3D-QSARpy: Combining variable selection strategies and machine learning techniques to build QSAR models

Abstract Quantitative Structure-Activity Relationship (QSAR) is a computer-aided technology in the field of medicinal chemistry that seeks to clarify the relationships between molecular structures and their biological activities. Such technologies allow for the acceleration of the development of new compounds by reducing the costs of drug design. This work presents 3D-QSARpy, a flexible, user-friendly and robust tool, freely available without registration, to support the generation of QSAR 3D models in an automated way. The user only needs to provide aligned molecular structures and the respective dependent variable. The current version was developed using Python with packages such as scikit-learn and includes various techniques of machine learning for regression. The diverse techniques employed by the tool is a differential compared to known methodologies, such as CoMFA and CoMSIA, because it expands the search space of possible solutions, and in this way increases the chances of obtaining relevant models. Additionally, approaches for select variables (dimension reduction) were implemented in the tool. To evaluate its potentials, experiments were carried out to compare results obtained from the proposed 3D-QSARpy tool with the results from already published works. The results demonstrated that 3D-QSARpy is extremely useful in the field due to its expressive results.

Extração de recomendações farmacológicas para subsidiar o processo de adaptação de guias de prática clínica utilizados no tratamento da fibrilação atrial não valvar - uma revisão sistemática de guias de prática clínica / Extraction of pharmacological recommendations to support the process of adaptation of clinical practice guides used in the treatment of non-valvular atrial fibrillation a systematic review of clinical practice guidelines

A fibrilação atrial (FA) não valvar é a arritmia cardíaca mais comum em adultos, principalmente na população idosa. Para o tratamento da FA, recomenda-se a utilização de guias de prática clínica (GPCs), que são documentos que apresentam as melhores e mais atualizadas evidências para o tratamento dos pacientes acometidos por essa arritmia. Todavia, o processo de desenvolvimento dos GPCs requer recursos humanos, financeiros e tempo. Assim, a adaptação dos referidos documentos é uma opção para reduzir a duplicação de esforços e possibilitar sua adequação para uso local. O objetivo deste trabalho foi elaborar uma matriz de recomendações farmacológicas para subsidiar o processo de adaptação de GPCs utilizados no tratamento da fibrilação atrial não valvar. Para tanto, aplicou-se o método ADAPTE: revisão sistematizada de GPCs, avaliação e seleção dos GPCs de qualidade e elaboração da matriz. Foram considerados elegíveis 26 GPCs com recomendações farmacológicas para assistência primária da fibrilação atrial não valvar em adultos, publicados em inglês, espanhol ou português no período de abril de 2014 a abril de 2019 e indexados às bases de referência: MEDLINE, Embase, Cochrane Library e em 12 bases de dados específicas. A qualidade dos GPCs, foi avaliada pela aplicação do instrumento Appraisal of Guidelines for Research & Evaluarion II (AGREE II), sendo considerados de alta qualidade aqueles que apresentaram nota igual ou superior a 60 % no domínio Rigor de desenvolvimento. Todas as etapas foram realizadas por, pelo menos, 2 avaliadores e em caso de discrepância, um terceiro avaliador participou do processo. Dos 26 GPCs avaliados apenas 7 (26,9%) foram considerados de alta qualidade. A maioria dos GPCs utiliza o escore CHA2DS2-VASc, que indica a profilaxia tromboembólica em pacientes com FA não valvar a partir da pontuação 1 (fator de risco não sexual) e sugere a anticoagulação com anticoagulantes de ação direta. Houve pouca ênfase à complexidade da profilaxia de eventos tromboembólicos em idosos. Esta matriz visa contribuir para que sejam realizadas discussões e adaptações de GPCs destinado ao tratamento da FA não valvar com ênfase nas demandas e necessidades locais

Non-valvular atrial fibrillation (AF) is the most common cardiac arrhythmia in adults, especially in the elderly population. For the treatment of AF, the use of clinical practice guidelines (CPGs) is recommended, which are documents that present the best and most up-to-date evidence for the treatment of patients who are affected by this arrhythmia. However, the CPGs development process requires human, financial and time resources. However, the adaptation of documents is an option to reduce the duplication of efforts and make it possible to adapt them for any local use. The objective of this work was to elaborate a matrix of pharmacological treatment to support the process of adaptation of CPGs used in the treatment of non-valvular atrial fibrillation. Therefore, the ADAPTE method was applied: systematic review of CPGs, evaluation and selection of quality CPGs and matrix definition. Twenty-six CPGs were considered eligible with pharmacological recommendations for primary care of non-valvular atrial fibrillation valid in adults, published in English, Spanish or Portuguese from April 2014 to April 2019 and indexed to the following reference databases: MEDLINE, Embase, Cochrane Library and in 12 specific databases. The quality of the CPGs was assessed by applying the Assessment of Guidelines for Research and Assessment II (AGREE II) instrument, being considered of high those who had a grade equal to or greater than 60% in the domain Rigour of development. All steps were performed by a least 2 evaluators and in case of discrepancy, a third evaluator participated in the process. Of the 26 CPGs evaluated, only 7 (26.9%) were considered to be of high quality. Most CPGs use the CHA2DS2-VASc score, which indicates thromboembolic prophylaxis in patients with non-valvular AF from score 1 (non-sexual risk factor), and suggest anticoagulation with direct-acting anticoagulants. There was little emphasis on the complexity of prophylaxis for thromboembolic events in the elderly. This matrix aims to contribute to discussion and adaptations of CPGs for the treatment of non-valvar AF with the emphasis on local demands and needs

Novel biopharmaceutical development investigations towards drug and formulation performance optimization

For a drug to excerpt pharmacological action after oral intake, it first needs to be released from the formulation, get into solution (dissolve), be absorbed, and reach the systemic circulation. Since only solubilized drugs can be absorbed, and thus have therapeutic effect, the understanding of the dissolution and drug release processes of a drug product is of primary importance. Such understanding allows a robust formulation development with an ideal in vivo performance. In order to meet set standards, the performance assessment of oral drug products, such as dissolution testing, often applies conditions that are not reflective of the in vivo environment. The use of non-physiologically relevant dissolution method during the drug product development phase can be misleading and give poor mechanistic understanding of the in vivo dissolution process. Hence, we hypothesized that applying physiologically relevant conditions to the dissolution test would result in more accurate in vivo predictability for a robust and precise development process. Since the buffering system in the intestinal lumen operates at low molarity values, phosphate buffer at low buffer capacity was used as a first approach to an in vivo relevant parameter. Furthermore, a biphasic system was used, that is, the low buffer capacity medium was paired with an organic layer (n-octanol) to mimic the concurrent drug absorption that happens with the in vivo dissolution. Both poorly and highly soluble drugs in immediate release formulations (ibuprofen and metronidazole, respectively) were tested in this set-up to assess the dissolution in the aqueous medium and the partitioning to the organic phase. Additionally, enteric coated formulations were tested in bicarbonate buffer at the in vivo reported molarities values to assess the impact of buffer species on drug dissolution. The evaluated parameters were the buffer system (bicarbonate buffer vs. phosphate buffer), buffer capacity and medium pH. In all approaches, dissolution was also carried out in compendial buffer for comparison purposes. Our results demonstrate that the USP-recommended dissolution method greatly lacked discriminatory power, whereas low buffer capacity media discriminated between manufacturing methods. The use of an absorptive phase in the biphasic dissolution test assisted in controlling the medium pH due to the drug removal from the aqueous medium. Hence, the applied noncompendial methods were more discriminative to drug formulation differences and manufacturing methods than conventional dissolution conditions. In this study, it was demonstrated how biphasic dissolution and a low buffer capacity can be used to assess drug product performance differences. This can be a valuable approach during the early stages of drug product development for investigating drug release with improved physiological relevance. Similarly, all the enteric coated formulations displayed a fast release in phosphate buffer and complied with the compendial performance specifications. On the other hand, they all had a much slower drug release in bicarbonate buffer and failed the USP acceptance criteria. Also, the nature of the drug (acid vs base) impacted the dissolution behavior in bicarbonate buffer. This study indicates that compendial dissolution test for enteric coated tablets lacks physiological relevance and it needs to be reevaluated. Thus, an in vivo relevant performance method for EC products is needed. Overall, the findings of this thesis comprehensively demonstrates that meaningful differences in performance and accordance to clinical reports were only obtained when physiological relevant conditions were applied. Hence, our results indicate that the central hypothesis was answered positively

Para que um medicamento exerça a ação farmacológica após a ingestão oral, ele primeiro precisa ser liberado da formulação, dissolver, ser absorvido e atingir a circulação sistêmica. Uma vez que apenas medicamentos solubilizados podem ser absorvidos e, assim, ter efeito terapêutico, a compreensão dos processos de dissolução e liberação de um medicamento é de extrema importância. Tal compreensão permite o desenvolvimento de uma formulação robusta com o desempenho in vivo ideal. Para atender aos padrões regulatórios previamente estabelecidos, a avaliação da performance de formulações orais, como por exemplo, o teste de dissolução, frequentemente aplica condições que não refletem o ambiente fisiológico. O uso de métodos de dissolução não fisiologicamente relevante durante a fase de desenvolvimento do medicamento pode gerar resultados equivocados sem uma compreensão mecanistica do processo de dissolução in vivo. Portanto, a hipótese desse trabalho é que a aplicação de condições fisiologicamente relevantes no teste de dissolução resultaria em uma predição mais precisa da dissolução in vivo para um processo de desenvolvimento robusto e preciso. Uma vez que o sistema tampão no lúmen intestinal possui baixa molaridade, o tampão fosfato com baixa capacidade tamponante foi usado como uma primeira abordagem como um meio de dissolução fisiologicamente relevante. Além disso, foi utilizado um sistema bifásico, ou seja, o meio de baixa capacidade tamponante combinado a uma fase orgânica (n-octanol) para imitar a absorção in vivo. Formulações de liberação imediata contendo fármacos de baixa e de alta solubilidade (ibuprofeno e metronidazol, respectivamente) foram testadas no sistema bifásico para avaliar a dissolução no meio aquoso e a partição para a fase orgânica. Ademais, formulações com revestimento entérico foram testadas em tampão bicarbonato nos valores de molaridades fisiológicos para avaliar o impacto da espécie tamponante na dissolução do fármaco. Os parâmetros avaliados foram o sistema tampão (tampão bicarbonato vs. tampão fosfato), capacidade tamponante e pH médio. Em todas as abordagens, a dissolução também foi realizada em tampão farmacopeico para fins de comparação. Nossos resultados demonstraram que o método de dissolução farmacopeico não foi discriminativo, enquanto o meio com menor capacidade tamponante diferenciou entre as formulações obtidas via granulação úmida ou compressão direta. Ademais, a utilização da fase orgânica no teste de dissolução bifásica auxiliou no controle do pH do meio aquoso. Portanto, os métodos não compendiais aplicados foram mais discriminativos do que as condições de dissolução convencionais. Neste estudo, foi demonstrado como a dissolução bifásica e uma baixa capacidade tamponante podem ser usadas para avaliar as diferenças na performance de formulações. Esta pode ser uma abordagem valiosa durante os estágios iniciais do desenvolvimento de medicamentos para investigar a liberação destes sob condições fisiologicamente relevantes. Da mesma forma, todas as formulações com revestimento entérico exibiram uma liberação rápida em tampão de fosfato e atenderam às especificações farmacopeicas. Entretanto, a liberação do fármaco foi muito mais lenta em tampão de bicarbonato e consequentemente não cumpriram com as especificações farmacopeicas. Além disso, a natureza do fármaco (ácido vs. base) impactou o comportamento de dissolução no tampão de bicarbonato. Este estudo indica que o teste de dissolução convencional para comprimidos de liberação retardada não possui relevância fisiológica e precisa ser reavaliado. Portanto, os resultados desta tese demonstram de forma abrangente que diferenças significativas na performance condizentes com relatórios clínicos foram obtidas apenas quando as condições fisiológicas relevantes foram aplicadas. Esses resultados indicam que a hipótese central foi respondida positivamente

New drugs registered in Brazil from 2003 to 2013: analysis from the perspective of child health

This study aims to analyze the new drugs registered in Brazil from 2003 to 2013 from the perspective of childcare needs, drug safety and considering the disease burden of the country. This is a retrospective cohort study including new drugs registered in Brazil between 2003 and 2013. Drug indications were related to the Disability-Adjusted Life Year (DALY) of the 2015 Global Burden of Disease Study. Association between the number of new drugs and DALY was determined by Spearman's coefficient. Post-marketing safety alerts specific to the pediatric population have been identified in the WHO Drug Information Bulletin and on websites of drug regulatory agencies. A total of 134 new drugs were included in the cohort and 46 (34.3%) had a pediatric indication. There was no evidence of an association between the disease burden in children in Brazil and the number of pediatric drugs. The safety alert data associated with the pediatric population published after registration of the new drugs were scarce. The number of new drugs launched in Brazil with a pediatric indication was small, reflecting the international challenges of developing effective and safe medicines for children. No association was found between the number of new drugs and the disease burden.

COVID-19 Community Stabilization and Sustainability Framework: An Integration of the Maslow Hierarchy of Needs and Social Determinants of Health.

All levels of government are authorized to apply coronavirus disease 2019 (COVID-19) protection measures; however, they must consider how and when to ease lockdown restrictions to limit long-term societal harm and societal instability. Leaders that use a well-considered framework with an incremental approach will be able to gradually restart society while simultaneously maintaining the public health benefits achieved through lockdown measures. Economically vulnerable populations cannot endure long-term lockdown, and most countries lack the ability to maintain a full nationwide relief operation. Decision-makers need to understand this risk and how the Maslow hierarchy of needs and the social determinants of health can guide whole of society policies. Aligning decisions with societal needs will help ensure all segments of society are catered to and met while managing the crisis. This must inform the process of incremental easing of lockdowns to facilitate the resumption of community foundations, such as commerce, education, and employment in a manner that protects those most vulnerable to COVID-19. This study proposes a framework for identifying a path forward. It reflects on baseline requirements, regulations and recommendations, triggers, and implementation. Those desiring a successful recovery from the COVID-19 pandemic need to adopt an evidence-based framework now to ensure community stabilization and sustainability.

Defining an age cut-off for older offenders: a systematic review of literature.

PURPOSE: In the literature, 65 years is commonly used as the age to designate an older person in the community. When studying older prisoners, there is much variation. The purpose of this paper is to investigate how researchers define older offenders and for what reasons. DESIGN/METHODOLOGY/APPROACH: The authors reviewed articles on health and well-being of older offenders to assess terminology used to describe this age group, the chosen age cut-offs distinguishing younger offenders from older offenders, the arguments provided to support this choice as well as the empirical base cited in this context. FINDINGS: The findings show that the age cut-off of 50 years and the term "older" were most frequently used by researchers in the field. The authors find eight main arguments given to underscore the use of specific age cut-offs delineating older offenders. They outline the reasoning provided for each argument and evaluate it for its use to define older offenders. ORIGINALITY/VALUE: With this review, it is hoped to stimulate the much-needed discussion advancing towards a uniform definition of the older offender. Such a uniform definition would make future research more comparable and ensure that there is no ambiguity when researchers state that the study population is "older offenders".

3Ts of low cure rate: taxonomy, themes and theory of low cure rate in Pakistan's TB control programme and gathering a 360-degree perspective through qualitative, in-depth interviewing approach.

OBJECTIVE: WHO recommends cure of tuberculosis (TB) as the best prevention strategy; however, information about factors associated with low cure rate in patients with drug-susceptible TB is limited in Pakistan. Therefore, the purpose of this study was to explore the factors that account for low TB cure rate. METHODOLOGY: The present qualitative study recruited diverse informants through purposive sampling to explore low cure rate situation in Badin between March and June 2017. Data were collected from clinicians, paramedics, lab technicians, district field supervisors, patients and treatment supporters through indepth and face-to-face interviews. Interviews were conducted in local languages (Urdu and Sindhi) and transcribed into English. Coding structure was developed inductively and applied on textual data to draw output at the levels of taxonomy, themes and theory, as proposed by Bradley et al. FINDINGS: Thirty-seven individuals consented to participate in this study and provided detailed account of the subject under enquiry. Review of interview data collected from a variety of informants resulted in the identification of four broad factors (taxonomy) that contributed to the situation of low cure rate in one of the districts implementing the public-private mix intervention. These factors were (1) health-seeking behaviour, (2) technical capacity of the healthcare provider, (3) managerial capacity of the healthcare provider, and (4) access to healthcare facility and services. Each factor is deconstructed into key dimensions (themes) that emerged from the dialogue between the interviewer and the respondents. Moreover, dimensions were exemplified through underlying concepts that correspond to theories for low cure rate. CONCLUSION: Change in programme reporting requirement has demeaned the significance of having cure as treatment outcome. Therefore, returning the focus to achieving cure status for TB cases will be beneficial for assessing the effectiveness of TB control efforts. In parallel to the care delivery system, a mechanism for disseminating disease-related and treatment-related information should be introduced.

Understanding the care and support needs of older people: a scoping review and categorisation using the WHO international classification of functioning, disability and health framework (ICF).

BACKGROUND: The number of older people with unmet care and support needs is increasing substantially due to the challenges facing the formal and informal care system in the United Kingdom. Addressing these unmet needs is becoming one of the urgent public health priorities. In order to develop effective solutions to address some of these needs, it is important first to understand the care and support needs of older people. METHODS: A scoping review was conducted, using the Arksey and O'Malley original and enhanced framework, to understand the care and support needs of older people, focusing on those living at home with chronic conditions in the UK. The search was conducted using five electronic data bases, grey literature and reference list checks. The WHO International Classification of Functioning, Disability and Health (ICF) framework was used to analyse and categorise the literature findings. RESULTS: Forty studies were included in the final analysis- 32 from academic literature and 8 from grey literature. The review highlighted that older adults faced a range of physical, social and psychological challenges due to living with chronic conditions and required care and support in three main areas: 1) social activities and relationships; 2) psychological health; and 3) activities related to mobility, self-care and domestic life. The review also highlighted that many older people demonstrated a desire to cope with their illness and maintain independence, however, environmental factors interfered with these efforts including: 1) lack of professional advice on self-care strategies; 2) poor communication and coordination of services; and 3) lack of information on services such as care pathways. A gap in the knowledge was also identified about the care and support needs of two groups within the older population: 1) older workers; and 2) older carers. CONCLUSIONS: The review highlighted that older people living with chronic conditions have unmet care needs related to their physical and psychological health, social life, as well as the environment in which they live and interact. Findings of this review also emphasized the importance of developing care models and support services based around the needs of older people.

Burden of primary care-type emergency department presentations using clinical assessment by general practitioners: A cross-sectional study.

OBJECTIVE: To compare methods of assessment of the burden of primary care-type ED (PCTED) presentations against clinical assessment by general practitioners (GPs) in ED. METHODS: A cross-sectional study involving clinical assessment of patients presenting to four EDs in Western Australia. The GPs assessed patients who were likely to be discharged home from ED, and considered whether they could be managed in general practice. Patient presentations were defined by the GPs as: PCTED; PCTED if additional primary care resources were available; or not PCTED. RESULTS: GP researchers determined that 80% of patients assessed were PCTED presentations, with one-third of these considered PCTED presentations if additional resources were available. A high proportion of identified PCTED presentations included categories excluded by previous methods. Analysis of linked data found the cohort assessed to be of lower urgency, younger, and with a shorter length of stay than the average patient being discharged from ED. After accounting for potential bias, it is suggested that 20-40% of all ED presentations could be PCTED presentations. CONCLUSIONS: Previous methods determining the burden of PCTED presentations have not been validated. Many presentations excluded by previous methods were identified as manageable in general practice by GPs clinically assessing patients in ED. Improved validation of criteria used to identify PCTED presentations will enable appropriately designed interventions to reduce such events.

Medical Complexity among Children with Special Health Care Needs: A Two-Dimensional View.

OBJECTIVE: To identify subgroups of U.S. children with special health care needs (CSHCN) and characterize key outcomes. DATA SOURCE: Secondary analysis of 2009-2010 National Survey of CSHCN. STUDY DESIGN: Latent class analysis grouped individuals into substantively meaningful classes empirically derived from measures of pediatric medical complexity. Outcomes were compared among latent classes with weighted logistic or negative binomial regression. PRINCIPAL FINDINGS: LCA identified four unique CSHCN subgroups: broad functional impairment (physical, cognitive, and mental health) with extensive health care (Class 1), broad functional impairment alone (Class 2), predominant physical impairment requiring family-delivered care (Class 3), and physical impairment alone (Class 4). CSHCN from Class 1 had the highest ED visit rates (IRR 3.3, p < .001) and hospitalization odds (AOR: 12.0, p < .001) and lowest odds of a medical home (AOR: 0.17, p < .001). CSHCN in Class 3, despite experiencing more shared decision making and medical home attributes, had more ED visits and missed school than CSHCN in Class 2 (p < .001); the latter, however, experienced more cost-related difficulties, care delays, and parents having to stop work (p < .001). CONCLUSIONS: Recognizing distinct impacts of cognitive and mental health impairments and health care delivery needs on CSHCN outcomes may better direct future intervention efforts.

Classification of Support Needs for Elderly Outpatients with Diabetes Who Live Alone.

OBJECTIVES: To investigate the support needs of elderly patients with diabetes and to classify elderly patients with diabetes living alone on the basis of support needs. METHODS: Support needs were derived from a literature review of relevant journals and interviews of outpatients as well as expert nurses in the field of diabetes to prepare a 45-item questionnaire. Each item was analyzed on a 4-point Likert scale. The study included 634 elderly patients with diabetes who were recruited from 3 hospitals in Japan. Exploratory factor analysis was performed to determine the underlying structure of support needs, followed by hierarchical cluster analysis to clarify the characteristics of patients living alone (n=104) who had common support needs. RESULTS: Exploratory factor analysis suggested a 5-factor solution with 23 items: (1) hope for class and gatherings, (2) hope for personal advice including emergency response, (3) supportlessness and hopelessness, (4) barriers to food preparation, (5) hope of safe medical therapy. The hierarchical cluster analysis of subjects yielded 7 clusters, including a no special-support needs group, a collective support group, a self-care support group, a personal-support focus group, a life-support group, a food-preparation support group and a healthcare-environment support group. CONCLUSIONS: The support needs of elderly patients with diabetes who live alone can be divided into 2 categories: life and self-care support. Implementation of these categories in outpatient-management programs in which contact time with patients is limited is important in the overall management of elderly patients with diabetes who are living alone.

A Rural Taxonomy of Population and Health-Resource Characteristics.

This policy brief reports the newly developed taxonomy of rural places based on relevant population and health-resource characteristics; and discusses how this classification tool can be utilized by policy makers and rural communities. Key Findings. (1) We classified 10 distinct types of rural places based on characteristics related to both demand (population) and supply (health resources) sides of the health services market. (2) In descending order, the most significant dimensions in our classification were facility resources, provider resources, economic resources, and age distribution. (3) Each type of rural place was distinct from other types of places based on one or two defining dimensions.

What Occupational Health Needs Arise in Workplaces Following Disasters? A Joint Analysis of Eight Cases of Disaster in Japan.

OBJECTIVE: To identify occupational health needs arising after disasters. METHODS: Using semistructured interviews with expert informants, we jointly analyzed the needs arising in eight disaster cases that threatened the lives or health of workers in Japan. RESULTS: Various types of health issues occurred in a wide range of employees. In total, we identified 100 needs in six phases after disasters and classified them across nine categories of worker characteristics. The proportion of health needs on the list that were applicable in each case varied from 13% to 49%. More needs arose when the companies were responsible for the disaster and when employee lives were lost. We also assessed the list as fairly comprehensive. CONCLUSIONS: The list developed in this study is expected to be effective for anticipating occupational health needs after disasters.

Consumer Health Information Needs and Question Classification: Analysis of Hypertension Related Questions Asked by Consumers on a Chinese Health Website.

This study built up a classification schema of consumer health questions which consisted of 48 quaternary categories and 35 annotation rules. Using such a schema, we manually classified 2,000 questions randomly selected from nearly 100 thousand hypertension-related messages posted by consumers on a Chinese health website to analyze the information needs of health consumers. The results showed questions in the categories of treatment, diagnosis, healthy lifestyle, management, epidemiology, and health provider choosing were 48.1%, 23.8%, 11.9%, 5.2%, 9.0%, and 1.9% respectively. The comparison of the questions asked by consumers and physicians showed that their health information needs were significantly different (P<0.0001).

Prediction of care burden of patients undergoing haemodialysis: development of a measuring tool.

BACKGROUND: The ageing of the population and new options for therapy have led to an increase in the number of patients undergoing dialysis. Rising costs in health care and new financial structures impose funding constraints on dialysis departments and force the departments to deploy nurses more efficiently. Therefore, predicting the nursing time spent on the care of patients is important. OBJECTIVE: Development of a classification tool to predict the burden of nursing care of patients undergoing dialysis. DESIGN: Observational study. PARTICIPANTS: 242 patients on dialysis in 12 centres. MEASUREMENTS: The time spent on nursing care within predefined areas, including patient independence, vascular access, psychosocial support, dialysis complexity, communication and specific nursing actions, was measured by observers. Average times and their standard deviations (SD) were calculated. Variation of patient characteristics was analysed. RESULTS: The average care time required for the four routine investigated domains, namely independence, vascular access, psychosocial support and dialysis complexity, was 59.23 (SD = 24.30) minutes per treatment per patient. CONCLUSION: Our study shows that it is possible to predict the burden of nursing care of patients undergoing dialysis by means of a classification model.

Automated Classification of Consumer Health Information Needs in Patient Portal Messages.

Patients have diverse health information needs, and secure messaging through patient portals is an emerging means by which such needs are expressed and met. As patient portal adoption increases, growing volumes of secure messages may burden healthcare providers. Automated classification could expedite portal message triage and answering. We created four automated classifiers based on word content and natural language processing techniques to identify health information needs in 1000 patient-generated portal messages. Logistic regression and random forest classifiers detected single information needs well, with area under the curves of 0.804-0.914. A logistic regression classifier accurately found the set of needs within a message, with a Jaccard index of 0.859 (95% Confidence Interval: (0.847, 0.871)). Automated classification of consumer health information needs expressed in patient portal messages is feasible and may allow direct linking to relevant resources or creation of institutional resources for commonly expressed needs.

The need to improve health care in prisons.

OBJECTIVE: To analyze physical structure, working conditions of health professionals and outline of the procedures established in prisons. METHODS: We analyzed 34 provisional detention centers and 69 male and six female prison units in the state of Sao Paulo, Southeastern Brazil, in 2009. A self-applied instrument was developed to collect quantitative data on the characteristics of health care structure, equipment and personnel in prisons. Analysis of variance (ANOVA) or equivalent non-parametric tests and Chi-square or Fisher's tests were used to compare categorical and continuous variables, respectively, between the groups. RESULTS: The main problems were delays in the results of laboratory tests and imaging. With respect to the teams, it was observed that a large majority were in conditions close to those proposed by the Bipartite Commission 2013 but without improvement being reflected in the indicators. With respect to the process, more than 60.0% of prisons located in small towns do not have the structural conditions to ensure secondary or tertiary health care for the continuity of treatment. CONCLUSIONS: This profile of prisons in the country can be used for planning and monitoring future actions for the continuous improvement of healthcare processes.