Population-based algorithms
Dotaz
Zobrazit nápovědu
Six population-based methods for real-valued black box optimization are thoroughly compared in this article. One of them, Nelder-Mead simplex search, is rather old, but still a popular technique of direct search. The remaining five (POEMS, G3PCX, Cauchy EDA, BIPOP-CMA-ES, and CMA-ES) are more recent and came from the evolutionary computation community. The recently proposed comparing continuous optimizers (COCO) methodology was adopted as the basis for the comparison. The results show that BIPOP-CMA-ES reaches the highest success rates and is often also quite fast. The results of the remaining algorithms are mixed, but Cauchy EDA and POEMS are usually slow.
- MeSH
- algoritmy * MeSH
- benchmarking metody MeSH
- lidé MeSH
- numerická analýza pomocí počítače MeSH
- teoretické modely * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
- srovnávací studie MeSH
INTRODUCTION: Patients with clinically node-positive bladder cancer were historically considered to have uniformly poor prognosis and were frequently treated with palliative chemotherapy (CHT) only. Although retrospective data show that long-term survival with combined treatment (surgery + CHT) is possible in one-third of these patients, consensus on a treatment algorithm is still lacking. The aim of the study is to compare the efficacy of different treatment modalities based on data from a population-based cancer registry. PATIENTS AND METHODS: The study comprises 661 patients identified from the Czech National Cancer Registry (1996-2015) with cTanyN1-3M0 bladder cancer; 195 were treated with CHT alone, 234 underwent radical cystectomy alone (RC), and 232 received a combination of RC and perioperative CHT (RC + CHT). Multivariate Cox proportional hazard regression analyses were used to evaluate the effectiveness of various treatments. RESULTS: The 5-year OS for CHT alone, RC alone, and RC + CHT were 21.7% (95% confidence interval [CI], 15.4%-28.0%), 12.1% (95% CI, 7.4%-16.7%), and 25.4% (95% CI, 18.9%-31.9%), respectively (P < .001). The median survivals were 17, 10, and 23 months, respectively. In multivariate analysis, age > 60 years (hazard ratio, 1.29; 95% CI, 1.06-1.56; P = .011) and clinical stage cT3-4 (hazard ratio, 1.39; 95% CI, 1.12-1.71; P = .002) were negative predictors of survival. When compared with CHT, RC + CHT reduced the risk of overall mortality by 21% (P = .044). CONCLUSION: Approximately one-quarter of clinically node-positive patients may achieve long-term survival with combined treatment integrating RC and perioperative CHT. The overall survival of patients is significantly improved with a multimodal approach in comparison to CHT alone.
- MeSH
- adjuvantní chemoterapie metody MeSH
- analýza přežití MeSH
- cystektomie metody MeSH
- Kaplanův-Meierův odhad MeSH
- kombinovaná terapie MeSH
- lidé středního věku MeSH
- lidé MeSH
- lymfatické metastázy MeSH
- nádory močového měchýře farmakoterapie patologie chirurgie MeSH
- proporcionální rizikové modely MeSH
- registrace MeSH
- retrospektivní studie MeSH
- senioři MeSH
- staging nádorů MeSH
- výsledek terapie MeSH
- Check Tag
- lidé středního věku MeSH
- lidé MeSH
- mužské pohlaví MeSH
- senioři MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
- srovnávací studie MeSH
- Geografické názvy
- Česká republika MeSH
OBJECTIVES: Refeeding syndrome (RFS) can be a life-threatening metabolic condition after nutritional replenishment if not recognized early and treated adequately. There is a lack of evidence-based treatment and monitoring algorithm for daily clinical practice. The aim of the study was to propose an expert consensus guideline for RFS for the medical inpatient (not including anorexic patients) regarding risk factors, diagnostic criteria, and preventive and therapeutic measures based on a previous systematic literature search. METHODS: Based on a recent qualitative systematic review on the topic, we developed clinically relevant recommendations as well as a treatment and monitoring algorithm for the clinical management of inpatients regarding RFS. With international experts, these recommendations were discussed and agreement with the recommendation was rated. RESULTS: Upon hospital admission, we recommend the use of specific screening criteria (i.e., low body mass index, large unintentional weight loss, little or no nutritional intake, history of alcohol or drug abuse) for risk assessment regarding the occurrence of RFS. According to the patient's individual risk for RFS, a careful start of nutritional therapy with a stepwise increase in energy and fluids goals and supplementation of electrolyte and vitamins, as well as close clinical monitoring, is recommended. We also propose criteria for the diagnosis of imminent and manifest RFS with practical treatment recommendations with adoption of the nutritional therapy. CONCLUSION: Based on the available evidence, we developed a practical algorithm for risk assessment, treatment, and monitoring of RFS in medical inpatients. In daily routine clinical care, this may help to optimize and standardize the management of this vulnerable patient population. We encourage future quality studies to further refine these recommendations.
- MeSH
- algoritmy * MeSH
- hodnocení rizik normy MeSH
- hodnocení stavu výživy * MeSH
- hospitalizovaní pacienti MeSH
- konsensus MeSH
- lékařská praxe založená na důkazech normy MeSH
- lidé MeSH
- metody pro podporu rozhodování * MeSH
- plošný screening normy MeSH
- realimentační syndrom diagnóza prevence a kontrola MeSH
- rizikové faktory MeSH
- směrnice pro lékařskou praxi jako téma MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
The analysis and segmentation of articular cartilage magnetic resonance (MR) images belongs to one of the most commonly routine tasks in diagnostics of the musculoskeletal system of the knee area. Conventional regional segmentation methods, which are based either on the histogram partitioning (e.g., Otsu method) or clustering methods (e.g., K-means), have been frequently used for the task of regional segmentation. Such methods are well known as fast and well working in the environment, where cartilage image features are reliably recognizable. The well-known fact is that the performance of these methods is prone to the image noise and artefacts. In this context, regional segmentation strategies, driven by either genetic algorithms or selected evolutionary computing strategies, have the potential to overcome these traditional methods such as Otsu thresholding or K-means in the context of their performance. These optimization strategies consecutively generate a pyramid of a possible set of histogram thresholds, of which the quality is evaluated by using the fitness function based on Kapur's entropy maximization to find the most optimal combination of thresholds for articular cartilage segmentation. On the other hand, such optimization strategies are often computationally demanding, which is a limitation of using such methods for a stack of MR images. In this study, we publish a comprehensive analysis of the optimization methods based on fuzzy soft segmentation, driven by artificial bee colony (ABC), particle swarm optimization (PSO), Darwinian particle swarm optimization (DPSO), and a genetic algorithm for an optimal thresholding selection against the routine segmentations Otsu and K-means for analysis and the features extraction of articular cartilage from MR images. This study objectively analyzes the performance of the segmentation strategies upon variable noise with dynamic intensities to report a segmentation's robustness in various image conditions for a various number of segmentation classes (4, 7, and 10), cartilage features (area, perimeter, and skeleton) extraction preciseness against the routine segmentation strategies, and lastly the computing time, which represents an important factor of segmentation performance. We use the same settings on individual optimization strategies: 100 iterations and 50 population. This study suggests that the combination of fuzzy thresholding with an ABC algorithm gives the best performance in the comparison with other methods as from the view of the segmentation influence of additive dynamic noise influence, also for cartilage features extraction. On the other hand, using genetic algorithms for cartilage segmentation in some cases does not give a good performance. In most cases, the analyzed optimization strategies significantly overcome the routine segmentation methods except for the computing time, which is normally lower for the routine algorithms. We also publish statistical tests of significance, showing differences in the performance of individual optimization strategies against Otsu and K-means method. Lastly, as a part of this study, we publish a software environment, integrating all the methods from this study.
INTRODUCTION: The aim of the study was to assess the differences in key parameters of type 1 diabetes (T1D) control associated with treatment and monitoring modalities including newly introduced hybrid closed-loop (HCL) algorithm in children and adolescents with T1D (CwD) using the data from the population-wide pediatric diabetes registry ČENDA. METHODS: CwD younger than 19 years with T1D duration >1 year were included and divided according to the treatment modality and type of CGM used: multiple daily injection (MDI), insulin pump without (CSII) and with HCL function, intermittently scanned continuous glucose monitoring (isCGM), real-time CGM (rtCGM), and intermittent or no CGM (noCGM). HbA1c, times in glycemic ranges, and glucose risk index (GRI) were compared between the groups. RESULTS: Data of a total of 3,251 children (mean age 13.4 ± 3.8 years) were analyzed. 2,187 (67.3%) were treated with MDI, 1,064 (32.7%) with insulin pump, 585/1,064 (55%) with HCL. The HCL users achieved the highest median TIR 75.4% (IQR 6.3) and lowest GRI 29.1 (7.8), both p < 0.001 compared to other groups, followed by MDI rtCGM and CSII groups with TIR 68.8% (IQR 9.0) and 69.0% (7.5), GRI 38.8 (12.5) and 40.1 (8.5), respectively (nonsignificant to each other). These three groups did not significantly differ in their HbA1c medians (51.8 [IQR 4.5], 50.7 [4.5], and 52.7 [5.7] mmol/mol, respectively). NoCGM groups had the highest HbA1c and GRI and lowest TIR regardless of the treatment modality. CONCLUSION: This population-based study shows that the HCL technology is superior to other treatment modalities in CGM-derived parameters and should be considered as a treatment of choice in all CwD fulfilling the indication criteria.
- MeSH
- diabetes mellitus 1. typu * farmakoterapie MeSH
- dítě MeSH
- glykovaný hemoglobin MeSH
- hypoglykemika terapeutické užití MeSH
- inzulin terapeutické užití MeSH
- krevní glukóza MeSH
- lidé MeSH
- mladiství MeSH
- regulace glykemie MeSH
- selfmonitoring glykemie MeSH
- Check Tag
- dítě MeSH
- lidé MeSH
- mladiství MeSH
- Publikační typ
- časopisecké články MeSH
Východiska: Cílem této práce je představit algoritmus separace plazmatických buněk ze vzorků kostní dřeně pacientů s mnohočetným myelomem. Zisk vysoce čistých buněčných populací je základní podmínkou aplikace moderních výzkumných postupů u tohoto onemocnění. Materiál a metody: Vzorky kostní dřeně byly získány od pacientů z Interní hematoonkologické kliniky FN Brno. Kostní dřeň byla nejprve zbavena červené složky (metodou hustotní gradientové centrifugace nebo lyzace), plazmatické buňky byly označeny monoklonální protilátkou proti syndecanu-1 (CD138) a separovány magneticky nebo na buněčném sorteru. Čistota separované populace byla vyhodnocena na průtokovém cytometru, případně morfologicky. Výsledky: Paralelně, magnetickou a fluorescenční separací, bylo zpracováno 28 vzorků kostní dřeně a byla vyhodnocena čistota separovaných frakcí. Na základě statistického hodnocení výsledných čistot jak v celém souboru vzorků, tak ve skupinách podle vstupního zastoupení plazmatických buněk byl navržen algoritmus separace s cut-off hodnotou 5 % plazmatických buněk v mononukleární frakci KD: vzorky s < 5 % plazmatických buněk jsou nadále tříděny na buněčném sorteru, vzorky s ? 5 % plazmatických buněk jsou separovány na magnetickém separátoru. Po ročním vyhodnocení uplatnění tohoto algoritmu na souboru 210 vzorků kostní dřeně se medián čistoty separovaných plazmatických buněk zvedl z 62,4 % (0,4–99,6 %) na 94,0 % (23,9–100 %). Závěr: Zavedení metodiky fluorescenčního třídění výrazně přispělo k celkovému zvýšení úspěšnosti separace plazmatických buněk ze vzorků kostní dřeně, a to především u vzorků s jejich nízkým vstupním zastoupením, kde dosud využívaná metodika magnetické separace není dostatečně účinná. Otevřela se tím také cesta k separaci plazmatických buněk ze vzorků kostní dřeně od jedinců s monoklonální gamapatií nejasného významu, kde je zastoupení plazmatických buněk typicky velmi nízké (desetiny, max. jednotky procent).
Backgrounds: The aim of this paper is to present an algorithm for plasma cell separation from bone marrow samples of multiple myeloma patients. The main prerequisite for applying modern research methods in this disease is gaining pure cell populations. Material and Methods: Bone marrow samples were collected from outpatients or inpatients of the Internal Haematology and Oncology Clinic of the Faculty Hospital Brno, after they had signed an Informed Consent Form. The bone marrow was first depleted of red cells (by density gradient centrifugation or erythrolysis), plasma cells were labelled by monoclonal antibody against syndecan-1 (CD138) and separated either magnetically or by cell sorter. The purity of separated population was evaluated by flow cytometry or, alternatively, morfologically. Results: We processed 28 bone marrow samples, in parallel, by magnetic or fluorescence-based separation, and we evaluated the purity of the separated fractions. Based on a statistical evaluation of resulting purities in the entire sample set as well as the individual groups divided according to the initial plasma cell content, a separation algorithm was proposed with a cut-off value of 5% of plasma cells in mononuclear fraction of bone marrow: samples with less than 5% of plasma cells are henceforth separated on cell sorter, samples with more than 5% are separated magnetically. The effectiveness of this algorithm was evaluated after the first year of its application on a dataset of 210 bone marrow samples: median purity of the separated plasma cells increased from 62.4% (0.4–99.6%) to 94.0% (23.9–100%). Conclusion: The introduction of a fluorescence-based separation markedly increased the effectiveness of plasma cell separation from bone marrow samples, mainly in samples with low plasma cell content where magnetic separation used thus far is not sufficient. This finding also opened a door for plasma cell separation of bone marrow samples from patients with monoclonal gammopathy of undetermined significance, where plasma cell count is typically below or just over one percent.
- Klíčová slova
- magnetická separace, buněčný sorter,
- MeSH
- algoritmy MeSH
- financování organizované MeSH
- imunomagnetická separace MeSH
- kostní dřeň patologie MeSH
- lidé MeSH
- mnohočetný myelom patologie MeSH
- monoklonální gamapatie nejasného významu MeSH
- plazmatické buňky patologie MeSH
- průtoková cytometrie MeSH
- Check Tag
- lidé MeSH
Od ledna 2014 bylo v České republice zahájeno adresné zvaní pojištěnců do programů screeningu zhoubných nádorů, konkrétně screeningu nádorů hrdla děložního a nádorů prsu (mamografického screeningu) u žen, a dále nádorů tlustého střeva a konečníku (kolorekta) u žen a mužů. Cílem je posílit stávající programy prevence a zvýšit dosud nedostatečnou účast v nich – proto jsou adresně zváni občané, kteří se těchto programů dlouhodobě neúčastní a riskují tak závažné nádorové onemocnění. Projekt je koordinován Ministerstvem zdravotnictví ČR ve spolupráci se zástupci dotčených odborných společností (gynekologie, gastroenterologie, gastrointestinální onkologie, radiodiagnostika, všeobecné lékařství, PL), zástupců zdravotních pojišťoven a dalších expertů jmenovaných ministrem zdravotnictví. Své klienty (pojištěnce) zvou k preventivním vyšetřením všechny zdravotní pojišťovny, které také hradí veškerá potřebná vyšetření. Projekt je realizován s pomocí finančních prostředků z fondů EU. Tento článek popisuje plošně implementovanou metodiku adresného zvaní, její datovou základnu a první výsledky projektu z první poloviny roku 2014, kdy bylo pozváno téměř 1,3 mil. českých občanů.
In January 2014, a programme of personalised invitations was launched in the Czech Republic, with the objective of inviting insured persons to cancer screening programmes; namely breast cancer screening and cervical cancer screening in women, and colorectal cancer screening both in women and men. This programme aims at strengthening the current cancer prevention programmes, and to increase the currently inadequate participation of the target population in these programmes; therefore, personalised invitations are sent to citizens who have not participated in these programmes for several years and therefore at risk of developing a serious disease. The project is coordinated by the Czech Ministry of Health in cooperation with the expert medical societies involved (gynaecology, gastroenterology, gastrointestinal oncology, diagnostic radiology, general practice), representatives of health care payers, and other experts nominated by the Minister of Health. All health care payers invite their clients (insured persons) to preventive check-ups, covering all examinations needed. The project has been realised with the assistance of financial resources from EU funds. This article describes the methodology of personalised invitations which has been implemented nationwide, its data background, and the first results of the project in the first half of 2014, when almost 1.3 million Czech citizens were invited. Key words: personalised invitation – screening – cancer – prevention – general practitioner – gynaecologist This study was supported by the project 36/14//NAP “Development and implementation of methodology for the evaluation of effectiveness of personalised invitations of citizens to cancer screening programmes” as part of the programme of the Czech Ministry of Health “National action plans and conceptions”. The authors declare they have no potential conflicts of interest concerning drugs, products, or services used in the study. The Editorial Board declares that the manuscript met the ICMJE “uniform requirements” for biomedical papers. Submitted: 29. 8. 2014 Accepted: 30. 9. 2014
- Klíčová slova
- adresné zvaní,
- MeSH
- algoritmy MeSH
- časná detekce nádoru MeSH
- databáze jako téma MeSH
- dospělí MeSH
- hodnocení programu statistika a číselné údaje MeSH
- kolorektální nádory * prevence a kontrola MeSH
- lidé středního věku MeSH
- lidé MeSH
- mladiství MeSH
- mladý dospělý MeSH
- nádory děložního čípku * prevence a kontrola MeSH
- nádory prsu * prevence a kontrola MeSH
- pacientův souhlas se zdravotní péčí * statistika a číselné údaje MeSH
- plošný screening * metody organizace a řízení statistika a číselné údaje MeSH
- poštovní služby MeSH
- připomínače a organizéry MeSH
- senioři MeSH
- všeobecné zdravotní pojištění MeSH
- výběr pacientů MeSH
- zlepšení kvality MeSH
- Check Tag
- dospělí MeSH
- lidé středního věku MeSH
- lidé MeSH
- mladiství MeSH
- mladý dospělý MeSH
- mužské pohlaví MeSH
- senioři MeSH
- ženské pohlaví MeSH
- Publikační typ
- práce podpořená grantem MeSH
- Geografické názvy
- Česká republika MeSH
Identification of risk factors for transient ischemic attack (TIA) is crucial for patients with atrial fibrillation (AF). However, identifying risk factors in young patients with low-risk AF is difficult, because the incidence of TIA in such patients is very low, which would result in traditional multiple logistic regression not being able to successfully identify the risk factors in such patients. Therefore, a novel algorithm for identifying risk factors for TIA is necessary. We thus propose a novel algorithm, which combines multiple correspondence analysis and hierarchical cluster analysis and uses the Taiwan National Health Insurance Research Database, a population-based database, to determine risk factors in these patients. The results of this study can help clinicians or patients with AF in preventing TIA or stroke events as early as possible.
Techniky strojového učení jsou metody, které umožní vytvořit z trénovací množiny případů model pro kategorie dat tak, že mohou být nové (neznámé) případy zařazeny do jedné nebo více kategorií schématem odpovídajícím modelu. Pro tento typ analýzy jsou velmi vhodná data ze studií sledujících určitou skupinu osob s opakovaným sběrem dat stejného typu. K vyhledávání znalostí z medicínských dat bylo užito různých algoritmů strojového učení. Bylo testováno několik algoritmů tak, aby bylo možno pokrýt většinu způsobů učení s učitelem. Byly provedeny dva typy pokusů. Jeden hledal vztahy mezi atributy, druhý testoval predikci budoucích příhod. Pro pokusy v tomto sdělení byla užita data z dvacet let trvající longitudinální primárně preventivní studie rizikových faktorů (RF) aterosklerózy u mužů středního věku. Studie se nazývá STULONG (LONGitudinal STUdy). Výsledky ukazují, že některé metody předpovídají některé poruchy lépe než jiné a že je tedy vhodné použít všechny algoritmy najednou a posuzovat spolehlivost výsledku na základě známého trendu každé metody. Algoritmy strojového učení byly také použity k předpovědi příčiny úmrtí. V tomto případě byly výsledky nevalné, pravděpodobně pro malé množství informace ve vstupních položkách v datového souboru.
Machine learning techniques are methods that given a training set of examples infer a model for the categories of the data, so that new (unknown) examples could be assigned to one or more categories by pattern matching within the model. The data from follow-up studies with repeated collection of the same type of data are very suitable for this analysis. Machine learning algorithms belonging to a variety of paradigms have been applied to knowledge discovery on medical data. All the used algorithms belong to the supervised learning paradigm. Several algorithms have been tested, trying to cover most of the kinds of supervised learning. Two kinds of experiments have been carried out. The first is intended to discover associations between attributes. The second kind is intended to test prediction of future disorders. For the experiments in this paper the data used was from the twenty years lasting primary preventive longitudinal study of the risk factors (RF) of atherosclerosis in middle aged men. Study is named STULONG (LONGitudinal STUdy). The results show that some methods predict some disorders better than others, so it is interesting to use all the algorithms at a time and consider the result confidence based upon the known tendency of each method. The machine learning algorithms have been also used in the prediction of death cause, obtaining poor results in this case, maybe due to the small amount of information (entries) of this type in the dataset.
- Klíčová slova
- dobývání znalostí, strojové učení s učitelem, vytěžování z biomedicínských dat, rizikové faktory aterosklerózy,
- MeSH
- algoritmy MeSH
- ateroskleróza diagnóza MeSH
- databáze faktografické MeSH
- financování organizované MeSH
- lidé středního věku MeSH
- lidé MeSH
- metody pro podporu rozhodování MeSH
- prognóza MeSH
- rizikové faktory MeSH
- systémy pro podporu klinického rozhodování MeSH
- ukládání a vyhledávání informací MeSH
- znalostní báze MeSH
- Check Tag
- lidé středního věku MeSH
- lidé MeSH
- mužské pohlaví MeSH
The sine-cosine algorithm (SCA) is a new population-based meta-heuristic algorithm. In addition to exploiting sine and cosine functions to perform local and global searches (hence the name sine-cosine), the SCA introduces several random and adaptive parameters to facilitate the search process. Although it shows promising results, the search process of the SCA is vulnerable to local minima/maxima due to the adoption of a fixed switch probability and the bounded magnitude of the sine and cosine functions (from -1 to 1). In this paper, we propose a new hybrid Q-learning sine-cosine- based strategy, called the Q-learning sine-cosine algorithm (QLSCA). Within the QLSCA, we eliminate the switching probability. Instead, we rely on the Q-learning algorithm (based on the penalty and reward mechanism) to dynamically identify the best operation during runtime. Additionally, we integrate two new operations (Lévy flight motion and crossover) into the QLSCA to facilitate jumping out of local minima/maxima and enhance the solution diversity. To assess its performance, we adopt the QLSCA for the combinatorial test suite minimization problem. Experimental results reveal that the QLSCA is statistically superior with regard to test suite size reduction compared to recent state-of-the-art strategies, including the original SCA, the particle swarm test generator (PSTG), adaptive particle swarm optimization (APSO) and the cuckoo search strategy (CS) at the 95% confidence level. However, concerning the comparison with discrete particle swarm optimization (DPSO), there is no significant difference in performance at the 95% confidence level. On a positive note, the QLSCA statistically outperforms the DPSO in certain configurations at the 90% confidence level.
- MeSH
- algoritmy * MeSH
- heuristika * MeSH
- počítačová simulace MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH