne's University Hospital (Brno, Czech Republic) and Mayo Clinic (Rochester, MN, USA), from 0.9076 to 0.9673 and from 0.9222 to 0.9400 respectively.Significance.By incorporating principles of evolutionary optimization, our approach reduces the reliance on human intuition and empirical guesswork in architecture design, thus promoting more efficient and effective neural network models. The proposed method achieved significantly improved results when compared to the state-of-the-art benchmark model (McNemar's test,p≪ 0.01). The results indicate that neural network architectures designed through machine-based optimization outperform those crafted using the subjective heuristic approach of a human expert. Furthermore, we show that well-designed data preprocessing significantly affects the models' performance.
- MeSH
- elektroencefalografie metody MeSH
- elektrokortikografie * MeSH
- lidé MeSH
- neuronové sítě * MeSH
- počítačové zpracování signálu MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
BACKGROUND: Prediction of susceptibility to multiple sclerosis (MS) might have important clinical applications, either as part of a diagnostic algorithm or as a means to identify high-risk individuals for prospective studies. We investigated the usefulness of an aggregate measure of risk of MS that is based on genetic susceptibility loci. We also assessed the added effect of environmental risk factors that are associated with susceptibility for MS. METHODS: We created a weighted genetic risk score (wGRS) that includes 16 MS susceptibility loci. We tested our model with data from 2215 individuals with MS and 2189 controls (derivation samples), a validation set of 1340 individuals with MS and 1109 controls taken from several MS therapeutic trials (TT cohort), and a second validation set of 143 individuals with MS and 281 controls from the US Nurses' Health Studies I and II (NHS/NHS II), for whom we also have data on smoking and immune response to Epstein-Barr virus (EBV). FINDINGS: Individuals with a wGRS that was more than 1.25 SD from the mean had a significantly higher odds of MS in all datasets. In the derivation sample, the mean (SD) wGRS was 3.5 (0.7) for individuals with MS and 3.0 (0.6) for controls (p<0.0001); in the TT validation sample, the mean wGRS was 3.4 (0.7) for individuals with MS versus 3.1 (0.7) for controls (p<0.0001); and in the NHS/NHS II dataset, the mean wGRS was 3.4 (0.8) for individuals with MS versus 3.0 (0.7) for controls (p<0.0001). In the derivation cohort, the area under the receiver operating characteristic curve (C statistic; a measure of the ability of a model to discriminate between individuals with MS and controls) for the genetic-only model was 0.70 and for the genetics plus sex model was 0.74 (p<0.0001). In the TT and NHS cohorts, the C statistics for the genetic-only model were both 0.64; adding sex to the TT model increased the C statistic to 0.72 (p<0.0001), whereas adding smoking and immune response to EBV to the NHS model increased the C statistic to 0.68 (p=0.02). However, the wGRS does not seem to be correlated with the conversion of clinically isolated syndrome to MS. INTERPRETATION: The inclusion of 16 susceptibility alleles into a wGRS can modestly predict MS risk, shows consistent discriminatory ability in independent samples, and is enhanced by the inclusion of non-genetic risk factors into the algorithm. Future iterations of the wGRS might therefore make a contribution to algorithms that can predict a diagnosis of MS in a clinical or research setting.
- MeSH
- alely MeSH
- algoritmy * MeSH
- dítě MeSH
- dospělí MeSH
- genotyp MeSH
- hodnocení rizik MeSH
- jednonukleotidový polymorfismus genetika MeSH
- kohortové studie MeSH
- lidé středního věku MeSH
- lidé MeSH
- lokus kvantitativního znaku MeSH
- mladiství MeSH
- odds ratio MeSH
- prediktivní hodnota testů MeSH
- předškolní dítě MeSH
- rizikové faktory MeSH
- roztroušená skleróza * epidemiologie genetika MeSH
- senioři MeSH
- životní prostředí MeSH
- Check Tag
- dítě MeSH
- dospělí MeSH
- lidé středního věku MeSH
- lidé MeSH
- mladiství MeSH
- mužské pohlaví MeSH
- předškolní dítě MeSH
- senioři MeSH
- ženské pohlaví MeSH
- Publikační typ
- práce podpořená grantem MeSH
- Research Support, N.I.H., Extramural MeSH
BACKGROUND: Identification of coordinately regulated genes according to the level of their expression during the time course of a process allows for discovering functional relationships among genes involved in the process. RESULTS: We present a single class classification method for the identification of genes of similar function from a gene expression time series. It is based on a parallel genetic algorithm which is a supervised computer learning method exploiting prior knowledge of gene function to identify unknown genes of similar function from expression data. The algorithm was tested with a set of randomly generated patterns; the results were compared with seven other classification algorithms including support vector machines. The algorithm avoids several problems associated with unsupervised clustering methods, and it shows better performance then the other algorithms. The algorithm was applied to the identification of secondary metabolite gene clusters of the antibiotic-producing eubacterium Streptomyces coelicolor. The algorithm also identified pathways associated with transport of the secondary metabolites out of the cell. We used the method for the prediction of the functional role of particular ORFs based on the expression data. CONCLUSION: Through analysis of a time series of gene expression, the algorithm identifies pathways which are directly or indirectly associated with genes of interest, and which are active during the time course of the experiment.
