Machine Learning and Clinical Text. Supporting Health Information Flow

Fluent health information flow is critical for clinical decision-making. However, a considerable part of this information is free-form text and inabilities to utilize it create risks to patient safety and cost-­effective hospital administration. Methods for automated processing of clinical text are emerging. The aim in this doctoral dissertation is to study machine learning and clinical text in order to support health information flow.First, by analyzing the content of authentic patient records, the aim is to specify clinical needs in order to guide the development of machine learning applications.The contributions are a model of the ideal information flow,a model of the problems and challenges in reality, and a road map for the technology development. Second, by developing applications for practical cases,the aim is to concretize ways to support health information flow. Altogether five machine learning applications for three practical cases are described: The first two applications are binary classification and regression related to the practical case of topic labeling and relevance ranking.The third and fourth application are supervised and unsupervised multi-class classification for the practical case of topic segmentation and labeling.These four applications are tested with Finnish intensive care patient records.The fifth application is multi-label classification for the practical task of diagnosis coding. It is tested with English radiology reports.The performance of all these applications is promising. Third, the aim is to study how the quality of machine learning applications can be reliably evaluated.The associations between performance evaluation measures and methods are addressed,and a new hold-out method is introduced.This method contributes not only to processing time but also to the evaluation diversity and quality. The main conclusion is that developing machine learning applications for text requires interdisciplinary, international collaboration. Practical cases are very different, and hence the development must begin from genuine user needs and domain expertise. The technological expertise must cover linguistics,machine learning, and information systems. Finally, the methods must be evaluated both statistically and through authentic user-feedback.

Design and evaluation of a continuous flow, integrated nebulizer-hydride generator for flame atomic absorption spectrometry

An evaluation of the performance of a continuous flow hydride generator-nebulizer for flame atomic absorption spectrometry was carried out. Optimization of nebulizer gas flow rate, sample acid concentration, sample and tetrahydroborate uptake rates and reductant concentration, on the As and Se absorbance signals was carried out. A hydrogen-argon flame was used. An improvement of the analytical sensitivity relative to the conventional bead nebulizer used in flame AA was obtained (2 (As) and 4.8 (Se) µg L-1). Detection limits (3σb) of 1 (As) and 1.3 (Se) µg L-1 were obtained. Accuracy of the method was checked by analyzing an oyster tissue reference material.

Method validation and stability study of quercetin in topical emulsions

This study validated a high performance liquid chromatography (HPLC) method for the quantitative evaluation of quercetin in topical emulsions. The method was linear within 0.05 - 200 μg/mL range with a correlation coefficient of 0.9997, and without interference in the quercetin peak. The detection and quantitation limits were 18 and 29 ng/mL, respectively. The intra- and inter-assay precisions presented R.S.D. values lower than 2%. An average of 93% and 94% of quercetin was recovered for non-ionic and anionic emulsions, respectively. The raw material and anionic emulsion, but not non-ionic emulsion, were stable in all storage conditions for one year. The method reported is a fast and reliable HPLC technique useful for quercetin determination in topical emulsions.

Evaluation of chitosan microparticles containing curcumin and crosslinked with sodium tripolyphosphate produced by spray drying

The aim of this study was to encapsulate curcumin into chitosan, using sodium tripolyphosphate (TPP) as an ionic crosslinker by the spray drying method. The influence of TPP on the properties of the final product, such as solubility, morphology, loading efficiency, thermal behavior, swelling degree and release profiles, was evaluated. The microparticles had a spherical morphology (0.5-20 µm) with no apparent porosity or cracks. Results indicated the formation of a polymeric network, which ensures effective protection for curcumin. Controlled-release studies were carried out at pH 1.2 and 6.8, to observe the influence of pH on curcumin release while the mechanism was analyzed using the Korsmeyer-Peppas equation.

Multi-component quantitation of loratadine, pseudoephedrine and paracetamol in plasma and pharmaceutical formulations with liquid chromatography-tandem mass spectrometry utilizing a monolithic column

The purpose of this study was to develop a rapid, simple and sensitive quantitation method for pseudoephedrine (PSE), paracetamol (PAR) and loratadine (LOR) in plasma and pharmaceuticals using liquid chromatography-tandem mass spectrometry with a monolithic column. Separation was achieved using a gradient composition of methanol-0.1% formic acid at a flow rate of 1.0 mL min-1. Mass spectral transitions were recorded in SRM mode. System validation was evaluated for precision, specificity and linearity. Limit of detection for pseudoephedrine, paracetamol, and loratadine were determined to be 3.14, 1.86 and 1.44 ng mL-1, respectively, allowing easy determination in plasma with % recovery of 93.12 to 101.56%.

Simultaneous and accurate determination of water- and fat-soluble vitamins in multivitamin tablets by using an RP-HPLC method

In the present study, a reversed-phase high-performance liquid chromatographic (RP-HPLC) procedure was developed and validated for the simultaneous determination of seven water-soluble vitamins (thiamine, riboflavin, niacin, cyanocobalamin, ascorbic acid, folic acid, and p-aminobenzoic acid) and four fat-soluble vitamins (retinol acetate, cholecalciferol, α-tocopherol, and phytonadione) in multivitamin tablets. The linearity of the method was excellent (R² > 0.999) over the concentration range of 10 - 500 ng mL-1. The statistical evaluation of the method was carried out by performing the intra- and inter-day precision. The accuracy of the method was tested by measuring the average recovery; values ranged between 87.4% and 98.5% and were acceptable quantitative results that corresponded with the label claims.

Evaluation of antiradical assays used in determining the antioxidant capacity of pure compounds and plant extracts

The efficiency of the chemiluminescence luminol method and colorimetric DPPH and ABTS methods in evaluating the antiradical capacity of pure compounds and plant extracts with antioxidant potential is compared. In case of pure compounds, the values of parameter 'n' (number of radicals quenched per molecule of antiradical) for ascorbic acid, p-hydroquinone, catechol, quercetin, and rutin are similar when measured by colorimetric assays; however, considerably lower values of n are obtained with the luminol assay. The antiradical activity of extracts from male and female individuals of Baccharis burchelli and Baccharis crispa were determined by the luminol assay and expressed using the new Trolox® percentage (%Trolox®) parameter.

Simple method for mass production of polypyrrole/carbon nanotubes hybrid artificial muscle

Large scale preparation of hybrid electrical actuators represents an important step for the production of low cost devices. Interfacial polymerization of polypyrrole in the presence of multi-walled carbon nanotubes represents a simple technique in which strong interaction between components is established, providing composite materials with potential applications as actuators due to the synergistic interaction between the individual components, i.e., fast response of carbon nanotubes, high strain of polypyrrole, and diversity in the available geometry of resulting samples.

HPLC-DAD based method for the quantification of flavonoids in the hydroethanolic extract of Tonina fluviatilis Aubl. (Eriocaulaceae) and their radical scavenging activity

This article describes the isolation and identification of flavonoids in the hydroethanolic extract of the aerial parts from Tonina fluviatilis and evaluation of their antiradical activity. A method based on HPLC-DAD was developed and validated for detecting and quantifying flavonoids in hydroethanolic extracts. The flavonoids identified and quantified in the extract were 6,7-dimethoxyquercetin-3-O-β-D-glucopyranoside (1), 6-hydroxy-7-methoxyquercetin-3-O-β-D-glucopyranoside (2), and 6-methoxyquercetin-3-O-β-D-glucopyranoside (3). The developed method presented good validation parameters, showing that the results obtained are consistent and can be used in ensuring the quantification of these constituents in the extracts. Compounds 2 and 3 showed strong antiradical activity when compared with the positive controls (quercetin and gallic acid).

Synthesis of 1H-benzoxazine-2,4-diones from heterocyclic anhydrides: evaluation of antioxidant and antimicrobial activities

A facile one-step synthesis of 1H-benzoxazine-2,4-diones from heterocyclic anhydrides and TMSA was described. This paper determines their antimicrobial activity against nine human bacterial pathogens by the broth microdilution method; antioxidant activity by DPPH• inactivation and a ferric-reducing power assay; and toxicity by a brine shrimp, Artemia salina, assay. The 1H-benzoxazine-2,4-dione yields were in the range of 57 to 98%. The novel compound 1H-pyrazino[2,3-][1,3]oxazine-2,4-dione 4c showed the highest antioxidant capacity (DPPH 35.4% and FRAP 0.063 µmol TEs/µmol).

Automatic evaluation and data generation for analytical chemistry instrumental analysis exercises

In general, laboratory activities are costly in terms of time, space, and money. As such, the ability to provide realistically simulated laboratory data that enables students to practice data analysis techniques as a complementary activity would be expected to reduce these costs while opening up very interesting possibilities. In the present work, a novel methodology is presented for design of analytical chemistry instrumental analysis exercises that can be automatically personalized for each student and the results evaluated immediately. The proposed system provides each student with a different set of experimental data generated randomly while satisfying a set of constraints, rather than using data obtained from actual laboratory work. This allows the instructor to provide students with a set of practical problems to complement their regular laboratory work along with the corresponding feedback provided by the system's automatic evaluation process. To this end, the Goodle Grading Management System (GMS), an innovative web-based educational tool for automating the collection and assessment of practical exercises for engineering and scientific courses, was developed. The proposed methodology takes full advantage of the Goodle GMS fusion code architecture. The design of a particular exercise is provided ad hoc by the instructor and requires basic Matlab knowledge. The system has been employed with satisfactory results in several university courses. To demonstrate the automatic evaluation process, three exercises are presented in detail. The first exercise involves a linear regression analysis of data and the calculation of the quality parameters of an instrumental analysis method. The second and third exercises address two different comparison tests, a comparison test of the mean and a t-paired test.

THE APPLICATION OF AUTOMATED CORRELATION OPTIMIZED WARPING TO THE QUALITY EVALUATION OF Radix Puerariae thomsonii: CORRECTING RETENTION TIME SHIFT IN THE CHROMATOGRAPHIC FINGERPRINTS

The application of automated correlation optimized warping (ACOW) to the correction of retention time shift in the chromatographic fingerprints of Radix Puerariae thomsonii (RPT) was investigated. Twenty-seven samples were extracted from 9 batches of RPT products. The fingerprints of the 27 samples were established by the HPLC method. Because there is a retention time shift in the established fingerprints, the quality of these samples cannot be correctly evaluated by using similarity estimation and principal component analysis (PCA). Thus, the ACOW method was used to align these fingerprints. In the ACOW procedure, the warping parameters, which have a significant influence on the alignment result, were optimized by an automated algorithm. After correcting the retention time shift, the quality of these RPT samples was correctly evaluated by similarity estimation and PCA. It is demonstrated that ACOW is a practical method for aligning the chromatographic fingerprints of RPT. The combination of ACOW, similarity estimation, and PCA is shown to be a promising method for evaluating the quality of Traditional Chinese Medicine.

EVALUATION OF A BUFFERED SOLID PHASE DISPERSION PROCEDURE ADAPTED FOR PESTICIDE ANALYSES IN THE SOIL MATRIX

An evaluation of the pesticides extracted from the soil matrix was conducted using a citrate-buffered solid phase dispersion sample preparation method (QuEChERS). The identification and quantitation of pesticide compounds was performed using gas chromatography-mass spectrometry. Because of the occurrence of the matrix effect in 87% of the analyzed pesticides, the quantification was performed using matrix-matched calibration. The method's quantification limits were between 0.01 and 0.5 mg kg-1. Repeatability and intermediate precision, expressed as a relative standard deviation percentage, were less than 20%. The recoveries in general ranged between 62% and 99%, with a relative standard deviation < 20%. All the responses were linear, with a correlation coefficient (r) ≥0.99.

SYNTHESIS AND BIOLOGICAL EVALUATION OF SPIRO[INDOLINE-3,4’-PYRANO[2,3-C:6,5-C’]DIPYRAZOL]- 2-ONES IN THE PRESENCE OF SBA-Pr-SO3H AS A NANOCATALYST

Sulfonic acid functionalized SBA-15 nanoporous material (SBA-Pr-SO3H) with a large pore size of 6 nm, a high surface area, high selectivity, and excellent chemical and thermal stability was applied as an efficient heterogeneous nanoporous acid catalyst in the reaction of isatin with pyrazolones under mild reaction conditions. A novel class of symmetrical spiro[indoline-3,4'-pyrano[2,3-c:6,5-c']dipyrazol]-2-one derivatives was successfully obtained in high yields. Comparison of these results with those reported in the literature shows that the current method is efficient, and results in better reaction times and yields of the desired products. Other advantages of this new method are its operational simplicity, easy work-up procedure, and the use of SBA-Pr-SO3H as a reusable and environmentally benign nanoreactor, such that the reaction proceeds easily in its nanopores. We also tested the antimicrobial activity of the prepared compounds using the disc diffusion method, and some of the synthesized compounds exhibited the best results against B. subtilis and S. aureus.

Kinetic evaluation of the dehydration of Yb(III) Lu(III) and Y(III) 4-chlorobenzylidenepyruvate by thermogravimetry (TG)

The dehydration kinetic of Yb, Lu and Y 4-chlorobenzylidenepyruvate was studied by using thermogravimetry and the kinetics parameters obtained by Flynn and Wall method suggest that the dehydration step follows a first order mechanism. The activation energies calculated were 103.6, 96.6 and 97.2 kJ/mol and the lifetime considering the temperature of 31 and 101 º C for the dehydration of these compounds were 23, 26, 31 minutes and 0.6, 1.3 and 1.4 seconds, respectively. The results have similar values and suggest that the water is attached in the same way.