Radiomics for classification of bone mineral loss: A machine learning study.

PURPOSE: The purpose of this study was to develop predictive models to classify osteoporosis, osteopenia and normal patients using radiomics and machine learning approaches. MATERIALS AND METHODS: A total of 147 patients were included in this retrospective single-center study. There were 12 men and 135 women with a mean age of 56.88±10.6 (SD) years (range: 28-87 years). For each patient, seven regions including four lumbar and three femoral including trochanteric, intertrochanteric and neck were segmented on bone mineral densitometry images and 54 texture features were extracted from the regions. The performance of four feature selection methods, including classifier attribute evaluation (CLAE), one rule attribute evaluation (ORAE), gain ratio attribute evaluation (GRAE) and principal components analysis (PRCA) along with four classification methods, including random forest (RF), random committee (RC), K-nearest neighbor (KN) and logit-boost (LB) were evaluated. Four classification categories, including osteopenia vs. normal, osteoporosis vs. normal, osteopenia vs. osteoporosis and osteoporosis+osteopenia vs. osteoporosis were examined for the defined seven regions. The classification model performances were evaluated using the area under the receiver operator characteristic curve (AUC). RESULTS: The AUC values ranged from 0.50 to 0.78. The combination of methods RF+CLAE, RF+ORAE and RC+ORAE yielded highest performance (AUC=0.78) in discriminating between osteoporosis and normal state in the trochanteric region. The combinations of RF+PRCA and LB+PRCA had the highest performance (AUC=0.76) in discriminating between osteoporosis and normal state in the neck region. CONCLUSION: The machine learning radiomic approach can be considered as a new method for bone mineral deficiency disease classification using bone mineral densitometry image features.

New physical approaches to treat cancer stem cells: a review

Cancer stem cells (CSCs) have been identified as the main center of tumor therapeutic resistance. They are highly resistant against current cancer therapy approaches particularly radiation therapy (RT). Recently, a wide spectrum of physical methods has been proposed to treat CSCs, including high energetic particles, hyperthermia (HT), nanoparticles (NPs) and combination of these approaches. In this review article, the importance and benefits of the physical CSCs therapy methods such as nanomaterial-based heat treatments and particle therapy will be highlighted

No disponible

Radiation Exposure and Bell's Palsy: A Hypothetical Association.

Bell's palsy is an idiopathic peripheral nerve palsy involving the facial nerve. It accounts for 60 to 75% of all cases of unilateral facial paralysis. The main mechanisms to induce BP remain unclear, but infection, ischemic condition and immunodeficiency may contribute to the development of Bell's palsy. Accumulating evidence has shown several factors can trigger the reactivation of latent HSV including psychological stressors, physical stressors and immunosuppression. Ionization and non-ionization radiations are of importance of physical stressors. Some data have shown radiation can reactivate HSVs. Based on preliminary studies showing radiation reactivation of HSVs, we aimed to hypothesize radiation (in both forms of ionization and non-ionization) may cause Bell's palsy. In the future, the role of radiotherapy, radiofrequency radiation from mobile phones and wireless devices in HSV reactivation and Bell's palsy should be investigated.

Reduction-oxidation (redox) system in radiation-induced normal tissue injury: molecular mechanisms and implications in radiation therapeutics

Every year, millions of cancer patients undergo radiation therapy for treating and destroying abnormal cell growths within normal cell environmental conditions. Thus, ionizing radiation can have positive therapeutic effects on cancer cells as well as post-detrimental effects on surrounding normal tissues. Previous studies in the past years have proposed that the reduction and oxidation metabolism in cells changes in response to ionizing radiation and has a key role in radiation toxicity to normal tissue. Free radicals generated from ionizing radiation result in upregulation of cyclooxygenases (COXs), nitric oxide synthase (NOSs), lipoxygenases (LOXs) as well as nicotinamide adenine dinucleotide phosphate oxidase (NADPH oxidase), and their effected changes in mitochondrial functions are markedly noticeable. Each of these enzymes is diversely expressed in multiple cells, tissues and organs in a specific manner. Overproduction of reactive oxygen radicals (ROS), reactive hydroxyl radical (ROH) and reactive nitrogen radicals (RNS) in multiple cellular environments in the affected nucleus, cell membranes, cytosol and mitochondria, and other organelles, can specifically affect the sensitive and modifying enzymes of the redox system and repair proteins that play a pivotal role in both early and late effects of radiation. In recent years, ionizing radiation has been known to affect the redox functions and metabolism of NADPH oxidases (NOXs) as well as having destabilizing and detrimental effects on directly and indirectly affected cells, tissues and organs. More noteworthy, chronic free radical production may continue for years, increasing the risk of carcinogenesis and other oxidative stress-driven degenerative diseases as well as pathologies, in addition to late effect complications of organ fibrosis. Hence, knowledge about the mechanisms of chronic oxidative damage and injury in affected cells, tissues and organs following exposure to ionizing radiation may help in the development of treatment and management strategies of complications associated with radiotherapy (RT) or radiation accident victims. Thus, this medically relevant phenomenon may lead to the discovery of potential antioxidants and inhibitors with promising results in targeting and modulating the ROS/NO-sensitive enzymes in irradiated tissues and organ injury systems

No disponible

New physical approaches to treat cancer stem cells: a review.

Cancer stem cells (CSCs) have been identified as the main center of tumor therapeutic resistance. They are highly resistant against current cancer therapy approaches particularly radiation therapy (RT). Recently, a wide spectrum of physical methods has been proposed to treat CSCs, including high energetic particles, hyperthermia (HT), nanoparticles (NPs) and combination of these approaches. In this review article, the importance and benefits of the physical CSCs therapy methods such as nanomaterial-based heat treatments and particle therapy will be highlighted.

The potential roles of bacteria to improve radiation treatment outcome

Many combined therapies have been proposed to enhance radiotherapy outcome, but they have several limitations. As a new feasible strategy, combination of radiotherapy with bacteria showed a significant positive impact on the tumor treatment and metastasis inhibition. Although probiotic bacteria and radiotherapy alone can be effective in the treatment of different cancers, the combination of these two therapies seems to enhance therapeutic outcome and is cost-effective. Bacterial cells can act as therapeutic/gene/drug delivery vehicles as well as theranostic agents. In this communication, we reviewed current evidences, studies, suggestions, and future-based directions on combination of radiotherapy and bacteria. In another sections, an overview on tumor hypoxia, bacteria in cancer therapy, and combination of radiotherapy and bacteria is presented. A brief overview on trials and animal studies which used bacteria to protect normal tissues against radiotherapy-induced complications is also included (AU)

No disponible

Reduction-oxidation (redox) system in radiation-induced normal tissue injury: molecular mechanisms and implications in radiation therapeutics.

Every year, millions of cancer patients undergo radiation therapy for treating and destroying abnormal cell growths within normal cell environmental conditions. Thus, ionizing radiation can have positive therapeutic effects on cancer cells as well as post-detrimental effects on surrounding normal tissues. Previous studies in the past years have proposed that the reduction and oxidation metabolism in cells changes in response to ionizing radiation and has a key role in radiation toxicity to normal tissue. Free radicals generated from ionizing radiation result in upregulation of cyclooxygenases (COXs), nitric oxide synthase (NOSs), lipoxygenases (LOXs) as well as nicotinamide adenine dinucleotide phosphate oxidase (NADPH oxidase), and their effected changes in mitochondrial functions are markedly noticeable. Each of these enzymes is diversely expressed in multiple cells, tissues and organs in a specific manner. Overproduction of reactive oxygen radicals (ROS), reactive hydroxyl radical (ROH) and reactive nitrogen radicals (RNS) in multiple cellular environments in the affected nucleus, cell membranes, cytosol and mitochondria, and other organelles, can specifically affect the sensitive and modifying enzymes of the redox system and repair proteins that play a pivotal role in both early and late effects of radiation. In recent years, ionizing radiation has been known to affect the redox functions and metabolism of NADPH oxidases (NOXs) as well as having destabilizing and detrimental effects on directly and indirectly affected cells, tissues and organs. More noteworthy, chronic free radical production may continue for years, increasing the risk of carcinogenesis and other oxidative stress-driven degenerative diseases as well as pathologies, in addition to late effect complications of organ fibrosis. Hence, knowledge about the mechanisms of chronic oxidative damage and injury in affected cells, tissues and organs following exposure to ionizing radiation may help in the development of treatment and management strategies of complications associated with radiotherapy (RT) or radiation accident victims. Thus, this medically relevant phenomenon may lead to the discovery of potential antioxidants and inhibitors with promising results in targeting and modulating the ROS/NO-sensitive enzymes in irradiated tissues and organ injury systems.

The potential roles of bacteria to improve radiation treatment outcome.

Many combined therapies have been proposed to enhance radiotherapy outcome, but they have several limitations. As a new feasible strategy, combination of radiotherapy with bacteria showed a significant positive impact on the tumor treatment and metastasis inhibition. Although probiotic bacteria and radiotherapy alone can be effective in the treatment of different cancers, the combination of these two therapies seems to enhance therapeutic outcome and is cost-effective. Bacterial cells can act as therapeutic/gene/drug delivery vehicles as well as theranostic agents. In this communication, we reviewed current evidences, studies, suggestions, and future-based directions on combination of radiotherapy and bacteria. In another sections, an overview on tumor hypoxia, bacteria in cancer therapy, and combination of radiotherapy and bacteria is presented. A brief overview on trials and animal studies which used bacteria to protect normal tissues against radiotherapy-induced complications is also included.

Combination of H120 and 1/96 avian infectious bronchitis virus vaccine strains protect chickens against challenge with IS/1494/06 (variant 2)-like infectious bronchitis virus.

Avian infectious bronchitis (IB) is a worldwide chicken disease, caused by avian infectious bronchitis virus (IBV) which infects all commercial poultry lines. The present study was done to evaluate protection caused by two different serotype vaccines (Massachusetts and 793/B) in order to evaluate protection against challenge with IS/1494/06-like virus (variant 2-like virus), which is prevalent in the Middle East. SPF chickens were divided into four groups (n = 20). First and second group as negative control group and non-vaccinated-challenged group received no vaccine. Groups 3 and 4 received H120-H120 and H120-1/96 IBV vaccine strains at the 1st and 14th day, respectively. Twenty one days after last vaccination, non-vaccinated-challenged group and vaccinated group were challenged using variant 2-like IBV. Serum samples were collected before challenge to measure humoral immune response of chickens. Five days after challenge, the tissue samples from the trachea, lungs and kidneys were taken to evaluate cilliary activity, viral load (quantitative real-time RT-PCR), and histopathological evaluation. Clinical sign scores were also recorded after challenge. Overall, the results showed a protective efficacy of the used vaccination program. Best cross protection (69.2%) was obtained in the H120-1/96 vaccinated group. Virus replication of the challenged virus in H120-1/96 group compared with H120-H120 group showed a significant reduction of viral load in trachea (1.5×103 compared to 503) and kidneys. Clinical sign scores of the challenged groups showed significant effect of the vaccination program to reduce clinical signs. The trachea pathological scores and histopathological findings in the lungs and kidneys also confirmed better protective efficacy of vaccinated groups. In conclusion, using combination of heterologous IBV vaccine serotypes (Massachusetts and 793/B) would be a better strategy to control variant 2-like viruses, but more evaluation is needed using other circulating isolates to find the best combination of vaccines.

Pathogenicity characteristics of an Iranian variant-2 (IS-1494) like infectious bronchitis virus in experimentally infected SPF chickens.

Avian infectious bronchitis (IB) is a major cause of economic loss to the poultry industry. IB virus primarily affects respiratory tract, but strains differ in their tropism for such other target organs as kidneys and alimentary tract. The objective of this study was to estimate the pathogenicity of an Iranian IB virus (IBV) variant (variant-2) which is one of the most prevalent isolates circulating in Iranian poultry farms. SPF chickens were intranasally inoculated with 104 EID50/0.1 ml of the virus. Sera, fecal swabs, and different tissue samples were collected on different days post infection. Clinical signs, gross pathology, and histological changes were recorded. The amount of virus genome was quantified in different tissues and feces using quantitative real-time PCR assay. The highest viral loads were detected in the feces and cecal tonsils. Real-time PCR results demonstrated variant-2 tropism for respiratory tract, digestive system and renal tissue that is due to its epitheliotropic nature. This is the first pathogenicity study of Iranian variant-2 virus. Based on histology observations and clinical signs this isolate was classified as a nephropathogenic IBV. Further knowledge of IBV pathogenesis permits to perform more effective prevention practice.

Higher circulating levels of anti-phosphatidylserine antibody in peptic ulcer patients infected with CagA-positive strains of Helicobacter pylori.

BACKGROUND: The CagA-positive strains of H. pylori were associated with the higher risk of peptic ulcer (PU) diseases. The aim of this study was to evaluate the serum concentrations of anti-phosphatidylserine (anti-PS) and anti-cardiolipin (anti-CL) antibodies in H. pylori-infected PU patients, H. pylori-infected asymptomatic (AS) carriers, and a healthy non-infected group and also to determine their correlation with the bacterial virulence factor CagA. METHODS: A total of 100 H. pylori-infected PU patients (80 patients were positive for anti-CagA antibody and 20 patients were negative for anti-CagA antibody), 65 H. pylori-infected AS carriers (40 subjects were positive for anti-CagA antibody and 25 subjects were negative for anti-CagA antibody) and 30 healthy H. pylori-negative subjects (as a control group) enrolled in the study. Serum samples of participants were tested for the levels of anti-PS and anti-CL antibodies by ELISA. RESULTS: The mean serum levels of anti-PS antibody in the PU group (13.46 +/- 2.90 RU/mL) was significantly higher than that observed in the H. pylori-infected AS group (1.57 +/- 0.38 RU/mL, p < 0.001) and healthy uninfected control group (0.77 +/- 0.32 RU/mL, p < 0.001). No significant difference was observed for the mean serum levels of anti-PS antibody between the AS group and uninfected control group. In the PU group, the mean serum levels of anti-PS antibody was significantly higher in patients with a positive test for anti-CagA antibody (16.46 +/- 3.55 RU/mL) in comparison to patients with a negative test for anti-CagA antibody (2.74 +/- 1.29 RU/mL; p < 0.01). The differences of the mean serum levels of anti-CL antibody were not significant between PU, AS, and control groups. CONCLUSIONS: These results showed higher serum levels of anti-PS antibody in patients with PU disease, especially in those infected with the CagA+ strains of H. pylori. Clinical significance of the anti-PS antibody in H. pylori-infected PU patients can be considered in additional follow up studies.

Uterine leiomyoma and its association with menstrual pattern and history of depo-medroxyprogesterone acetate injections.

BACKGROUND AND AIM: Despite the high prevalence of uterine leiomyoma, according to recent review studies there is uncertainty and a paucity of information regarding its predisposing or protective factors. The aim of this study was to assess the possible association between menstrual cycle pattern and occurrence of surgically treated myomas and also to check if depo-medroxyprogesterone acetate (DMPA) injection earlier in reproductive life can affect the later occurrence of myomas needing surgical treatment. METHODS: In a case-control study in Ardabil, 85 women with definite diagnosis of surgically treated uterine leiomyoma and 154 community controls were enrolled. Possible predictors of myoma including menstrual cycle and menstrual bleeding patterns were assessed. Data were analyzed using SPSS software (SPSS, IBM, Somers, NY). Odds ratios were used as the main statistic in assessing the strength of observed associations. RESULTS: Mean age of the participants was 41.8 ± 8.5 years. Length of menstrual cycle was associated with myoma and a higher likelihood of myoma was observed among those having shorter menstrual cycles (P < 0.05). Number of menstrual bleeding days was also associated with surgically treated myoma and longer bleeding periods increased the likelihood of myoma (P < 0.05). Only one of the eight women who had a history of depo-medroxyprogesterone acetate injections had developed surgically treated uterine leiomyoma and the others belonged to the control group without a history of surgical treatment for uterine leiomyoma. CONCLUSION: Menstrual cycle pattern is associated with developing leiomyomas requiring surgical treatment. DMPA, other than its role in myoma treatment, is also assumed to have a role in preventing myomas, but due to the small sample size in this study, larger scale prospective trials are needed in the future.

Risk factor investigation for cardiovascular health through WHO STEPS approach in Ardabil, Iran.

OBJECTIVES: Reliable evidence is the keystone for any noncommunicable disease (NCD) prevention plan to be initiated. In this study we carried out a risk factor investigation based on the WHO Stepwise approach to Surveillance (STEPS). METHODS: The study was conducted on 1000 adults between 15 and 64 years of age living in Ardabil province, north-west Iran during 2006, based on the WHO STEPS approach to surveillance of risk factors for NCD. At this stage only the first and second steps were carried out. Data were collected through standard questionnaires and methods analyzed using STATA version 8 statistical software package. RESULTS: 29.0% of men and 2.6% of women were current daily tobacco smokers. The mean number of manufactured cigarettes smoked per day was 18.9 among current daily smokers. Smoking was most prevalent among men of low-income families and those of lower education. The mean body mass index (BMI) was 26.6 kg/m(2), and was significantly correlated with systolic blood pressure. 58.9% were overweight or obese; 18.0% had raised blood pressure and 3.7% had isolated systolic hypertension. The mean number of servings of fruit consumed per day was 1.1; 33.1% had low levels of activity. Combined risk factor analysis showed that 4.1% of participants were in the low-risk group (up to 5.1% among men and 3.2% among women). Those in the high-risk group comprised 25.6% in the 25- to 44-year age group and 49.7% in the 45- to 64-year age group. Mean BMI increased by age in both sexes at least at the first three decades of adult life. CONCLUSION: Based on observed status of risk for cardiovascular health, burden of cardiovascular diseases is expected to increase if an effective prevention strategy is not undertaken.

Simultaneous spectrophotometric determination of paracetamol, phenylephrine and chlropheniramine in pharmaceuticals using chemometric approaches.

BACKGROUND AND THE PURPOSE OF THE STUDY: The linear multivariate calibration models such as principal components regression (PCR) and partial least squares regressions (PLS1 and PLS2) due to the mathematical simplicity and physical or chemical interpretability are sufficient and generally preferred method for analysis of multicomponent drugs. In this study, simultaneous determination of paracetamol, phenylephrine and chlorpheniramine in pharmaceuticals using chemometric methods and UV spectrophotometry is reported as a simple alternative technique. MATERIAL AND METHODS: Principal components regression (PCR) and partial least squares regressions (PLS1 and PLS2) were used for chemometric analyses of data obtained from the spectra of paracetamol, phenylephrine and chlorpheniramine between wavelengths of 200 to 400 nm at several concentrations within their linear ranges. The analytical performance of these chemometric methods were characterized by relative prediction errors and recoveries (%) and compared with each other. RESULTS: PCR, PLS1 and PLS2 were successfully applied to a tablet formulation, with no interference from excipients as indicated by the recovery. However, the PLS1 shows better results due to its flexibility and mathematical principals. CONCLUSION: The proposed methods are simple and rapid requiring no separation step, and can be easily used as an alternative in the quality control of drugs.

Soft-modeling based spectrofluorimetric study of simultaneous equilibria.

A two-way soft resolution method will fail when applied to a simultaneous equilibria system due to rank deficiency in its concentration profiles. Increasing the dimensionality of measurements from two-way to three-way data can be used to overcome this problem. Simultaneous dissociation of two weak acids is considered as a model for simultaneous equilibria. Three-way data obtained from excitation-emission spectrofluorimetric monitoring of a pH-metric titration is analyzed using a proper combination of well-known soft-modeling methods. Multivariate curve resolution-alternating least squares is used for calculating the excitation and emission spectral profiles of involved species and rank annihilation factor analysis for obtaining the contribution of each species in measured excitation-emission matrices at different pHs. The results of simulated and real simultaneous acids dissociation equilibria showed that the proposed combined method performs well even in situation when the equilibrium constants are close to each other. The applicability of method for study of an acidic dissociation is also shown.

Interaction of anionic dyes and cationic surfactants with ionic liquid character.

The interactions of an imidazolium based ionic liquid (IL), namely 1-dodecyl-3-methylimidazolium chloride [C12 mim][Cl] with two sulfonated anionic dyes, azocarmine G and methyl orange, are studied spectrophotometrically in both acidic and basic media. ILs (with some surface active character) can interact with the above dyes and cause considerable shifts in their spectra. These interactions are then compared with some surfactant-dye interactions. Evolving factor analysis (EFA) and multivariate curve resolution-alternating least squares (MCR-ALS) are used for complete resolution of the measured spectrophotometric data. The concentration and spectral profiles of all species were calculated without any assumption of the chemical models. The spectral variation of dye solutions as a function of IL concentrations below and above the critical aggregation concentration (CAC) is analyzed using MCR-ALS as a soft-modeling technique. The ion pair formation constants between ILs and dyes were calculated using the obtained concentration profiles.

Simultaneous spectrophotometric determination of paracetamol, ibuprofen and caffeine in pharmaceuticals by chemometric methods.

In this study, the simultaneous determination of paracetamol, ibuprofen and caffeine in pharmaceuticals by chemometric approaches using UV spectrophotometry has been reported as a simple alternative to using separate models for each component. Spectra of paracetamol, ibuprofen and caffeine were recorded at several concentrations within their linear ranges and were used to compute the calibration mixture between wavelengths 200 and 400 nm at an interval of 1 nm in methanol:0.1 HCl (3:1). Partial least squares regression (PLS), genetic algorithm coupled with PLS (GA-PLS), and principal component-artificial neural network (PC-ANN) were used for chemometric analysis of data and the parameters of the chemometric procedures were optimized. The analytical performances of these chemometric methods were characterized by relative prediction errors and recoveries (%) and were compared with each other. The GA-PLS shows superiority over other applied multivariate methods due to the wavelength selection in PLS calibration using a genetic algorithm without loss of prediction capacity. Although the components show an important degree of spectral overlap, they have been determined simultaneously and rapidly requiring no separation step. These three methods were successfully applied to pharmaceutical formulation, capsule, with no interference from excipients as indicated by the recovery study results. The proposed methods are simple and rapid and can be easily used in the quality control of drugs as alternative analysis tools.

Net analyte signal-based simultaneous determination of ethanol and water by quartz crystal nanobalance sensor.

Net analyte signal (NAS)-based method called HLA/GO was applied for the selectively determination of binary mixture of ethanol and water by quartz crystal nanobalance (QCN) sensor. A full factorial design was applied for the formation of calibration and prediction sets in the concentration ranges 5.5-22.2 microg mL(-1) for ethanol and 7.01-28.07 microg mL(-1) for water. An optimal time range was selected by procedure which was based on the calculation of the net analyte signal regression plot in any considered time window for each test sample. A moving window strategy was used for searching the region with maximum linearity of NAS regression plot (minimum error indicator) and minimum of PRESS value. On the base of obtained results, the differences on the adsorption profiles in the time range between 1 and 600 s were used to determine mixtures of both compounds by HLA/GO method. The calculation of the net analytical signal using HLA/GO method allows determination of several figures of merit like selectivity, sensitivity, analytical sensitivity and limit of detection, for each component. To check the ability of the proposed method in the selection of linear regions of adsorption profile, a test for detecting non-linear regions of adsorption profile data in the presence of methanol was also described. The results showed that the method was successfully applied for the determination of ethanol and water.

Creatinine, blood urea nitrogen and thyroid hormone levels before and after haemodialysis.

A study was carried out on 57 patients with chronic renal failure in a hospital in Kerman city, Islamic Republic of Iran. Blood samples were taken before and after haemodialysis to measure blood urea nitrogen and serum creatinine, triiodothyronine (T3) and thyroxine (T4) levels. Findings revealed that before dialysis T4 in 11 cases and T3 in 29 cases were lower than the normal range, but after haemodialysis only 3 cases for T4 and 15 cases for T3 were lower than normal levels. The remaining cases reverted to normal state. We suggest that a feedback relationship exists between the major end catabolic products (creatinine and blood urea nitrogen) and thyroid hormone serum levels.

Performance comparison of neural network training algorithms in modeling of bimodal drug delivery.

The major aim of this study was to model the effect of two causal factors, i.e. coating weight gain and amount of pectin-chitosan in the coating solution on the in vitro release profile of theophylline for bimodal drug delivery. Artificial neural network (ANN) as a multilayer perceptron feedforward network was incorporated for developing a predictive model of the formulations. Five different training algorithms belonging to three classes: gradient descent, quasi-Newton (Levenberg-Marquardt, LM) and genetic algorithm (GA) were used to train ANN containing a single hidden layer of four nodes. The next objective of the current study was to compare the performance of aforementioned algorithms with regard to predicting ability. The ANNs were trained with those algorithms using the available experimental data as the training set. The divergence of the RMSE between the output and target values of test set was monitored and used as a criterion to stop training. Two versions of gradient descent backpropagation algorithms, i.e. incremental backpropagation (IBP) and batch backpropagation (BBP) outperformed the others. No significant differences were found between the predictive abilities of IBP and BBP, although, the convergence speed of BBP is three- to four-fold higher than IBP. Although, both gradient descent backpropagation and LM methodologies gave comparable results for the data modeling, training of ANNs with genetic algorithm was erratic. The precision of predictive ability was measured for each training algorithm and their performances were in the order of: IBP, BBP>LM>QP (quick propagation)>GA. According to BBP-ANN implementation, an increase in coating levels and a decrease in the amount of pectin-chitosan generally retarded the drug release. Moreover, the latter causal factor namely the amount of pectin-chitosan played slightly more dominant role in determination of the dissolution profiles.