SEARCH · PubMed Health

Results for “Optimization”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,333 records · Page 74Linked to original sources

PubMed1995

Treatment planning optimization by conjugate gradients and simulated annealing methods in stereotactic radiosurgery.

PURPOSE: This paper presents a new optimization method of treatment planning in linac stereotactic radiosurgery. METHODS AND MATERIALS: On a workstation integrating x-rays, computed tomography (CT), magnetic resonance imaging (MRI), and digital subtracted angiography (DSA) images, we first determine the outlines of the target volume and surrounding healthy tissues to spare. To achieve complete optimization of the treatment plans, this method decomposes the optimization process in two steps. The position of the isocenters and the diameter of the collimators are first deduced by a conjugate gradients method, from the position and size of ellipsoids or spheres modeling the target volume. The other irradiation parameters, such as the isocenter dose, the aperture, and the weight of each irradiation plane and of their irradiation sectors are finally deduced by a simulated annealing optimization algorithm. RESULTS: The system can perform multitarget/multisector treatment plans that are automatically obtained in a satisfactory time (as a rule, 20 min for a two-target irradiation), much faster than the time needed for a manual treatment planning. We present the results in two cases: the simulation of a single-target treatment and a two-target real treatment with constraints. In these two cases, we can control the dose received by target and sensitive volumes. CONCLUSION: This method achieves an excellent conformation of the estimated isodose curves with the outlines of the target volume, which allows us to avoid the surrounding healthy tissues, thanks to the different weighting factors given on each volume concerned according to the importance we grant to each of them.

Angiography, Digital Subtraction↗

PubMed1995

Optimization of rotational radiotherapy treatment planning.

PURPOSE: Rotational therapy treatment planning for rotationally symmetric geometry of tumor and healthy tissue provides an important example of testing various approaches to optimizing dose distributions for therapeutic x-ray irradiations. In this article, dose distribution optimization is formulated as a variational problem. This problem is solved analytically and numerically. METHODS AND MATERIALS: The classical Lagrange method is used to derive equations and inequalities that give necessary conditions for minimizing the mean-square deviation between the ideal dose distribution and the achievable dose distribution. The solution of the resulting integral equation with Cauchy kernel is used to derive analytical formulas for the minimizing irradiation intensity function. RESULTS: The solutions are evaluated numerically and the graphs of the minimizing intensity functions and the corresponding dose distributions are presented. CONCLUSIONS: The optimal solutions obtained using the mean-square criterion lead to significant underdosage in some areas of the tumor volume. Possible solutions to this shortcoming are investigated and medically more appropriate criteria for optimization are proposed for future investigations.

Humans↗

PubMed1982

Preferential codon usage in prokaryotic genes: the optimal codon-anticodon interaction energy and the selective codon usage in efficiently expressed genes.

By considering the nucleotide sequence of several highly expressed coding regions in bacteriophage MS2 and mRNAs from Escherichia coli, it is possible to deduce some rules which govern the selection of the most appropriate synonymous codons NNU or NNC read by tRNAs having GNN, QNN or INN as anticodon. The rules fit with the general hypothesis that an efficient in-phase translation is facilitated by proper choice of degenerate codewords promoting a codon-anticodon interaction with intermediate strength (optimal energy) over those with very strong or very weak interaction energy. Moreover, codons corresponding to minor tRNAs are clearly avoided in these efficiently expressed genes. These correlations are clearcut in the normal reading frame but not in the corresponding frameshift sequences +1 and +2. We hypothesize that both the optimization of codon-anticodon interaction energy and the adaptation of the population to codon frequency or vice versa in highly expressed mRNAs of E. coli are part of a strategy that optimizes the efficiency of translation. Conversely, codon usage in weakly expressed genes such as repressor genes follows exactly the opposite rules. It may be concluded that, in addition to the need for coding an amino acid sequence, the energetic consideration for codon-anticodon pairing, as well as the adaptation of codons to the tRNA population, may have been important evolutionary constraints on the selection of the optimal nucleotide sequence.

Anticodon↗

PubMed1980

Neurological development in very-low-birthweight infants. Application of a standardized examination and Prechtl's optimality concept in routine evaluations.

Modern methods of newborn intensive care have greatly improved long-term morbidity rates of very-low-birthweight (VLBW) infants. Our standardized neurological examination was applied to 3- and 6-month-old infants and expressed as a score by using Prechtl's optimality concept. Among 98 VLBW infants, 56 were at high risk because of perinatal complications with possible cerebral distress and 42 had no complications. The VLBW infants were also divided into AGA (61) and SGA (37) babies. In addition, 29 full-term infants were enrolled as controls. A statistical analysis of the optimality scores revealed that all VLBW infants had significantly lower mean scores at the corrected age of 3 months than the full-term controls. Intrauterine growth retardation and perinatal cerebral distress clearly depress the optimality scores. At 6 months only infants with high perinatal risk had considerably lower scores than the age controls. Two-thirds of all VLBW infants were found to have a developmental delay and/or a neurological deficit at the corrected age of 3 months. At age 6 months, however, a marked catch-up and/or self-repair had occurred, as was documented by about 70% of normal optimality scores. Head circumference measurements over the first year of life can be an important assisting factor in developmental assessments. If a microcephalic infant does not show higher than normal head growth velocity a severe developmental delay or neurological deficit must be expected. At 12 months the Bayley scores of psychomotor development have served to complement the preceding neurological and head growth findings.

Cephalometry↗

PubMed1994

In search of the best stimulus: an optimization procedure for finding efficient stimuli in the cat auditory cortex.

Units in the auditory cortex of cats respond to a large variety of stimuli: pure tones, AM- and FM-modulated signals, clicks, wideband noise, natural sounds, and more. However, no single family of sounds was found to be optimal (in the sense that oriented lines are optimal in the visual cortex). The search for optimal complex sounds is hard because of the high dimensionality of the space of interesting sounds. In an effort to overcome this problem, an automatic search procedure for finding efficient stimuli in high-dimensional sound spaces was developed. This procedure chooses the stimuli to be presented according to the responses to past stimuli, trying to increase the strength of the response. The results of applying this method to recordings of population activity in the primary auditory cortex of cats are described. The search was applied to single tones, two-tone stimuli, four-tone stimuli and to a two-dimensional subset of nine-tone stimuli, parametrized by the center frequency and the fixed difference between adjacent frequencies. The method was able to find efficient stimuli, and its performance improved with the dimension of the sound spaces. Efficient stimuli, found in different optimization runs using population activity recorded from the same electrode, often shared similar frequencies and pairs of frequencies, and tended to evoke similar levels of activity. This result indicates that a global analysis of the location of spectral peaks is performed at the level of the auditory cortex.

Acoustic Stimulation↗

PubMed1992

Optimization schemes for selective excitations: application to the DIGGER pulses.

In this work, two distinct approaches to the tailoring of selective radiofrequency (RF) pulses were applied to a cos-sinc pulse of the DIGGER sequence used in localized spectroscopy. Ideally, three such pulses combined with a gradient in each direction destroy the Mz component of the magnetization everywhere but in the volume of interest. In the first approach, the optimal RF amplitude modulation is found by minimizing the difference between the ideal and the computed Mz profiles. In the second strategy, the RF pulse envelope is adjusted by optimization of the tip angle profile. Computed slice profiles optimized by each of these methods have been compared to experimental results. Simulations as well as experiments show that the second approach, which optimizes tip angles, is the most efficient.

Magnetic Resonance Spectroscopy↗

PubMed1994

Optimal use of directional coronary atherectomy is required to ensure long-term angiographic benefit: a study with matched procedural outcome after atherectomy and angioplasty.

OBJECTIVES: This study was designed to examine whether restenosis is related to the extent or mechanism of lumen improvement and to explore angiographic determinants of optimal atherectomy. BACKGROUND: Directional atherectomy induces a greater extent of immediate gain and late loss but has not been found to yield a better late angiographic lumen than angioplasty in randomized trials. The difference in lumen renarrowing may be related to either the extent or the mechanism of immediate gain. The design of previous studies has precluded the detection of a device-specific effect on restenosis. METHODS: A retrospective analysis was based on matching a prospectively collected series of 80 native coronary arteries successfully treated with atherectomy with a prospectively collected series of 80 native coronary arteries successfully treated with balloon angioplasty. Angiographic analysis was performed in 160 lesions to explore whether a specific device-related effect exists. Multivariate analyses were performed to determine the correlates of minimal lumen diameter at follow-up and late lumen loss and to identify the procedural characteristics for optimal atherectomy. RESULTS: Matching resulted in two comparable groups with equivalent baseline clinical and stenosis characteristics. By study design, atherectomy and angioplasty resulted in similar mean (+/- SD) immediate lumen gain (1.15 +/- 0.44 vs. 1.10 +/- 0.40 mm, p = 0.50). However, lumen loss was more pronounced after atherectomy, and, thus, the minimal lumen diameter at follow-up differed significantly between the two groups (1.78 +/- 0.57 vs. 2.00 +/- 0.56 mm, p = 0.001). Device type was retained in the multivariate analysis as an independent predictor of late minimal lumen diameter and lumen loss. Multivariate analysis identified vessel size and immediate gain as determinants of optimal atherectomy. CONCLUSIONS: Restenosis is a consequence not only of the extent of lumen improvement but also of the mechanism of vessel wall injury (debulking vs. dilating). While performing atherectomy, the operator should strive for an optimal procedural result to accommodate an increased intimal hyperplastic response.

Angioplasty, Balloon↗

PubMed1990

An analytic approach to optimized retracted missing tissue compensators.

The introduction of an attenuating medium into a photon beam serves both to reduce the intensity of the primary beam and to create secondary radiation due to scatter. When retracted missing tissue compensators are employed to compensate for irregular surface contour or internal inhomogeneities, they are often fabricated without regard to the scattered radiation that they introduce into the system. The study of a mathematically describable conical geometry has clearly demonstrated the need for improved compensator design. Experimental results obtained with this geometry can be reproduced with good agreement, using theoretical calculations based on primary and first order scattered radiation. This method of analysis may be extended to predict the shape of a compensator which will produce an optimized dose distribution at a given depth in a phantom, equivalent to that which would be obtained when an irregular surface is filled with unit density material (bolus), producing a flat surface. An optimized compensator was constructed based on these theoretical considerations and excellent agreement was observed between theory and experiment. Dramatic improvement in the restoration of bolus dose is obtained with this optimized compensator. Finally, an anthropomorphic phantom of the neck region has been constructed and the performance of a compensator designed according to current clinical methods for this geometry has been evaluated. The performance of an optimized compensator specific to this geometry is presented and good agreement between theoretical predictions and experimental results is observed. Dramatic improvement in bolus dose restoration over that obtained with the clinically designed compensator is realized.

Humans↗

PubMed1993

Optimal atrioventricular (AV) pacing interval during temporary AV sequential pacing after cardiac surgery.

Temporary dual chamber atrioventricular (AV) pacing is often used to increase cardiac output (CO) after cardiac surgery. The AV interval was varied to investigate the effect on CO in 13 patients. CO was computed from the Fick principle using mixed venous oxygen saturation (SvO2), arterial oxygen saturation (SaO2), hemoglobin, and oxygen consumption (VO2). AV intervals were varied randomly from 0.025 to 0.300 seconds in 0.025-second increments. The effect on CO from increasing the AV interval was dependent on the control CO. In all patients, as the AV interval was increased from 0.025 to 0.100 seconds, CO progressively increased. In most patients, the highest (optimal) CO occurred with AV pacing and averaged 300 mL/min greater than with atrial (A) pacing alone (P < .0001). In patients with a high initial CO (> 6.0 L/min), CO peaked and averaged 0.5 L/min more than with A pacing. CO was maximal for each of these patients at a unique AV interval between 0.100 and 0.225 seconds, and at intervals greater than 0.225 seconds CO decreased (P < .01). In patients with intermediate CO (4-6 L/min) at AV intervals greater than 0.100 seconds, a plateau in CO was reached. No consistent pattern was seen in patients with low initial CO (< 4.0 L/min). Maximal CO may be achieved by optimizing the AV interval in patients following cardiac surgery. The optimal AV interval is between 0.100 and 0.225 seconds and is different for each patient. Continuous SvO2 monitoring allows rapid evaluation of CO changes and optimization of the AV pacing interval.

Atrioventricular Node↗

PubMed2005

Optimization of liver biopsy RNA sampling and use of reference RNA for cDNA microarray analysis.

In this study, we used the rat liver as a model system to optimize the conditions for extracting RNA from liver biopsies for use in cDNA microarrays. We found that a 5-mm biopsy with a 16-gauge needle and storage in RNA later at 4 degrees C were optimal conditions for RNA extraction. The most important factor for the quantity and quality of RNA extraction was the sample diameter. Using the optimized sampling conditions and a cDNA microarray, we compared the expression of genes in the normal and the fibrotic tissues of the LEC rat liver, a model of liver tumorigenesis, with SD rat liver RNA as a reference. We found 29 genes that were up-regulated and 33 genes that were down-regulated in the fibrotic part of the liver. Furthermore, with the help of the reference RNA, we were able to classify the expression profiles into five groups without complex mathematical analyses; without the reference RNA, the genes could be classified into only two groups. Finally, we found that osteopontin was expressed at a very high level in the fibrotic portion of the LEC rat liver. This cDNA microarray result was validated by immunohistochemistry, which showed an elevated expression of osteopontin in the region of cholangiocarcinoma and a lack of expression in normal tissues. With optimized conditions, we should be able to apply the microarray system for routine practice.

Animals↗

PubMed2005

An optimized protein in-gel digest method for reliable proteome characterization by MALDI-TOF-MS analysis.

Human lung epithelial cells (A549) were used as a model to develop a reliable proteome characterization method by peptide mass fingerprinting (PMF). Lung cell lysate proteins and protein standards were separated by 2D-gel electrophoresis, stained with Coomassie blue, gel plugs were subjected to commonly adapted as well as optimized in-gel digestion/sample preparation methods. Samples were analyzed by MALDI-TOF-MS. Optimization parameters included, use of NH(4)OAc in destaining and in-gel digestion buffers, detergent/salt removal prior to in-gel digestion, use of solvents of varying polarities (0%, 30%, 60% ACN containing 0.1% TFA) to improve peptide recoveries, matrix composition (alpha-cyano-4-hydroxycinamic acid-organic solvent combinations) and on-target salt removal. This led to enhanced mass spectral information and a sensitivity gain in the order of 6-10 fold compared to that of common procedures, yielding reliable, unambiguous protein identification with femtomol protein sensitivity by Autoflex MALDI-TOF-MS. Triplicate analyses by two analysts revealed consistent, wide range m/z values including in < 1200Da region by relieving matrix-exerted signal suppression, requiring one trial to obtain a unique protein identification with superior PMF results for the optimized method. Analyses of ten A549 proteins in replicates using the optimized method yielded fast, reliable characterization, suggesting the potential application of this method in high-throughput protein identification by PMF.

Cell Line↗

PubMed2006

Randomized comparison of simultaneous biventricular stimulation versus optimized interventricular delay in cardiac resynchronization therapy. The Resynchronization for the HemodYnamic Treatment for Heart Failure Management II implantable cardioverter defibrillator (RHYTHM II ICD) study.

BACKGROUND: The clinical value of interventricular (V-V) delay optimization in patients with chronic congestive heart failure (CHF) undergoing implantation of a device for cardiac resynchronization therapy (CRT) has not been clearly demonstrated. METHODS: RHYTHM II was a single-blind randomized trial including 121 recipients of a device for CRT with cardioverter/defibrillator capabilities (CRT-D) randomly assigned in a 1:3 ratio to simultaneous (n = 30) versus optimized (OPT) (n = 91) biventricular pacing. V-V delay was optimized by echocardiography. The study end points were (1) freedom from CRT-D system-related complications and (2) changes between preimplant and 6 months of follow-up in (a) New York Heart Association CHF functional class, (b) distance covered during a 6-minute hall walk, and (c) quality of life (QOL). RESULTS: In the OPT group, the V-V delay ranged from 0 to 80 milliseconds, with 28.4% of patients stimulated at an OPT V-V delay of 0 milliseconds. The overall 6-month survival free of adverse events requiring invasive interventions was 81.8%. In the whole cohort, 6 months of CRT-D was associated with a significant decrease in New York Heart Association class, increase in the distance covered during the 6-minute hall walk, and improvement in QOL (each P < .0001). The effects of CRT-D on these end points were similar in both study groups. CONCLUSIONS: Cardioverter-defibrillator capabilities was associated with a significant alleviation of CHF symptoms, increase in functional capacity, and improvement in QOL. The optimization of the V-V delay conferred no additional benefit compared with simultaneous biventricular stimulation.

Aged↗

PubMed2006

Optimization of anterior eye fluorescein viewing.

PURPOSE: To optimize anterior eye fluorescein viewing and image capture. DESIGN: Prospective experimental investigation. METHODS: The spectral radiance of ten different models of slit-lamp blue luminance and the spectral transmission of three barrier filters were measured. Optimal clinical instillation of fluorescein was evaluated by a comparison of four different instillation methods of fluorescein into 10 subjects. Two methods used a floret, and two used minims of different concentration. The resulting fluorescence was evaluated for quenching effects and efficiency over time. RESULTS: Spectral radiance of the blue illumination typically had an average peak at 460 nm. Comparison between three slit-lamps of the same model showed a similar spectral radiance distribution. Of the slit-lamps examined, 8.3% to 50.6% of the illumination output was optimized for >80% fluorescein excitation, and 1.2% to 23.5% of the illumination overlapped with that emitted by the fluorophore. The barrier filters had an average cut-off at 510 to 520 nm. Quenching was observed for all methods of fluorescein instillation. The moistened floret and the 1% minim reached a useful level of fluorescence in on average approximately 20s ( approximately 2.5x faster than the saturated floret and 2% minim) and this lasted for approximately 160 seconds. CONCLUSIONS: Most slit-lamps' blue light and yellow barrier filters are not optimal for fluorescein viewing and capture. Instillation of fluorescein using a moistened floret or 1% minim seems most clinically appropriate as lower quantities and concentrations of fluorescein improve the efficiency of clinical examination.

Adult↗

PubMed2026

Optimized AAV5-RPGR ORF15 Gene Therapy Rescues Photoreceptor Structure and Function in X-Linked Retinitis Pigmentosa Mouse Model.

PURPOSE: To develop and evaluate an rAAV5-based gene therapy vector expressing an optimized human RPGR ORF15 transgene (rAAV5-RPGR) for the treatment of X-linked retinitis pigmentosa caused by RPGR mutations, addressing the challenges of cloning the unstable wild-type ORF15 sequence. DESIGN: This was a prospective experimental study. SUBJECTS: This was an animal study. METHODS: An optimized RPGR ORF15 sequence was designed to eliminate problematic secondary structures and cryptic splice sites. In vitro expression was validated in HEK 293T and photoreceptor-like 661 W cells. A complete Rpgr knockout mouse model (Rpgr-knockout [KO]) was generated and characterized phenotypically. Therapeutic efficacy was assessed in Rpgr-KO mice via subretinal injection of rAAV5-RPGR at low (1 × 10⁹ vg/eye), medium (3 × 10⁹ vg/eye), or high (1 × 10¹⁰ vg/eye) doses. Structural and functional outcomes were evaluated at 12- and 14-month postinjection. Short-term safety was assessed in rabbits 1 month after subretinal injection. MAIN OUTCOME MEASURES: Level of RPGR protein expression and Protein isoform profile (elimination of truncated isoforms), Cellular localization of transgene expression and Dose-dependence of expression, outer nuclear layer thickness, and electroretinography parameters. RESULTS: (1) The optimized vector increased RPGR protein expression 3.3-fold in vitro compared to wild-type and eliminated truncated isoforms. (2) Subretinal delivery of rAAV5-RPGR in mice demonstrated dose-dependent transgene expression localized correctly to photoreceptor inner segments. (3) In Rpgr-KO mice, high-dose treatment significantly preserved outer nuclear layer thickness at the injection site (42% greater than controls at 14 months, P < .01) and central retina (P < .05), reduced aberrant rhodopsin mislocalization (P < .01), and partially restored retinal function. ERG showed significantly improved scotopic a-wave (≥100 vs <90 µV in controls at 10 cd·s/m²) and photopic b-wave amplitudes (49-66 vs 31-46 µV at 30 cd·s/m²) in treated mice. (4) No vector-related toxicity was observed in rabbits. CONCLUSIONS: rAAV5-RPGR mediated efficiently, targeted expression of optimized RPGR-ORF15, significantly preserved photoreceptor structure and function in a severe X-linked retinitis pigmentosa mouse model, and demonstrated a favorable safety profile. This study provides preclinical proof-of-concept for RPGR-targeted gene replacement therapy.

Animals↗

PubMed2004

Prediction of optimal versus suboptimal cytoreduction of advanced-stage serous ovarian cancer with the use of microarrays.

OBJECTIVE: The purpose of this study was to define gene expression patterns that are associated with the optimal versus suboptimal debulking of advanced-stage serous ovarian cancers. STUDY DESIGN: RNA from 44 advanced serous ovarian cancers (19 optimal, 25 suboptimal) was evaluated with microarrays that contain >22,000 genes. Genes were screened on the basis of their association with debulking status to obtain the top 120 differentially expressed genes. These genes were then used to develop a predictive model for debulking status, which was subjected to out-of-sample cross validation. RESULTS: We found that patterns of expression of 32 genes can distinguish between optimal and suboptimal debulking with 72.7% predictive accuracy. An analysis of the data that were based on clusters of co-ordinately expressed genes resulted in only a marginal improvement in predictive accuracy (75%). CONCLUSION: These data support the hypothesis that favorable survival that is associated with optimal debulking of advanced ovarian cancers is due to, at least in part, the underlying biologic characteristics of these cancers.

Biomarkers, Tumor↗

PubMed2005

Frequency of sudden cardiac death among acute myocardial infarction survivors with optimized medical and revascularization therapy.

The epidemiologic pattern of sudden cardiac death (SCD) may have changed in the modern treatment era of patients after an acute myocardial infarction (AMI). We evaluated the effect of optimized medical and revascularization therapy on the incidence of SCD after an AMI. A total of 2,130 consecutive patients (mean age 59 +/- 10 years) with an AMI from 2 European centers (Germany and Finland) was included in the study. In this population, 1,004 patients (47%) were treated with an optimized medical and revascularization strategy (defined as treatment with revascularization, beta blockers, aspirin, statins, and angiotensin-converting enzyme inhibitors). Nonoptimized treatment, defined as a lack of any optimized treatment, was received by 1,126 patients (53%). During the mean follow-up of 2.9 +/- 1.3 years, the incidence of SCD was very low among patients who received optimized treatment (1.2%, annual incidence 0.4%) compared with those who did not (3.6%, annual incidence 1.4%, p <0.01). The treatment strategy that had the greatest effect on differences in the SCD rate was revascularization therapy, with the hazard ratio of SCD being 2.1 (95% confidence interval 1.2 to 3.7, p <0.01) for SCD among nonrevascularized patients. Nonoptimized treatment was more often received by older patients, women, diabetic patients, and those with depressed left ventricular function. In conclusion, the incidence of SCD is low in the modern treatment era of patients after an AMI. Coronary revascularization seems to have a great effect on altered the epidemiologic pattern of SCD.

Adrenergic beta-Antagonists↗

PubMed2005

Optimism, dietary habits, body mass index and smoking among young Finnish adults.

The association between optimism and health habits was evaluated among 31-year-old men and women (n=8690) born in Northern Finland in 1966. Both women and men above the upper quartile for optimism more often ate fresh vegetables and salads (women 76%/men 57%), berries (23%/9%), fruit (67%/42%), low-fat cheese (25%/16%) and salad dressing (15%/17%) than those below the lower quartile (56%/31%, 14%/5%, 52%/26%, 18%/10% and 10%/5%, respectively) with women in higher proportion than in men in each case. Pessimism was associated with infrequent consumption of foods rich in fiber and salad dressing and the proportions of high consumers of alcohol. Proportion of subjects with BMI of 30.0 kg/m2 and above and that of current smokers were higher among the pessimists than among the optimists. Thus lack of optimism is associated with a cluster of unhealthy dietary and other habits. This may at least partly explain the positive association of optimism with health found in previous studies.

Adult↗

PubMed2005

An optimized experimental protocol based on neuro-evolutionary algorithms application to the classification of dyspeptic patients and to the prediction of the effectiveness of their treatment.

OBJECTIVE: This paper aims to present a specific optimized experimental protocol (EP) for classification and/or prediction problems. The neuro-evolutionary algorithms on which it is based and its application with two selected real cases are described in detail. The first application addresses the problem of classifying the functional (FD) or organic (OD) forms of dyspepsia; the second relates to the problem of predicting the 6-month follow-up outcome of dyspeptic patients treated by helicobacter pylori (HP) eradication therapy. METHODS AND MATERIAL: The database built by the multicentre observational study, performed in Italy by the NUD-look Study Group, provided the material studied: a collection of data from 861 patients with previously uninvestigated dyspepsia, being referred for upper gastrointestinal endoscopy to 42 Italian Endoscopic Services. The proposed EP makes use of techniques based on advanced neuro-evolutionary systems (NESs) and is structured in phases and steps. The use of specific input selection (IS) and training and testing (T and T) techniques together with genetic doping (GenD) algorithm is described in detail, as well as the steps taken in the two benchmark and optimization protocol phases. RESULTS: In terms of accuracy results, a value of 79.64% was achieved during optimization, with mean benchmark values of 64.90% for the linear discriminant analysis (LDA) and 68.15% for the multi layer perceptron (MLP), for the classification task. A value of 88.61% was achieved during optimization for the prediction task, with mean benchmark values of 49.32% for the LDA and 70.05% for the MLP. CONCLUSIONS: The proposed EP has led to the construction of inductors that are viable and usable on medical data which is representative but highly not linear. In particular, for the classification problem, these new inductors may be effectively used on the basal examination data to support doctors in deciding whether to avoid endoscopic examinations; whereas, in the prediction problem, they may support doctors' decisions about the advisability of eradication therapy. In both cases the variables selected indicate the possibility of reducing the data collection effort and also of providing information that can be used for general investigations on symptom relevance.

Algorithms↗