Using the diagnostic odds ratio to select multivariate sequential patterns in order to build an interpretable pattern-based classifier in a clinical domain (Preprint)

Background

It is important to exploit all available data on patients in settings such as intensive care burn units (ICBUs), where several variables are recorded over time. It is possible to take advantage of the multivariate patterns that model the evolution of patients to predict their survival. However, pattern discovery algorithms generate a large number of patterns, of which only some are relevant for classification.

Objective

We propose to use the diagnostic odds ratio (DOR) to select multivariate sequential patterns used in the classification in a clinical domain, rather than employing frequency properties.

Methods

We used data obtained from the ICBU at the University Hospital of Getafe, where 6 temporal variables for 465 patients were registered every day during 5 days, and to model the evolution of these clinical variables, we used multivariate sequential patterns by applying 2 different discretization methods for the continuous attributes. We compared 4 ways in which to employ the DOR for pattern selection: (1) we used it as a threshold to select patterns with a minimum DOR; (2) we selected patterns whose differential DORs are higher than a threshold with regard to their extensions; (3) we selected patterns whose DOR CIs do not overlap; and (4) we proposed the combination of threshold and nonoverlapping CIs to select the most discriminative patterns. As a baseline, we compared our proposals with Jumping Emerging Patterns, one of the most frequently used techniques for pattern selection that utilizes frequency properties.

Results

We have compared the number and length of the patterns eventually selected, classification performance, and pattern and model interpretability. We show that discretization has a great impact on the accuracy of the classification model, but that a trade-off must be found between classification accuracy and the physicians’ capacity to interpret the patterns obtained. We have also identified that the experiments combining threshold and nonoverlapping CIs (Option 4) obtained the fewest number of patterns but also with the smallest size, thus implying the loss of an acceptable accuracy with regard to clinician interpretation. The best classification model according to the trade-off is a JRIP classifier with only 5 patterns (20 items) that was built using unsupervised correlation preserving discretization and differential DOR in a beam search for the best pattern. It achieves a specificity of 56.32% and an area under the receiver operating characteristic curve of 0.767.

Conclusions

A method for the classification of patients’ survival can benefit from the use of sequential patterns, as these patterns consider knowledge about the temporal evolution of the variables in the case of ICBU. We have proved that the DOR can be used in several ways, and that it is a suitable measure to select discriminative and interpretable quality patterns.

Combination gel of 2% amitriptyline and 0.5% ketamine to treat refractory erythromelalgia pain - a case report of pain control success

Erythromelalgia (EM) is a rare autosomal dominant neuropathy characterized by the combination of severe burning pain and erythematous warm extremities. Chronic pain control is most often unsuccessful and a completely effective therapy is yet to be identified. Recent studies have reported significant improvements in pain management using a combination of amitriptyline and ketamine in a topical formulation. We describe a 1-year follow-up pain control success case of a male patient with EM, proposed for topical use of a 2% Amitriptyline and 0.5% Ketamine gel.

Combination gel of 2% amitriptyline and 0.5% ketamine to treat refractory erythromelalgia pain - a case report of pain control success

Erythromelalgia (EM) is a rare autosomal dominant neuropathy characterized by the combination of severe burning pain and erythematous warm extremities. Chronic pain control is most often unsuccessful and a completely effective therapy is yet to be identified. Recent studies have reported significant improvements in pain management using a combination of amitriptyline and ketamine in a topical formulation. We describe a 1-year follow-up pain control success case of a male patient with EM, proposed for topical use of a 2% Amitriptyline and 0.5% Ketamine gel.

Online psychological therapy for kids during social distancing: A study case in a brazilian clinical setting

Introduction

In response to the spread of COVID-19, many Brazilian therapists faced the challenge of taking their practices online considering legal and ethical issues, besides learning to handle new technologies in a way the therapeutic setting was maintained. The cooperation of the family is fundamental for the creation and maintenance of an adequate therapeutic setting. Children are not sufficiently mature to speak clearly about what bothers them or to talk about how they feel and why, so, drawing, pretend playing, story telling, playing games are the common tools for children’s communication during therapy.

Objectives

Evaluating if online therapy for children can support therapeutic play tools and be effective in a virtual environment preserving the therapeutic setting.

Methods

Two children aged 6 to 11 attended the psychological sessions that were conducted through video calls.The family should provide a silent and private room for those sessions. The children were free to choose the toy they would like to play with and that was available at home such as board games, comic and story books. Mimicry, drawing, an adaptation of the Winnicott Squiggle Game were used, as well as electronic games through screen sharing.

Results

The emotional conflicts were expressed either through conventional games and play or electronic games. Playing with children online was possible as well as maintaining the therapeutic alliance in order to carry on with the treatment in a proper therapeutic setting.

Conclusions

Online therapy for kids showed to be an effective form of service delivery, under strict measures of social distancing in Brazil.

Intervention to promote physical activation and improve sleep and response feeding in infants for preventing obesity early in life, the baby-act trial: Rationale and design

Infant obesity is increasing in the US, particularly among Hispanics. Rapid weight gain during infancy increases the risk of obesity later in life and could be prevented through multi-modal interventions addressing multiple risk factors through population-level programs.

OBJECTIVES

1) determine the extent to which the intervention, compared with the usual care control condition, improves healthy weight gain and specific behaviors (physical activity, sleep, diet) in the first year of life and 2) evaluate the cost of the intervention as a modification of the current WIC standard of care.

METHODS

The lifestyle intervention focuses on age-appropriate infant physical activation, healthy sleep and sedentary patterns, and response feeding, by improving parenting skills delivered through a combination of technology (web-platform and text messages) and phone counseling. It is being tested among caregivers of infant participants of the Puerto Rico WIC program through a cluster-randomized controlled trial in 14 WIC clinics in San Juan starting in pregnancy until the infant is 12 months of age. The main outcome is infant rate of weight gain at 12 months; secondary outcomes include objectively measured hours of infant movement, sedentary behaviors and sleep, diet quality score and response feeding behaviors. We are also recording fees, time and personnel involved in the intervention development, maintenance and dissemination.

CONCLUSIONS

If successful, the intervention could be incorporated as a 'best practice' through WIC policy as a means to strengthen obesity prevention efforts to improve minority health and eliminate health disparities among Hispanics and possibly other at-risk groups beyond the childhood period. Clinicaltrials.gov registration: NCT03517891.

The Retrochiasmal Optic Pathway: A Link in Jeopardy

The case of an intraventricular meningioma is presented and the visual complication incurred by its surgical resection is discussed. The importance of selecting the most optimal surgical approach and the basis for that selection are highlighted.

GEOTECNOLOGIAS APLICADA NOS CONFLITOS DE USO DO SOLO EM ÁREAS DE PRESERVAÇÃO PERMANENTE NO MUNICÍPIO DE BARRA BONITA/SP

As áreas de conflito são definidas pelo mau uso do solo pelo homem e vem causando sérios problemas ao meio ambiente, resultando em desequilíbrio ecológico e desgaste dos recursos naturais, especialmente quando se refere às áreas de preservação permanente, que têm importância fundamental para os ecossistemas de equilíbrio e preservação dos recursos hídricos. O planejamento é um fator chave para o controle dos impactos ambientais ao meio ambiente. As áreas de preservação permanente evitam o assoreamento e erosão proporcionando uma proteção natural, principalmente em áreas das nascentes. Os serviços ambientais prestados auxiliam a proteção da flora e fauna, na preservação dos corredores ecológicos, e na continuação das espécies ali presentes. Este estudo teve por objetivo avaliar os conflitos de uso e ocupação da terra em áreas de Preservação Permanente do município de Barra Bonita/SP, utilizando como base cartográfica, o Sistema de Informação Geográfica (SIG) e imagem de satélite Sentinel 2-A de 2017, em escala 1:10.000. Os resultados mostraram que quase ¾ da área é ocupado com cana-de-açúcar (72,72%) e que as áreas de preservação permanente estão sendo usados inadequadamente por cana-de-açúcar (72,75%). O SIG ArcGis e as técnicas de geoprocessamento demonstraram agilidade e eficiência na identificação, quantificação e edição de mapas de uso do solo, preservação permanente e de conflitos em áreas de preservação permanente.

Non-adhesion to therapy in the elderly, in Tábua

Introduction Most medicines are taken by the elderly because they suffer natural changes, which lead to chronic and degenerative diseases. Older people often have increasingly complex medication regimens, which may lead to errors with dosing and administration and to non-adherence to therapy. Non-adherence to therapy leads to a decrease in therapeutic efficacy, an increase in morbidity, suffering, and health costs. It is influenced by several factors that can and should be driven to improve health status.

Objectives The objective of this study was to determine and evaluate the medication regimen complexity in an elderly population, in Tábua, and verify its relation with adherence to therapy.

Methodology Surveys were applied to elderly people in order to collect the medication data. The study lasted for 5 months and took place at a pharmacy (n = 337). Only people with ≥65 years were included. Medication regimen complexity was assessed using the Brazilian translation for the Medication Regimen Complexity Index (MRCI) and adhesion to therapy was measured by MAT scale. Data was analysed with SPSS statistical program, version 24.0.

Results Our study showed a high percentage of adhesion to therapy (65%) and also of polypharmacy among the elderly (84,9%). Most medication that elderly take belong to the cardiovascular system pharmaceutical group (94,1%). Still, people described some difficulties to adhesion to therapy, mainly forgetfulness (73,66%). Data also revealed that individuals with more literacy and those who are not under polypharmacy showed more adherence to therapy (p = 0.000 and p = 0.012). The most significant result from our study was that MRCI and non-adherence are correlated statistically, that is, a higher MRCI leads to an increase in non-adherence to therapy (p = 0.001).

Conclusion Healthcare professionals should be aware that high levels of medication regimen complexity suggest bad outcomes and non-adherence to therapy. They should assist the elderly, help avoid errors, and find solutions to improve adherence to therapy, whenever possible.

Histopathological hallmarks of cutaneous lesions of capillary malformation-arteriovenous malformation syndrome

IMPORTANCE

Capillary malformation-arteriovenous malformation (CM-AVM) syndrome is a recently described syndrome with distinctive cutaneous lesions. Very little is known about the histopathology of these lesions.

OBJECTIVE

The purpose of the study was to evaluate the histopathological characteristics of the pink macules of the CM-AVM syndrome and to investigate if these pink macules could be classified as capillary malformations or arteriovenous malformations based on their histopathological features.

DESIGN-SETTINGS-PARTICIPANTS

We conducted a retrospective multicenter study involving eight hospitals in Spain. Fifteen biopsies from pink macules of the CM-AVM syndrome were analysed and compared with five biopsies of diverse capillary malformations and three stage I arteriovenous malformations.

RESULTS

Pink macules' biopsies of the CM-AVM syndrome showed similar features including a high vascular density encompassing capillaries and numerous thick-walled arterioles mainly located in the superficial dermis, a predominance of elongated over round vessels, scarce or absent erythrocytes within the lumina and discrete perivascular inflammation. CMs were characterized by an increased number of capillary-type vessels mostly rounded and located in the upper dermis. AVMs were composed by highly increased numbers of vessels with a branching pattern involving the full thickness of the dermis, without erythrocytes within the lumina. Wilms tumour 1 protein was positive in the endothelial cells both in pink macules of the CM-AVM and in arteriovenous malformations.

CONCLUSIONS AND RELEVANCE

Pink macules of the CM-AVM syndrome seem to be different from capillary malformations. Our results suggest that histologically and immunohistochemically they are closer to incipient arteriovenous malformations than to capillary malformations. A deepened knowledge about the nature of these skin lesions will contribute to the better understanding of capillary malformation-arteriovenous malformation syndrome, and will open the possibility of new and more specific treatments in the future.

[COVID-19: how to transform a noninvasive ventilation device in a critical care ventilator]

La pandemia del COVID-19 ha hecho estragos, no solo en el número de víctimas fatales sino también en la infraestructura de los hospitales y unidades de cuidados intensivos. El número limitado de respiradores es una preocupación de toda la comunidad dada la demanda masiva y a muy corto plazo de estos equipos. Esta presentación tiene como fin dar soluciones sencillas para ventilar pacientes intubados de modo mandatorio utilizando equipos de ventilación no invasiva. Las soluciones propuestas permiten 2 estrategias claras frente al COVID-19: Reemplazar las máquinas de anestesia para disponer de ellas en pacientes. Usar la opción de equipos de ventilación no invasiva para pacientes con COVID-19 a modo de «puente» y a la espera de la liberación de un respirador específico en la unidad de cuidados críticos.

DECLIVIDADE E POTENCIAL PARA MECANIZAÇÃO AGRÍCOLA DA BACIA HIDROGRÁFICA DO RIBEIRÃO PEDERNEIRAS - PEDERNEIRAS/SP

A declividade do terreno contribui para o escoamento das águas, pois quanto maior for o trecho em declive, maior será o escoamento da água pela superfície, arrastando outros materiais para os recursos hídricos superficiais, influenciando a qualidade da água e a infiltração e nos processos erosivos fluviais e pluviais, assim como na tipologia da vegetação, bem como contribui para a formação do solo e serve de indicador na definição de áreas de risco e restrição de uso. A declividade dos rios pode ser associada à velocidade do escoamento, transporte de sedimentos e conformação das áreas de preservação permanentes. Este trabalho teve como objetivo analisar a declividade do terreno na bacia hidrográfica do ribeirão Pederneiras, estado de São Paulo e classificá-la quanto as áreas aptas e inaptas à mecanização agrícola. A área de estudo está localizada entre as coordenadas geográficas 22°20' e 22°26' de latitude S e 48°44' e 48°56' de longitude W Gr., situadas nos municípios de Agudos e Pederneiras, do estado de São Paulo, com uma área de 14918,28 ha. Os mapas de declividade foram elaborados por meio de técnicas de geoprocessamento, tendo-se como base cartográfica: as cartas planialtimétricas do Instituto Brasileiro de Geografia e Estatística e a imagem do satélite Sentinel-2 em ambiente de Sistema de Informação Geográfica – ArcGis 10.4.1. As classes de declividade do solo foram classificadas como relevo plano (0 – 3%), suave ondulado (3 – 8%), ondulado (8 – 20%), forte ondulado (20 – 45%), montanhoso (45 – 75%) e escarpado (> 75%) e áreas para mecanização agrícola como aptas (áreas mecanizáveis) e inaptas (áreas não mecanizáveis). Os resultados mostraram que o relevo plano e suavemente ondulado predominou em quase 89% da área, enquadrando-as em áreas aptas à mecanização com pequenas restrições. v

Nucleoid Size Scaling and Intracellular Organization of Translation across Bacteria

The scaling of organelles with cell size is thought to be exclusive to eukaryotes. Here, we demonstrate that similar scaling relationships hold for the bacterial nucleoid. Despite the absence of a nuclear membrane, nucleoid size strongly correlates with cell size, independent of changes in DNA amount and across various nutrient conditions. This correlation is observed in diverse bacteria, revealing a near-constant ratio between nucleoid and cell size for a given species. As in eukaryotes, the nucleocytoplasmic ratio in bacteria varies greatly among species. This spectrum of nucleocytoplasmic ratios is independent of genome size, and instead it appears linked to the average population cell size. Bacteria with different nucleocytoplasmic ratios have a cytoplasm with different biophysical properties, impacting ribosome mobility and localization. Together, our findings identify new organizational principles and biophysical features of bacterial cells, implicating the nucleocytoplasmic ratio and cell size as determinants of the intracellular organization of translation.

Haemodynamic and analgesic control in a perioperative opioid-free approach to bariatric surgery - A case report

New approaches to bariatric surgery aim to achieve stress-free anaesthesia with sympathetic stability to protect organs and provide sufficient tissue perfusion, analgesia and rapid emergence. Opioid-free and multimodal approaches to anaesthesia provide intra- and post-operative sedation and analgesia, particularly advantageous in morbidly obese patients, but their feasibility and efficacy are still disputed. We describe the case of a female patient proposed for laparoscopic bariatric surgery, conducted under an opioid-free anaesthesia protocol, the haemodynamic, ventilatory and analgesic control, and intra- and post-operative monitoring and complications.

Application of Machine Learning Methods to Ambulatory Circadian Monitoring (ACM) for Discriminating Sleep and Circadian Disorders

The present study proposes a classification model for the differential diagnosis of primary insomnia (PI) and delayed sleep phase disorder (DSPD), applying machine learning methods to circadian parameters obtained from ambulatory circadian monitoring (ACM). Nineteen healthy controls and 242 patients (PI = 184; DSPD = 58) were selected for a retrospective and non-interventional study from an anonymized Circadian Health Database (https://kronowizard.um.es/). ACM records wrist temperature (T), motor activity (A), body position (P), and environmental light exposure (L) rhythms during a whole week. Sleep was inferred from the integrated variable TAP (from temperature, activity, and position). Non-parametric analyses of TAP and estimated sleep yielded indexes of interdaily stability (IS), intradaily variability (IV), relative amplitude (RA), and a global circadian function index (CFI). Mid-sleep and mid-wake times were estimated from the central time of TAP-L5 (five consecutive hours of lowest values) and TAP-M10 (10 consecutive hours of maximum values), respectively. The most discriminative parameters, determined by ANOVA, Chi-squared, and information gain criteria analysis, were employed to build a decision tree, using machine learning. This model differentiated between healthy controls, DSPD and three insomnia subgroups (compatible with onset, maintenance and mild insomnia), with accuracy, sensitivity, and AUC >85%. In conclusion, circadian parameters can be reliably and objectively used to discriminate and characterize different sleep and circadian disorders, such as DSPD and OI, which are commonly confounded, and between different subtypes of PI. Our findings highlight the importance of considering circadian rhythm assessment in sleep medicine.

A methodology based on multiple criteria decision analysis for combining antibiotics in empirical therapy

BACKGROUND

The current situation of critical progression in resistance to more effective antibiotics has forced the reuse of old highly toxic antibiotics and, for several reasons, the extension of the indications of combined antibiotic therapy as alternative options to broad spectrum empirical mono-therapy. A key aspect for selecting an appropriate and adequate antimicrobial therapy is that prescription must be based on local epidemiology and knowledge since many aspects, such as prevalence of microorganisms and effectiveness of antimicrobials, change from hospitals, or even areas and services within a single hospital. Therefore, the selection of combinations of antibiotics requires the application of a methodology that provides objectivity, completeness and reproducibility to the analysis of the detailed microbiological, epidemiological, pharmacological information on which to base a rational and reasoned choice.

METHODS

We proposed a methodology for decision making that uses a multiple criteria decision analysis (MCDA) to support the clinician in the selection of an efficient combined empiric therapy. The MCDA includes a multi-objective constrained optimization model whose criteria are the maximum efficacy of therapy, maximum activity, the minimum activity overlapping, the minimum use of restricted antibiotics, the minimum toxicity of antibiotics and the activity against the most prevalent and virulent bacteria. The decision process can be defined in 4 steps: (1) selection of clinical situation of interest, (2) definition of local optimization criteria, (3) definition of constraints for reducing combinations, (4) manual sorting of solutions according to patient's clinical conditions, and (5) selection of a combination.

EXPERIMENTS AND RESULTS

In order to show the application of the methodology to a clinical case, we carried out experiments with antibiotic susceptibility tests in blood samples taken during a five years period at a university hospital. The validation of the results consists of a manual review of the combinations and experiments carried out by an expert physician that has explained the most relevant solutions proposed according to current clinical knowledge and their use.

CONCLUSION

We show that with the decision process proposed, the physician is able to select the best combined therapy according to different criteria such as maximum efficacy, activity and minimum toxicity. A method for the recommendation of combined antibiotic therapy developed on the basis of a multi-objective optimization model may assist the physicians in the search for alternatives to the use of broad-spectrum antibiotics or restricted antibiotics for empirical therapy. The decision proposed can be easily reproduced for any local epidemiology and any different clinical settings.

Validation of a Device for the Ambulatory Monitoring of Sleep Patterns: A Pilot Study on Parkinson's Disease

The development of wearable devices has increase interest in the use of ambulatory methods to detect sleep disorders more objectively than those permitted by subjective scales evaluating sleep quality, while subjects maintain their usual lifestyle. This study aims to validate an ambulatory circadian monitoring (ACM) device for the detection of sleep and wake states and apply it to the evaluation of sleep quality in patients with Parkinson disease (PD). A polysomnographic validation study was conducted on a group of patients with different sleep disorders in a preliminary phase, followed by a pilot study to apply this methodology to PD patients. The ACM device makes it possible to estimate the main sleep parameters very accurately, as demonstrated by: (a) the lack of significant differences between the mean values detected by PSG and ACM in time in bed (TIB), total sleep time (TST), sleep efficiency (SE), and time awake after sleep onset (WASO); (b) the slope of the correlation lines between the parameters estimated by the two procedures, very close to 1, which demonstrates the linearity of the predictions; (c) the low bias value in the estimates obtained through ACM. Sleep in PD is associated with lower distal skin temperature, efficiency and overall sleep time; greater WASO, activity during sleep and duration of naps and a worse circadian function index. In summary, the ACM device has proven to be clinically useful to evaluate sleep in an objective manner, thanks to the integrated management of different complementary variables, having advantages over conventional actigraphy.

MODELO AUTOMÁTICO DE CLASSIFICAÇÃO DE BOVINOS PARA O ABATE VIA REDES NEURAIS ARTIFICIAIS

Hoje em dia, a busca por ferramentas que facilitam e até mesmo substituem o trabalho humano têm ganhado grande destaque mundial. As redes neurais artificiais (RNAs) é uma dessas ferramentas, pois apresentam uma quantidade de aplicações, principalmente quando se trata de classificação de dados, reconhecimento de padrões, análise de imagens, entre outros. Com este intuito, o objetivo deste trabalho foi desenvolver uma ferramenta de classificação automática de bovinos por intermédio de uma Rede Neural Artificial (RNA) de três camadas. Essa rede é conhecida como Multilayer Perceptron (MLP), aqui do tipo feed forward (sem realimentação) e com algoritmo de treinamento backpropagation (retropropagação do erro) com treinamento supervisionado. A ideia foi identificar os grupos de abate e os que requerem alimentação mais intensiva, utilizando como variáveis de entrada da rede massa e altura e como variável de saída, o índice de massa corporal (IMC). Os dados utilizados neste trabalho foram obtidos de um rebanho de 147 vacas Nelore, localizadas na cidade de Santa Rita do Pardo - Mato Grosso do Sul (MS). Dos resultados, a rede obteve um excelente desempenho na fase de treinamento (100 amostras), com erro quadrado médio em torno de 10-5. Já na fase do diagnóstico (operação da rede), foi submetida à rede as 47 amostras restantes dos dados de vacas Nelore que não fizeram parte do treinamento da mesma, desses resultados, a rede apresentou em média, um erro em torno de 0,6% em relação à saída desejada (dados normalizados), o que acarretou num erro de 1 amostra das 47 analisadas.