Deep learning based decision tree ensembles for incomplete medical datasets.

BACKGROUND: In practice, the collected datasets for data analysis are usually incomplete as some data contain missing attribute values. Many related works focus on constructing specific models to produce estimations to replace the missing values, to make the original incomplete datasets become complete. Another type of solution is to directly handle the incomplete datasets without missing value imputation, with decision trees being the major technique for this purpose. OBJECTIVE: To introduce a novel approach, namely Deep Learning-based Decision Tree Ensembles (DLDTE), which borrows the bounding box and sliding window strategies used in deep learning techniques to divide an incomplete dataset into a number of subsets and learning from each subset by a decision tree, resulting in decision tree ensembles. METHOD: Two medical domain problem datasets contain several hundred feature dimensions with the missing rates of 10% to 50% are used for performance comparison. RESULTS: The proposed DLDTE provides the highest rate of classification accuracy when compared with the baseline decision tree method, as well as two missing value imputation methods (mean and k-nearest neighbor), and the case deletion method. CONCLUSION: The results demonstrate the effectiveness of DLDTE for handling incomplete medical datasets with different missing rates.

Combining data discretization and missing value imputation for incomplete medical datasets.

Data discretization aims to transform a set of continuous features into discrete features, thus simplifying the representation of information and making it easier to understand, use, and explain. In practice, users can take advantage of the discretization process to improve knowledge discovery and data analysis on medical domain problem datasets containing continuous features. However, certain feature values were frequently missing. Many data-mining algorithms cannot handle incomplete datasets. In this study, we considered the use of both discretization and missing-value imputation to process incomplete medical datasets, examining how the order of discretization and missing-value imputation combined influenced performance. The experimental results were obtained using seven different medical domain problem datasets: two discretizers, including the minimum description length principle (MDLP) and ChiMerge; three imputation methods, including the mean/mode, classification and regression tree (CART), and k-nearest neighbor (KNN) methods; and two classifiers, including support vector machines (SVM) and the C4.5 decision tree. The results show that a better performance can be obtained by first performing discretization followed by imputation, rather than vice versa. Furthermore, the highest classification accuracy rate was achieved by combining ChiMerge and KNN with SVM.

Multifunctional biological properties and phytochemical constituents of Mangifera indica L. seed kernel extract for preventing skin aging.

This study aimed to investigate the potential of Mangifera indica L. seed kernel extract, which is highly discarded by the global food processing industry, as a multifunctional bioactive ingredient for nutraceutical and cosmeceutical applications. Different extracting solvents were utilized, the extracts were then tested for their antioxidant activities using DPPH, ABTS radical scavenging assays, and inhibition of lipid peroxidation. Additionally, total phenolic content (TPC), total flavonoid content (TFC), and gallic acid content were elucidated using Folin-Ciocalteu and aluminum chloride colorimetric assays, as well as high performance liquid chromatography. The hydroethanolic extract (KMHE) exhibited the highest percentage yield, with the highest antioxidant activity owing to its high phenolic content. KMHE consisted of 773.66 ± 9.42 mg GAE/g extract in TPC, 36.20 ± 4.20 mg RU/g extract in TFC. Additionally, gallic acid was shown to be a major constituent of KMHE. KMHE was investigated for anti-tyrosinase, anti-hyaluronidase, anti-MMP-2, and anti-MMP-9 activities. Moreover, the anti-inflammatory effects of KMHE were studied in RAW 264.7 cells induced by nitric oxide and KMHE was shown to prevent DNA damage, indicating an inhibitory effect on cellular aging. KMHE showed outstanding anti-tyrosinase activity and was as potent an anti-hyaluronidase as gallic acid. Additionally, our results reveal notable anti-MMP-2 and anti-MMP-9 effects that were not significantly different from those of gallic acid. Furthermore, KMHE demonstrated 61.54 ± 2.39% nitric oxide inhibition, with no cytotoxic effects, in RAW264.7 cells, and also prevented DNA damage in the human fibroblast BJ cell line with no cytotoxic effects. Therefore, KMHE could be a promising, natural multifunctional bioactive compound for nutraceutical and cosmeceutical applications.

Effects of Carissa carandas Linn. Fruit, Pulp, Leaf, and Seed on Oxidation, Inflammation, Tyrosinase, Matrix Metalloproteinase, Elastase, and Hyaluronidase Inhibition.

In this study, the potential of Carissa carandas Linn. as a natural anti-aging, antioxidant, and skin whitening agent was studied. Various parts of C. carandas, including fruit, leaf, seed, and pulp were sequentially extracted by maceration using n-hexane, ethyl acetate, and ethanol, respectively. High-performance liquid chromatography, Folin-Ciocalteu, and Dowd method were used to investigate their chemical compositions. The inhibitory activities of oxidation process, matrix metalloproteinases (MMPs), elastase, hyaluronidase, and tyrosinase were analyzed. Cytotoxicity was determined by 3-(4,5-dimethylthiazol-2-yl)-2,5 diphenyl tetrazolium bromide assay in a human epidermal keratinocyte line (HaCaT). The results exhibited that ethyl acetate could extract the most ursolic acid from C. carandas, while ethanol could extract the most phenolics and flavonoids. The leaf extract had the highest content of ursolic acid, phenolics, and flavonoids. The leaf extracted with ethyl acetate (AL) had the highest ursolic acid content (411.8 mg/g extract) and inhibited MMP-1, NF-kappa B, and tyrosinase activity the most. Ursolic acid has been proposed as a key component in these biological activities. Although several C. carandas extracts are beneficial to human skin, AL has been proposed for use in cosmetics and cosmeceuticals due to its superior anti-wrinkle, anti-inflammation, and whitening properties.

Chemical Constituents, Antioxidant, Anti-MMPs, and Anti-Hyaluronidase Activities of Thunbergia laurifolia Lindl. Leaf Extracts for Skin Aging and Skin Damage Prevention.

This study aimed to investigate the potential usage of Thunbergia laurifolia Lindl. leaf extracts in the cosmetic industry. Matrix metalloproteinases (MMPs) and hyaluronidase inhibition of T. laurifolia leaf extracts, prepared using reflux extraction with deionized water (RE) and 80% v/v ethanol using Soxhlet's apparatus (SE), were determined. Rosmarinic acid, phenolics, and flavonoids contents were determined using high-performance liquid chromatography, Folin-Ciocalteu, and aluminum chloride colorimetric assays, respectively. Antioxidant activities were determined by 1,1-diphenyl-2-picrylhydrazyl (DPPH) and linoleic acid-thiocyanate assays. MMP-1 inhibition was investigated using enzymatic and fluorescent reactions, whereas MMP-2, MMP-9, and hyaluronidase inhibition were investigated using gel electrophoresis. Cytotoxicity on human fibroblast cell line was also investigated. The results demonstrated that SE contained significantly higher content of rosmarinic acid (5.62% ± 0.01%) and flavonoids (417 ± 25 mg of quercetin/g of extract) but RE contained a significantly higher phenolics content (181 ± 1 mg of gallic acid/g of extract; p < 0.001). SE possessed higher lipid peroxidation inhibition but less DPPH• scavenging activity than RE. Both extracts possessed comparable hyaluronidase inhibition. SE was as potent an MMP-1 inhibitor as gallic acid (half maximal inhibitory concentration values were 12.0 ± 0.3 and 8.9 ± 0.4 mg/cm3, respectively). SE showed significantly higher MMP-2 and MMP-9 inhibition than RE (p < 0.05). Therefore, SE is a promising natural anti-ageing ingredient rich in rosmarinic acid and flavonoids with antioxidant, anti-hyaluronidase, and potent MMPs inhibitory effects that could be applied in the cosmetic industry.

Dermal Delivery Enhancement of Natural Anti-Ageing Compounds from Ocimum sanctum Linn. Extract by Nanostructured Lipid Carriers.

This study aimed to develop nanodelivery systems for enhancing the Ocimum sanctum Linn. extract delivery into the skin. Rosmarinic acid (RA) was used as a marker for the quantitative determination of the extract by high-performance liquid chromatography. Nanostructured lipid carriers (NLC), nanoemulsion, liposome, and niosome, were developed and characterized for internal droplet size, polydispersity index (PDI), and zeta potential using photon correlation spectroscopy. Irritation properties of each formulations were investigated by hen's egg test on the chorioallantoic membrane. In vitro release, skin permeation, and skin retention are determined. NLC was suggested as the most suitable system since it enhances the dermal delivery of RA with the significant skin retention amount of 27.1 ± 1.8% (p < 0.05). Its internal droplet size, PDI, and zeta potential were 261.0 ± 5.3 nm, 0.216 ± 0.042, and -45.4 ± 2.4 mV, respectively. RA released from NLC with a sustained release pattern with the release amount of 1.29 ± 0.15% after 24 h. NLC induced no irritation and did not permeate through the skin. Therefore, NLC containing O. sanctum extract was an attractive dermal delivery system that was safe and enhanced dermal delivery of RA. It was suggested for further used as topical anti-ageing products.

Outlier Removal in Model-Based Missing Value Imputation for Medical Datasets.

Many real-world medical datasets contain some proportion of missing (attribute) values. In general, missing value imputation can be performed to solve this problem, which is to provide estimations for the missing values by a reasoning process based on the (complete) observed data. However, if the observed data contain some noisy information or outliers, the estimations of the missing values may not be reliable or may even be quite different from the real values. The aim of this paper is to examine whether a combination of instance selection from the observed data and missing value imputation offers better performance than performing missing value imputation alone. In particular, three instance selection algorithms, DROP3, GA, and IB3, and three imputation algorithms, KNNI, MLP, and SVM, are used in order to find out the best combination. The experimental results show that that performing instance selection can have a positive impact on missing value imputation over the numerical data type of medical datasets, and specific combinations of instance selection and imputation methods can improve the imputation results over the mixed data type of medical datasets. However, instance selection does not have a definitely positive impact on the imputation result for categorical medical datasets.

Composition and Bioactivity of Essential Oil from Citrus grandis (L.) Osbeck 'Mato Peiyu' Leaf.

'Mato Peiyu' pomelo (Citrus grandis (L.) Osbeck 'Mato Peiyu') leaves from pruning are currently an agricultural waste. The aim of this study was to isolate essential oils from these leaves through steam distillation (SD) and solvent-free microwave extraction (SFME) and to evaluate their applicability to skin care by analyzing their antimicrobial, antioxidant (diphenyl-1-picrylhydrazyl scavenging assay, ß-carotene/linoleic acid assay, and nitric oxide scavenging assay), anti-inflammatory (5-lipoxygenase inhibition assay), and antityrosinase activities. The gas chromatography-mass spectrometry results indicated that the main components of 'Mato Peiyu' leaf essential oils were citronellal and citronellol, with a total percentage of 50.71% and 59.82% for SD and SFME, respectively. The highest bioactivity among all assays was obtained for 5-lipoxygenase inhibition, with an IC50 value of 0.034% (v/v). The MIC90 of the antimicrobial activity of essential oils against Escherichia coli, Pseudomonas aeruginosa, Staphylococcus aureus, and Candida albicans ranged from 0.086% to 0.121% (v/v). Citronellal and citronellol were the main contributors, accounting for at least 54.58% of the essential oil's bioactivity. This paper is the first to report the compositions and bioactivities of 'Mato Peiyu' leaf essential oil, and the results imply that the pomelo leaf essential oil may be applied in skin care.

SVM and SVM Ensembles in Breast Cancer Prediction.

Breast cancer is an all too common disease in women, making how to effectively predict it an active research problem. A number of statistical and machine learning techniques have been employed to develop various breast cancer prediction models. Among them, support vector machines (SVM) have been shown to outperform many related techniques. To construct the SVM classifier, it is first necessary to decide the kernel function, and different kernel functions can result in different prediction performance. However, there have been very few studies focused on examining the prediction performances of SVM based on different kernel functions. Moreover, it is unknown whether SVM classifier ensembles which have been proposed to improve the performance of single classifiers can outperform single SVM classifiers in terms of breast cancer prediction. Therefore, the aim of this paper is to fully assess the prediction performance of SVM and SVM ensembles over small and large scale breast cancer datasets. The classification accuracy, ROC, F-measure, and computational times of training SVM and SVM ensembles are compared. The experimental results show that linear kernel based SVM ensembles based on the bagging method and RBF kernel based SVM ensembles with the boosting method can be the better choices for a small scale dataset, where feature selection should be performed in the data pre-processing stage. For a large scale dataset, RBF kernel based SVM ensembles based on boosting perform better than the other classifiers.

Research performance of AACSB accredited institutions in Taiwan: before versus after accreditation.

INTRODUCTION: More and more universities are receiving accreditation from the Association to Advance Collegiate Schools of Business (AACSB), which is an international association for promoting quality teaching and learning at business schools. To be accredited, the schools are required to meet a number of standards ensuring that certain levels of teaching quality and students' learning are met. However, there are a variety of points of view espoused in the literature regarding the relationship between research and teaching, some studies have demonstrated that research and teaching these are complementary elements of learning, but others disagree with these findings. CASE DESCRIPTION: Unlike past such studies, we focus on analyzing the research performance of accredited schools during the period prior to and after receiving accreditation. The objective is to answer the question as to whether performance has been improved by comparing the same school's performance before and after accreditation. In this study, four AACSB accredited universities in Taiwan are analyzed, including one teaching oriented and three research oriented universities. Research performance is evaluated by comparing seven citation statistics, the number of papers published, number of citations, average number of citations per paper, average citations per year, h-index (annual), h-index, and g-index. DISCUSSION AND EVALUATION: The analysis results show that business schools demonstrated enhanced research performance after AACSB accreditation, but in most accredited schools the proportion of faculty members not actively doing research is larger than active ones. CONCLUSION: This study shows that the AACSB accreditation has a positive impact on research performance. The findings can be used as a reference for current non-accredited schools whose research goals are to improve their research productivity and quality.

On mining incomplete medical datasets: Ordering imputation and classification.

BACKGROUND: To collect medical datasets, it is usually the case that a number of data samples contain some missing values. Performing the data mining task over the incomplete datasets is a difficult problem. In general, missing value imputation can be approached, which aims at providing estimations for missing values by reasoning from the observed data. Consequently, the effectiveness of missing value imputation is heavily dependent on the observed data (or complete data) in the incomplete datasets. OBJECTIVE: In this paper, the research objective is to perform instance selection to filter out some noisy data (or outliers) from a given (complete) dataset to see its effect on the final imputation result. Specifically, four different processes of combining instance selection and missing value imputation are proposed and compared in terms of data classification. METHODS: Experiments are conducted based on 11 medical related datasets containing categorical, numerical, and mixed attribute types of data. In addition, missing values for each dataset are introduced into all attributes (the missing data rates are 10%, 20%, 30%, 40%, and 50%). For instance selection and missing value imputation, the DROP3 and k-nearest neighbor imputation methods are employed. On the other hand, the support vector machine (SVM) classifier is used to assess the final classification accuracy of the four different processes. RESULTS: The experimental results show that the second process by performing instance selection first and imputation second allows the SVM classifiers to outperform the other processes. CONCLUSIONS: For incomplete medical datasets containing some missing values, it is necessary to perform missing value imputation. In this paper, we demonstrate that instance selection can be used to filter out some noisy data or outliers before the imputation process. In other words, the observed data for missing value imputation may contain some noisy information, which can degrade the quality of the imputation result as well as the classification performance.

An efficient data preprocessing approach for large scale medical data mining.

BACKGROUND: The size of medical datasets is usually very large, which directly affects the computational cost of the data mining process. Instance selection is a data preprocessing step in the knowledge discovery process, which can be employed to reduce storage requirements while also maintaining the mining quality. This process aims to filter out outliers (or noisy data) from a given (training) dataset. However, when the dataset is very large in size, more time is required to accomplish the instance selection task. OBJECTIVE: In this paper, we introduce an efficient data preprocessing approach (EDP), which is composed of two steps. The first step is based on training a model over a small amount of training data after preforming instance selection. The model is then used to identify the rest of the large amount of training data. METHODS: Experiments are conducted based on two medical datasets for breast cancer and protein homology prediction problems that contain over 100000 data samples. In addition, three well-known instance selection algorithms are used, IB3, DROP3, and genetic algorithms. On the other hand, three popular classification techniques are used to construct the learning models for comparison, namely the CART decision tree, k-nearest neighbor (k-NN), and support vector machine (SVM). RESULTS: The results show that our proposed approach not only reduces the computational cost by nearly a factor of two or three over three other state-of-the-art algorithms, but also maintains the final classification accuracy. CONCLUSIONS: To perform instance selection over large scale medical datasets, it requires a large computational cost to directly execute existing instance selection algorithms. Our proposed EDP approach solves this problem by training a learning model to recognize good and noisy data. To consider both computational complexity and final classification accuracy, the proposed EDP has been demonstrated its efficiency and effectiveness in the large scale instance selection problem.

Antioxidant and Anti-Inflammatory Properties of Longan (Dimocarpus longan Lour.) Pericarp.

This study examined the antioxidant and anti-inflammatory activities of the water extract of longan pericarp (WLP). The results showed that WLP exhibited radical scavenging, reducing activity and liposome protection activity. In addition, WLP also inhibited lipopolysaccharide (LPS)-induced nitric oxide (NO) production in macrophages. Further, administration of WLP, in the range of 100-400 mg/kg, showed a concentration-dependent inhibition on paw edema development following carrageenan (Carr) treatment in mice. The anti-inflammatory effects of WLP may be related to NO and tumor necrosis factor (TNF-α) suppression and associated with the increase in the activities of antioxidant enzymes, including catalase, superoxide dismutase, and glutathione peroxidase. Overall, the results showed that WLP might serve as a natural antioxidant and inflammatory inhibitor.

Risk management strategy to increase the safety of workers in the nanomaterials industry.

In recent years, many engineered nanomaterials (NMs) have been produced, but increasing research has revealed that these may have toxicities far greater than conventional materials and cause significant adverse health effects. At present, there is insufficient data to determine the permissible concentrations of NMs in the workplace. There is also a lack of toxicity data and environmental monitoring results relating to complete health risk assessment. In view of this, we believe that workers in the NMs industry should be provided with simple and practical risk management strategy to ensure occupational health and safety. In this study, we developed a risk management strategy based on the precautionary risk management (PRM). The risk of the engineered NMs manufacturing plants can be divided into three levels based on aspect identification, solubility tests, dermal absorption, and cytotoxic analyses. The risk management strategies include aspects relating to technology control, engineering control, personal protective equipment, and monitoring of the working environment for each level. Here we report the first case in which a simple and practical risk management strategy applying in specific engineered NMs manufacturing plants. We are confident that our risk management strategy can be effectively reduced engineered NM industries risks for workers.

Antimicrobial, antioxidant, and anti-inflammatory activities of essential oils from five selected herbs.

Eucalyptus bridgesiana, Cymbopogon martinii, Thymus vulgaris, Lindernia anagallis, and Pelargonium fragrans are five species of herbs used in Asia. Their essential oils were analyzed by GC-MS, and a total of 36 components were detected. The results of our study indicated that, except for the essential oil of P. fragrans, all of the essential oils demonstrated obvious antimicrobial activity against a broad range of microorganisms. The C. martinii essential oil, which is rich in geraniol, was the most effective antimicrobial additive. All of the essential oils demonstrated antioxidant activities on 2,2-diphenyl-1-picrylhydrazyl radical scavenging assay, ß-carotene/linoleic acid assay, and nitric oxide radical scavenging assay. Furthermore, the T. vulgaris essential oil, which possesses plentiful thymol, exhibited the highest antioxidant activity. For P. acnes-induced secretion of pro-inflammatory cytokines, the essential oils of P. aeruginosa, C. martinii, and T. vulgaris reduced the TNF-α, IL-1ß, and IL-8 secretion levels of THP-1 cells.

Skin penetrating abilities and reservoir effects of neat DMF and DMF/water mixtures.

This study was set out to determine the skin permeabilities of neat N, N-dimethylformamide (DMF, denoted as DMF(100%)) and DMF/water mixtures (including 50% DMF/50% water and 10% DMF/90% water mixtures (v/v), denoted as DMF(50%) and DMF(10%), respectively) and to assess their skin reservoir effects on the systemic absorption. The penetration fluxes for DMF(10%) and DMF(50%) (=0.015 and 0.126 mg/cm(2)/h, respectively) were only approximately 1.1%and 15% in magnitude as that of DMF(100%) (=0.872+/-0.231 mg/cm(2)/h), respectively. The above results could be because the perturbation effect of the DMF content was much more significant than the rehydration effect of the water content on skin permeability. We found that 85.9%, 96.6% and 98.7% of applied doses were still remaining on the skin surface, 4.98%, 0.838% and 0.181% were still remaining in the skin layer, and 9.09%, 2.61% and 1.17% penetrated through the skin layer after the 24-h exposure for DMF(100%), DMF(50%) and DMF(10%), respectively. We found that the half-life (T(1/2)) of DMF retaining in the skin layer were 12.3, 4.07 and 1.24h for DMF(100%), DMF(50%) and DMF(10%), respectively. The estimated reservoir effect for DMF(100%) (=34.1%) was higher than that of DMF(50%) and DMF(10%) (=27.1% and 14.1%, respectively). The above results suggest that the impact associated with the internal burden of DMF could be prolonged even the external exposure of DMF is terminated, particularly for those dermal contact with DMF/water mixtures with high DMF contents.

Improving image annotation via useful representative feature selection.

This paper describes the automatic assignment of images into classes described by individual keywords provided with the Corel data set. Automatic image annotation technology aims to provide an efficient and effective searching environment for users to query their images more easily, but current image retrieval systems are still not very accurate when assigning images into a large number of keyword classes. Noisy features are the main problem, causing some keywords never to be assigned to their correct images. This paper focuses on improving image classification, first by selection of features to characterise each image, and then the selection of the most suitable feature vectors as training data. A Pixel Density filter (PDfilter) and Information Gain (IG) are proposed to perform these respective tasks. We filter out the noisy features so that groups of images can be represented by their most important values. The experiments use hue, saturation and value (HSV) colour feature space to categorise images according to one of 190 concrete keywords or subsets of these. The study shows that feature selection through the PDfilter and IG can improve the problem of spurious similarity.

Urinary excretion of toluene diisocyanates in rats following dermal exposure.

Toluene diisocyanates (TDI) are commonly used in polyurethane (PU)-related products. TDIs have been documented as the leading cause of occupational asthma. Skin exposure to TDI in the workplace is common. However, no studies in the literature have investigated the exact biomarker concentration profile for skin TDI absorption through any in vivo animal studies. In this study a rat model was used to evaluate the TDI skin absorption to explore the dose-response pattern and to determine the kinetic characteristics of urinary toluene diamine (U-TDA) during skin exposure. TDIs were topically exposed on the dorsum of rat skin at 0.2%, 1% and 5%. Consecutive urine samples were collected for 6 days and U-TDA were analysed using GC/ECD. It was demonstrated in this rat study that absorption of 2,4- and 2,6-TDI through skin contact is possible. A clear dose-dependent skin absorption relationship for 2,4- and 2,6-TDI was demonstrated by the AUC, Cmax findings and accumulative amounts (r > or = 0.968). U-TDA concentration profiles in 6-day consecutive urine samples fit well in the first-order kinetics, although higher order kinetics could not be excluded for the high dose. The apparent half-lives for excretory urinary TDA were about 20 h consistent at various skin exposures. It is concluded that skin absorption of TDI was confirmed in a rat model and a clear dose-dependent skin absorption relationship for 2,4- and 2,6-TDI was demonstrated. Excretory U-TDA concentrations in 6-day consecutive urine samples via skin exposure reveal the first-order kinetics and the half-lives were about 20 h.

Improved analysis of dialkylphosphates in urine using strong anion exchange disk extraction and in-vial derivatization.

Determination of dialkylphosphates (DAPs) in urine is useful for assessing human exposure to organophosphates (OPs). An improved method for the determination of four DAPs based on a strong anion exchange (SAX) disk extraction and in-vial derivatization was presented in this study. The matrix effect of urine components such as chloride ion and phosphate ion by using a SAX disk to extract DAPs in urine analysis was carefully evaluated. It was observed that the chloride ion mainly affected the extraction of diethylphosphate (DEP), dimethylthiophosphate (DMTP), and diethylthiophosphate (DETP) in urine. The addition of silver hydroxide could significantly improve the extraction efficiencies of these three DAPs, but it decreases the extraction efficiencies of dimethyldithiophosphate (DMDTP) and diethyldithiophosphate (DEDTP). The LOD of this method for DMTP, DETP, DMDTP, and DEDTP are 5, 5, 11, and 5 microg/L, respectively. A pretreatment strategy for the determination of DMTP, DMDTP, DETP, and DEDTP in urine was proposed which can provide reliable and prompt determination of routine urine analysis.

Microwave-assisted acid hydrolysis of toluene diamine conjugates in urine samples for biomarkers in toluene diisocyanate analysis.

Toluene diamines (TDAs) in urine have been used widely to determine the amount of toluene diisocyanate (TDI) absorbed by humans. Conventional hydrolysis to prepare a sample of urine takes approximately 16h. An attempt is made to apply microwave-assisted heating (MAH) to reduce the duration of analysis. Urine collected from rats exposed to a mixture of 2,4- and 2,6-TDI was diluted with non-exposed human urine 1/1250-, 1/500- and 1/250-fold. The urine samples were hydrolyzed by both conventional heating and MAH. The hydrolysis efficiency obtained using MAH significantly exceeded that obtained using conventional heating. Hydrolysis by MAH required only 20min, 48 times faster than with conventional heating. The use of the MAH method in hydrolysis was demonstrated to be reproducible, timesaving and efficient technique in measuring the concentration of urinary TDAs.