Ibero-Panamerican Federation of Periodontology Delphi study on the trends of periodontology and periodontics by the year 2030. A Latin American consensus.

BACKGROUND AND OBJECTIVE: As elsewhere in the world, the prevalence of periodontitis in stages I-II is high in the Latin American population, this scenario emphasizes the need for identification of urgent needs for allocating adequate resources to provide diagnosis, prevention, and treatment of these diseases. The aim of this Delphi study was to predict the trends in periodontology/periodontics in the Latin American region by the year 2030. METHODS: A steering committee and an advisory group of experts in periodontology/periodontics were selected from 16 countries. An open questionnaire of 60 questions was validated and used following the Delphi methodology. RESULTS: Two hundred and twenty-five experts from Latin America answered the two rounds of the questionnaire. Moderate to strong consensus was reached on 45 questions (75%). The prediction was that the prevalence of gingivitis and periodontitis in stages I and II will be maintained, the importance of the link with systemic diseases will increase, and the impact of prevention and periodontal treatment will also increase, mainly in the private sector. There was a strong consensus that plastic and regenerative surgical procedures will increase, as well as the demand for training in the specialty of periodontology. CONCLUSIONS: The present study has provided relevant and useful information on predictions in periodontology/periodontics in Latin America, with important level of consensus among experts. It has been predicted that periodontitis will still be a highly prevalent disease, and its links with other medical conditions should demand more attention by health authorities to develop adequate prevention and management policies and strategies.

Named Entity Recognition in Electronic Health Records: A Methodological Review.

OBJECTIVES: A substantial portion of the data contained in Electronic Health Records (EHR) is unstructured, often appearing as free text. This format restricts its potential utility in clinical decision-making. Named entity recognition (NER) methods address the challenge of extracting pertinent information from unstructured text. The aim of this study was to outline the current NER methods and trace their evolution from 2011 to 2022. METHODS: We conducted a methodological literature review of NER methods, with a focus on distinguishing the classification models, the types of tagging systems, and the languages employed in various corpora. RESULTS: Several methods have been documented for automatically extracting relevant information from EHRs using natural language processing techniques such as NER and relation extraction (RE). These methods can automatically extract concepts, events, attributes, and other data, as well as the relationships between them. Most NER studies conducted thus far have utilized corpora in English or Chinese. Additionally, the bidirectional encoder representation from transformers using the BIO tagging system architecture is the most frequently reported classification scheme. We discovered a limited number of papers on the implementation of NER or RE tasks in EHRs within a specific clinical domain. CONCLUSIONS: EHRs play a pivotal role in gathering clinical information and could serve as the primary source for automated clinical decision support systems. However, the creation of new corpora from EHRs in specific clinical domains is essential to facilitate the swift development of NER and RE models applied to EHRs for use in clinical practice.

Factors Associated with the Extent of Clinical Attachment Loss in Periodontitis: A Multicenter Cross-Sectional Study.

Periodontitis has significant public health implications, affecting individuals' overall health, well-being, and quality of life. This study aimed to assess the risk factors associated with the extent of clinical attachment loss (CAL) in a population diagnosed with periodontitis. Six hundred and sixty-seven patients with different degrees of CAL (mild, n = 223; moderate, n = 256; and advanced, n = 188) were enrolled. Socio-demographics, lifestyle, microbiological profiles, specific immune response, obesity, and single-nucleotide polymorphism of the IL1 gene were determined. Unconditional logistic regression models were conducted to determine the factors associated with the extent of CAL. Aging, smoking, microbial factors, plaque index, and IgG2 antibodies against Aggregatibacter actinomycetemcomitans were associated with advanced CAL. IgG2 antibodies against A. actinomycetemcomitans (OR 1.50; CI 95% 1.23-1.81), plaque accumulation (OR 2.69; CI 95% 2.20-3.29), Porphyromonas gingivalis (OR 1.93; CI 95% 1.35-2.76), Tanerella forsythia (OR 1.88; CI 95%1.30-2.70), and current smoking (OR 1.94; CI 95% 1.31-2.87) were associated with advanced CAL. Gene IL polymorphisms, obesity, and stress were not associated with the extent of CAL. Aging, plaque accumulation, smoking, and having antibodies against A. actinomycetemcomitans were the most critical factors associated with advanced CAL. In contrast, obesity, stress, and gene polymorphisms were not associated with the extent of CAL.

Characterization of Rice Yield Based on Biomass and SPAD-Based Leaf Nitrogen for Large Genotype Plots.

The use of Unmanned Aerial Vehicle (UAV) images for biomass and nitrogen estimation offers multiple opportunities for improving rice yields. UAV images provide detailed, high-resolution visual information about vegetation properties, enabling the identification of phenotypic characteristics for selecting the best varieties, improving yield predictions, and supporting ecosystem monitoring and conservation efforts. In this study, an analysis of biomass and nitrogen is conducted on 59 rice plots selected at random from a more extensive trial comprising 400 rice genotypes. A UAV acquires multispectral reflectance channels across a rice field of subplots containing different genotypes. Based on the ground-truth data, yields are characterized for the 59 plots and correlated with the Vegetation Indices (VIs) calculated from the photogrammetric mapping. The VIs are weighted by the segmentation of the plants from the soil and used as a feature matrix to estimate, via machine learning models, the biomass and nitrogen of the selected rice genotypes. The genotype IR 93346 presented the highest yield with a biomass gain of 10,252.78 kg/ha and an average daily biomass gain above 49.92 g/day. The VIs with the highest correlations with the ground-truth variables were NDVI and SAVI for wet biomass, GNDVI and NDVI for dry biomass, GNDVI and SAVI for height, and NDVI and ARVI for nitrogen. The machine learning model that performed best in estimating the variables of the 59 plots was the Gaussian Process Regression (GPR) model with a correlation factor of 0.98 for wet biomass, 0.99 for dry biomass, and 1 for nitrogen. The results presented demonstrate that it is possible to characterize the yields of rice plots containing different genotypes through ground-truth data and VIs.

Negation-based transfer learning for improving biomedical Named Entity Recognition and Relation Extraction.

BACKGROUND AND OBJECTIVES: Named Entity Recognition (NER) and Relation Extraction (RE) are two of the most studied tasks in biomedical Natural Language Processing (NLP). The detection of specific terms and entities and the relationships between them are key aspects for the development of more complex automatic systems in the biomedical field. In this work, we explore transfer learning techniques for incorporating information about negation into systems performing NER and RE. The main purpose of this research is to analyse to what extent the successful detection of negated entities in separate tasks helps in the detection of biomedical entities and their relationships. METHODS: Three neural architectures are proposed in this work, all of them mainly based on Bidirectional Long Short-Term Memory (Bi-LSTM) networks and Conditional Random Fields (CRFs). While the first architecture is devoted to detecting triggers and scopes of negated entities in any domain, two specific models are developed for performing isolated NER tasks and joint NER and RE tasks in the biomedical domain. Then, weights related to negation detection learned by the first architecture are incorporated into those last models. Two different languages, Spanish and English, are taken into account in the experiments. RESULTS: Performance of the biomedical models is analysed both when the weights of the neural networks are randomly initialized, and when weights from the negation detection model are incorporated into them. Improvements of around 3.5% of F-Measure in the English language and more than 7% in the Spanish language are achieved in the NER task, while the NER+RE task increases F-Measure scores by more than 13% for the NER submodel and around 2% for the RE submodel. CONCLUSIONS: The obtained results allow us to conclude that negation-based transfer learning techniques are appropriate for performing biomedical NER and RE tasks. These results highlight the importance of detecting negation for improving the identification of biomedical entities and their relationships. The explored techniques show robustness by maintaining consistent results and improvements across different tasks and languages.

Geometry Regularized Autoencoders.

A fundamental task in data exploration is to extract low dimensional representations that capture intrinsic geometry in data, especially for faithfully visualizing data in two or three dimensions. Common approaches use kernel methods for manifold learning. However, these methods typically only provide an embedding of the input data and cannot extend naturally to new data points. Autoencoders have also become popular for representation learning. While they naturally compute feature extractors that are extendable to new data and invertible (i.e., reconstructing original features from latent representation), they often fail at representing the intrinsic data geometry compared to kernel-based manifold learning. We present a new method for integrating both approaches by incorporating a geometric regularization term in the bottleneck of the autoencoder. This regularization encourages the learned latent representation to follow the intrinsic data geometry, similar to manifold learning algorithms, while still enabling faithful extension to new data and preserving invertibility. We compare our approach to autoencoder models for manifold learning to provide qualitative and quantitative evidence of our advantages in preserving intrinsic structure, out of sample extension, and reconstruction. Our method is easily implemented for big-data applications, whereas other methods are limited in this regard.

Synchronization between videofluoroscopic swallowing study and surface electromyography in patients with neurological involvement presenting symptoms of dysphagia / Sincronización entre la videodeglución y la electromiografía de superficie en pacientes con afectación neurológica y síntomas de disfagia

Introduction: Dysphagia is defined as the difficulty in transporting food and liquids from the mouth to the stomach. The gold standard to diagnose this condition is the videofluoroscopic swallowing study. However, it exposes patients to ionizing radiation. Surface electromyography is a non-radioactive alternative for dysphagia evaluation that records muscle electrical activity during swallowing. Objective: To evaluate the relationship between the relative activation times of the muscles involved in the oral and pharyngeal phases of swallowing and the kinematic events detected in the videofluoroscopy. Materials and methods: Electromiographic signals from ten patients with neurological involvement who presented symptoms of dysphagia were analyzed simultaneously with videofluoroscopy. Patients were given 5 ml of yogurt, 10 ml of water, and 3 g of crackers. Masseter, suprahyoid, and infrahyoid muscle groups were studied bilaterally. The bolus transit through the mandibular line, vallecula, and the cricopharyngeus muscle was analyzed in relation to the onset and offset times of each muscle group activation. Results: The average time of the pharyngeal phase was 0.89 ± 0.12 s. Muscle activation was mostly observed prior to the bolus transit through the mandibular line and vallecula. The end of the muscle activity suggested that the passage of the bolus through the cricopharyngeus muscle was almost complete. Conclusión: The muscle activity times, duration of the pharyngeal phase, and sequence of the muscle groups involved in swallowing were determined using sEMG validated with the videofluoroscopic swallowing study.

Introducción. La disfagia se define como la dificultad para movilizar la comida desde la boca hasta el estómago. La prueba diagnóstica para esta condición es la videofluoroscopia, la cual no es totalmente inocua pues utiliza radiación ionizante. La electromiografía de superficie registra la actividad eléctrica de los músculos de manera no invasiva, por lo que puede considerarse como una alternativa para evaluar la deglución y estudiar la disfagia. Objetivo. Evaluar la relación entre los tiempos relativos de activación de los músculos implicados en la fase oral y faríngea de la deglución, con los movimientos registrados durante la videofluoroscopia. Materiales y métodos. Se analizaron las señales de la electromiografía de superficie de 10 pacientes neurológicos con síntomas de disfagia, captadas en forma simultánea con la videofluoroscopia. Se suministraron 5 ml de yogur y 10 ml de agua, y 3 g de galleta. Se estudiaron bilateralmente los grupos musculares maseteros, suprahioideos e infrahioideos. Se analizó el paso del bolo por la línea mandibular, las valleculas y el músculo cricofaríngeo, correlacionándolo con el tiempo inicial y el final de la activación de cada uno de los grupos musculares. Resultados. El tiempo promedio de la fase faríngea fue de 0,89 ± 0,12 s. En la mayoría de los casos, hubo activación muscular antes del paso por la línea mandibular y las valleculas. La terminación de la actividad muscular parece corresponder al momento en que se completa el paso del bolo alimenticio por el músculo cricofaríngeo. Conclusión. Se determinaron los tiempos de actividad muscular, la duración de la fase faríngea y la secuencia de la activación de los grupos musculares involucrados en la deglución, mediante electromiografía de superficie, validada con la videofluoroscopia.

Sincronización entre la videodeglución y la electromiografía de superficie en pacientes con afectación neurológica y síntomas de disfagia / Synchronization between videofluoroscopic swallowing study and surface electromyography in patients with neurological involvement presenting symptoms of dysphagia

Introducción. La disfagia se define como la dificultad para movilizar la comida desde la boca hasta el estómago. La prueba diagnóstica para esta condición es la videofluoroscopia, la cual no es totalmente inocua pues utiliza radiación ionizante. La electromiografía de superficie registra la actividad eléctrica de los músculos de manera no invasiva, por lo que puede considerarse como una alternativa para evaluar la deglución y estudiar la disfagia. Objetivo. Evaluar la relación entre los tiempos relativos de activación de los músculos implicados en la fase oral y faríngea de la deglución, con los movimientos registrados durante la videofluoroscopia. Materiales y métodos. Se analizaron las señales de la electromiografía de superficie de 10 pacientes neurológicos con síntomas de disfagia, captadas en forma simultánea con la videofluoroscopia. Se suministraron 5 ml de yogur y 10 ml de agua, y 3 g de galleta. Se estudiaron bilateralmente los grupos musculares maseteros, suprahioideos e infrahioideos. Se analizó el paso del bolo por la línea mandibular, las valleculas y el músculo cricofaríngeo, correlacionándolo con el tiempo inicial y el final de la activación de cada uno de los grupos musculares. Resultados. El tiempo promedio de la fase faríngea fue de 0,89 ± 0,12 s. En la mayoría de los casos, hubo activación muscular antes del paso por la línea mandibular y las valleculas. La terminación de la actividad muscular parece corresponder al momento en que se completa el paso del bolo alimenticio por el músculo cricofaríngeo. Conclusión. Se determinaron los tiempos de actividad muscular, la duración de la fase faríngea y la secuencia de la activación de los grupos musculares involucrados en la deglución, mediante electromiografía de superficie, validada con la videofluoroscopia.

Introduction: Dysphagia is defined as the difficulty in transporting food and liquids from the mouth to the stomach. The gold standard to diagnose this condition is the videofluoroscopic swallowing study. However, it exposes patients to ionizing radiation. Surface electromyography is a non-radioactive alternative for dysphagia evaluation that records muscle electrical activity during swallowing. Objective: To evaluate the relationship between the relative activation times of the muscles involved in the oral and pharyngeal phases of swallowing and the kinematic events detected in the videofluoroscopy. Materials and methods: Electromiographic signals from ten patients with neurological involvement who presented symptoms of dysphagia were analyzed simultaneously with videofluoroscopy. Patients were given 5 ml of yogurt, 10 ml of water, and 3 g of crackers. Masseter, suprahyoid, and infrahyoid muscle groups were studied bilaterally. The bolus transit through the mandibular line, vallecula, and the cricopharyngeus muscle was analyzed in relation to the onset and offset times of each muscle group activation. Results: The average time of the pharyngeal phase was 0.89 ± 0.12 s. Muscle activation was mostly observed prior to the bolus transit through the mandibular line and vallecula. The end of the muscle activity suggested that the passage of the bolus through the cricopharyngeus muscle was almost complete. Conclusion: The muscle activity times, duration of the pharyngeal phase, and sequence of the muscle groups involved in swallowing were determined using sEMG validated with the videofluoroscopic swallowing study.

Cost Disclosure of Surgeon "Scorecards": Effects on Operating Room Costs for Total Hip and Knee Arthroplasty.

Background: Rising health care costs, coupled with an emphasis on cost containment, continue to gain importance. Surgeon cost scorecards developed to track case-based expenditures can help surgeons compare themselves with their peers and identify areas of potential quality improvement. Purpose: We sought to investigate what effect surgeon scorecards had on operating room (OR) costs in orthopedic surgery. Methods: Our hospital distributed OR cost scorecards to 4 adult reconstruction fellowship-trained orthopedic surgeons beginning in 2012. The average direct per-case supply cost of procedures was calculated quarterly and collected over a 5-year period, and each surgeon's data were compared with that of their peers. All 4 surgeons were made aware of the costs of other surgeons at the 2-year mark. The initial 2 years of data was compared with that of the final 2 years. Results: The average direct per-case supply cost ranged from $4955 to $5271 for total knee arthroplasty (TKA) and $5469 to $5898 for total hip arthroplasty (THA) during the initial 2-year period. After implementing disclosures, the costs for TKA and THA, respectively, ranged from $4266 to $4515 (14% annual cost savings) and from $5073 to $5727 (5% annual cost savings); 3 of the 4 surgeons said that cost transparency altered their practice. Conclusion: Our comparison suggests that orthopedic surgeons' participation in a program of operative cost disclosure may be useful to them; we found a possible association with reduced per-case costs for TKA and THA at our institution over a 5-year period. More rigorous study that incorporates the effects of the scorecards on patient outcomes is warranted.

Elective surgery after Covid-19: A narrative review of the literature / Cirugía electiva posterior a enfermedad por COVID-19: revisión narrativa de la literatura

Abstract By November 2021, at the time of preparing this article, the disease caused by the new coronavirus (Coronavirus Disease 2019 - COVID-19), declared as a pandemic by the World Health Organization (WHO) on March 11, 2020, had affected more than 128 million people and claimed upwards of 5 million lives. Many of the patients who suffered from this disease will need elective procedures, and this will require knowledge on how to perform the surgery, what tests to order and the extent of preoperative optimization. The objective of this work was to conduct a narrative review of the current evidence regarding time to the performance of an elective procedure in a patient who suffered from COVID-19, the preoperative tests that need to be ordered, and the degree of clinical optimization required according to the complexity of the surgery and individual patient clinical condition. A search was conducted in the Pubmed/Medline, Science Direct, OVID and SciELO databases, as well as in the World Health Organization (WHO) and the Centers for Disease Control and Prevention (CDC) web-based platforms. Although the evidence is still limited, different scientific societies have issued relevant guidelines pertaining to the timing of an elective procedure after COVID-19 infection. For patients who were asymptomatic, the time is 4 weeks after the initial diagnosis of SARS-CoV-2, whereas for symptomatic patients with a mild to moderate course, the time is at least 7 weeks, and 12 weeks if ICU admission was required. There are no guidelines pertaining to preoperative tests or the degree of clinical optimization, although institutional protocols have been developed based on expert consensus on the topic.

Resumen La enfermedad por el nuevo coronavirus COVID-19 (Coronavirus Disease 2019) declarada pandemia por la Organización Mundial de la Salud (OMS) el 11 de marzo de 2020, ha registrado más de 128 millones de casos a escala mundial, con más de cinco millones de muertes a noviembre de 2021, fecha de elaboración de este artículo. Muchos de los pacientes que tuvieron esta enfermedad se someterán a procedimientos electivos, y es necesario saber realizar la cirugía, los exámenes por solicitar y el grado de optimización preoperatoria. El objetivo de este trabajo es elaborar una revisión narrativa de la evidencia actual respecto al tiempo de realización de un procedimiento electivo en un paciente que tuvo COVID-19, los exámenes preoperatorios que se deben solicitar y el grado de optimización clínica según la complejidad de la cirugía y el estado clínico del paciente. Para ello, se realizó una búsqueda en bases de datos (Pubmed/Medline, Science Direct, OVID, SciELO), así como en plataformas web de la Organización Mundial de la Salud (OMS) y los Centers for Diseases Control and Prevention (CDC). Aunque la evidencia aún es limitada, diferentes sociedades científicas han dado pautas relevantes respecto al tiempo de realización de un procedimiento electivo despues de sufrir COVID-19. Para el caso de pacientes que fueron asintomáticos es de 4 semanas después del diagnóstico de infección por SARS-CoV-2, mientras que para pacientes sintomáticos con un curso de la enfermedad leve a moderado es de mínimo 7 semanas, y de 12 semanas si requirió ingreso a cuidados intensivos. No hay guías que orienten en cuanto a la solicitud de exámenes preoperatorios y el grado de optimización clínica, pero sí protocolos institucionales basados en consenso de expertos que abordan esta temática.

Predictors of Successful Early Discharge for Total Hip and Knee Arthroplasty in Octogenarians.

Background: Decreased length of stay after total joint arthroplasty (TJA) is becoming a more common way to contain healthcare costs and increase patient satisfaction. There is little evidence to support "early" discharge in elderly patients. Purpose: We sought to identify preoperative factors that correlated with early discharge (by postoperative day [POD] 1) in comparison to late discharge (after POD2) in octogenarians after TJA. Methods: In a retrospective cohort study from a single institution, we identified 482 patients ages 80 to 89 who underwent primary TJA from January 2014 to December 2017; 319 had total knee arthroplasty (TKA) and 163 had total hip arthroplasty (THA). Data collected included preoperative knee range of motion (ROM), demographics, and comorbidities; 90-day readmission and mortality rates were also evaluated. P values for continuous data were calculated using student's t test and for categorical data using χ2 testing. Results: Of octogenarian patients, 30.9% were discharged by POD1. Early discharge was associated with being male, married, and nonsmoking, as well as having an American Society of Anesthesiologists (ASA) score of 2, independent preoperative ambulation, and a postoperative caregiver. Type of procedure (TKA vs THA), body mass index, laterality, preoperative range of motion (ROM) for TKA, and single vs multilevel home did not affect the probability of early discharge. Discharge on POD1 was not associated with increased 90-day readmission rates. There were no deaths. Conclusion: Early discharge for octogenarians can be successfully implemented in a select subset of patients without increasing 90-day readmission or death rates. There are multiple factors that predict successful early discharge.

Directed Functional Coordination Analysis of Swallowing Muscles in Healthy and Dysphagic Subjects by Surface Electromyography.

Swallowing is a complex sequence of highly regulated and coordinated skeletal and smooth muscle activity. Previous studies have attempted to determine the temporal relationship between the muscles to establish the activation sequence pattern, assessing functional muscle coordination with cross-correlation or coherence, which is seriously impaired by volume conduction. In the present work, we used conditional Granger causality from surface electromyography signals to analyse the directed functional coordination between different swallowing muscles in both healthy and dysphagic subjects ingesting saliva, water, and yoghurt boluses. In healthy individuals, both bilateral and ipsilateral muscles showed higher coupling strength than contralateral muscles. We also found a dominant downward direction in ipsilateral supra and infrahyoid muscles. In dysphagic subjects, we found a significantly higher right-to-left infrahyoid, right ipsilateral infra-to-suprahyoid, and left ipsilateral supra-to-infrahyoid interactions, in addition to significant differences in the left ipsilateral muscles between bolus types. Our results suggest that the functional coordination analysis of swallowing muscles contains relevant information on the swallowing process and possible dysfunctions associated with dysphagia, indicating that it could potentially be used to assess the progress of the disease or the effectiveness of rehabilitation therapies.

Caracterización de un corpus extraído de historias clínicas electrónicas de maternas a través de técnicas de procesamiento de lenguaje natural / Characterization of a corpus extracted from maternal electronic health records through natural language processing techniques

Este artículo tuvo como propósito caracterizar el texto libre disponible en una historia clínica electrónica de una institución orientada a la atención de pacientes en embarazo. La historia clínica electrónica, más que ser un repositorio de datos, se ha convertido en un sistema de soporte a la toma de decisiones clínicas. Sin embargo, debido al alto volumen de información y a que parte de la información clave de las historias clínicas electrónicas está en forma de texto libre, utilizar todo el potencial que ofrece la información de la historia clínica electrónica para mejorar la toma de decisiones clínicas requiere el apoyo de métodos de minería de texto y procesamiento de lenguaje natural. Particularmente, en el área de Ginecología y Obstetricia, la implementación de métodos del procesamiento de lenguaje natural podría ayudar a agilizar la identificación de factores asociados al riesgo materno. A pesar de esto, en la literatura no se registran trabajos que integren técnicas de procesamiento de lenguaje natural en las historias clínicas electrónicas asociadas al seguimiento materno en idioma español. En este trabajo se obtuvieron 659 789 tokens mediante los métodos de minería de texto, un diccionario con palabras únicas dado por 7 334 tokens y se estudiaron los n-grams más frecuentes. Se generó una caracterización con una arquitectura de red neuronal CBOW (continuos bag of words) para la incrustación de palabras. Utilizando algoritmos de clustering se obtuvo evidencia que indica que palabras cercanas en el espacio de incrustación de 300 dimensiones pueden llegar a representar asociaciones referentes a tipos de pacientes, o agrupar palabras similares, incluyendo palabras escritas con errores ortográficos. El corpus generado y los resultados encontrados sientan las bases para trabajos futuros en la detección de entidades (síntomas, signos, diagnósticos, tratamientos), la corrección de errores ortográficos y las relaciones semánticas entre palabras para generar resúmenes de historias clínicas o asistir el seguimiento de las maternas mediante la revisión automatizada de la historia clínica electrónica(AU)

The purpose of this article was to characterize the free text available in an electronic health record of an institution, directed at the care of patients in pregnancy. More than being a data repository, the electronic health record (HCE) has become a clinical decision support system (CDSS). However, due to the high volume of information, as some of the key information in EHR is in free text form, using the full potential that EHR information offers to improve clinical decision-making requires the support of methods of text mining and natural language processing (PLN). Particularly in the area of gynecology and obstetrics, the implementation of PLN methods could help speed up the identification of factors associated with maternal risk. Despite this, in the literature there are no papers that integrate PLN techniques in EHR associated with maternal follow-up in Spanish. Taking into account this knowledge gap, in this work a corpus was generated and characterized from the EHRs of a gynecology and obstetrics service characterized by treating high-risk maternal patients. PLN and text mining methods were implemented on the data, obtaining 659 789 tokens and a dictionary with unique words given by 7 334 tokens. The characterization of the data was developed from the identification of the most frequent words and n-grams and a vector representation of embedding words in a 300-dimensional space was performed using a CBOW (Continuous Bag of Words) neural network architecture. The embedding of words allowed to verify by means of Clustering algorithms, that the words associated to the same group can come to represent associations referring to types of patients, or group similar words, including words written with spelling errors. The corpus generated and the results found lay the foundations for future work in the detection of entities (symptoms, signs, diagnoses, treatments), correction of spelling errors and semantic relationships between words to generate summaries of medical records or assist the follow-up of mothers through the automated review of the electronic health record(AU)

A keyphrase-based approach for interpretable ICD-10 code classification of Spanish medical reports.

BACKGROUND AND OBJECTIVES: The 10th version of International Classification of Diseases (ICD-10) codification system has been widely adopted by the health systems of many countries, including Spain. However, manual code assignment of Electronic Health Records (EHR) is a complex and time-consuming task that requires a great amount of specialised human resources. Therefore, several machine learning approaches are being proposed to assist in the assignment task. In this work we present an alternative system for automatically recommending ICD-10 codes to be assigned to EHRs. METHODS: Our proposal is based on characterising ICD-10 codes by a set of keyphrases that represent them. These keyphrases do not only include those that have literally appeared in some EHR with the considered ICD-10 codes assigned, but also others that have been obtained by a statistical process able to capture expressions that have led the annotators to assign the code. RESULTS: The result is an information model that allows to efficiently recommend codes to a new EHR based on their textual content. We explore an approach that proves to be competitive with other state-of-the-art approaches and can be combined with them to optimise results. CONCLUSIONS: In addition to its effectiveness, the recommendations of this method are easily interpretable since the phrases in an EHR leading to recommend an ICD-10 code are known. Moreover, the keyphrases associated with each ICD-10 code can be a valuable additional source of information for other approaches, such as machine learning techniques.

Stochastic Multilayer Optimization for an Acrylic Acid Reactor.

In this paper, a multilayer stochastic optimization approach is implemented to solve a dynamic optimization problem under uncertainties for an acrylic acid reactor. The proposed methodology handles different sources of uncertainties (internal, external, process), being a novel approach to obtain more realistic solutions in the context of process optimization. A comparison against deterministic dynamic optimization, single-layer stochastic optimization, and typical PI control loops is carried out. The results show the efficacy of the multilayer stochastic optimization approach for handling different sources of uncertainties, improving the economic profitability of the process while fulfilling the safety constraints in all of the scenarios analyzed.

Machine learning based analysis of speech dimensions in functional oropharyngeal dysphagia.

BACKGROUND AND OBJECTIVE: The normal swallowing process requires a complex coordination of anatomical structures driven by sensory and cranial nerves. Alterations in such coordination cause swallowing malfunctions, namely dysphagia. The dysphagia screening methods are quite subjective and experience dependent. Bearing in mind that the swallowing process and speech production share some anatomical structures and mechanisms of neurological control, this work aims to evaluate the suitability of automatic speech processing and machine learning techniques for screening of functional dysphagia. METHODS: Speech recordings were collected from 46 patients with functional oropharyngeal dysphagia produced by neurological causes, and 46 healthy controls. The dimensions of speech including phonation, articulation, and prosody were considered through different speech tasks. Specific features per dimension were extracted and analyzed using statistical tests. Machine learning models were applied per dimension via nested cross-validation. Hyperparameters were selected using the AUC - ROC as optimization criterion. RESULTS: The Random Forest in the articulation related speech tasks retrieved the highest performance measures (AUC=0.86±0.10, sensitivity=0.91±0.12) for individual analysis of dimensions. In addition, the combination of speech dimensions with a voting ensemble improved the results, which suggests a contribution of information from different feature sets extracted from speech signals in dysphagia conditions. CONCLUSIONS: The proposed approach based on speech related models is suitable for the automatic discrimination between dysphagic and healthy individuals. These findings seem to have potential use in the screening of functional oropharyngeal dysphagia in a non-invasive and inexpensive way.

Condiciones modificadoras del riesgo de enfermedad periodontal: una revisión narrativa sobre la evidencia en américa latina / Modifying conditions for the risk of periodontal disease: a narrative review of the evidence in latin america / Condições de doença periodontal modificadoras de risco: uma revisão narrativa sobre as evidências na américa latina

Resumen La diferencia entre la prevalencia de la enfermedad periodontal en América Latina y las reportadas en otras regiones del mundo, podría estar explicada en parte por las características culturales, políticas y económicas propias de cada territorio. Además, la exposición e interacción de factores e indicadores de riesgo pueden variar en cada región. Hasta el momento no se ha reportado alguna revisión de literatura ni revisión sistemática sobre los factores e indicadores de riesgo presentes y estudiados en Latinoamérica. El objetivo de esta revisión narrativa es reportar la evidencia disponible sobre las condiciones modificadoras del riesgo (indicadores y factores de riesgo) que se han estudiado en la población latinoamericana, y proponer recomendaciones para las futuras investigaciones que permitan realizar revisiones sistemáticas en esta región. A partir de los hallazgos de esta revisión, los autores consideran que es necesario aumentar las publicaciones científicas, y especialmente la investigación analítica sobre factores de riesgo y sus interacciones con las particularidades propias de cada país latinoamericano, siguiendo metodologías estándar basadas en la nueva clasificación de la enfermedad periodontal para que en un futuro sea posible recopilar esta información en revisiones sistemáticas sobre factores de riesgo.

Abstract The difference between the prevalence of periodontal disease in Latin America and those reported in other regions of the world, could be explained in part by the cultural, political and economic characteristics of each territory. Furthermore, the exposure and interaction of risk factors and indicators may be different in each region. So far, no literature review or systematic review has been reported on the risk factors and indicators present and studied in Latin America. The aim of this narrative review is to report the available evidence on the risk modifying conditions (indicators and risk factors) that have been studied in the Latin American population, and to give recommendations for future research in the region that will allow for systematic reviews in the context of our region. Based on the findings of this review, the authors consider that it is necessary to increase scientific publications, especially analytical research on risk factors and their interactions with the specific characteristics of each Latin American country, following standard methodologies based on the new classification of the disease. periodontal so that in the future it is possible to compile this information in systematic reviews on risk factors.

Resumo A diferença entre a prevalência da doença periodontal na América Latina e as relatadas em outras regiões do mundo pode ser parcialmente explicada pelas características culturais, políticas e econômicas de cada território. Além disso, a exposição e interação dos fatores e indicadores de risco podem variar em cada região. Até o momento, nenhuma revisão de literatura ou revisão sistemática foi relatada sobre os fatores e indicadores de risco presentes e estudados na América Latina. O objetivo desta revisão narrativa é relatar as evidências disponíveis sobre as condições modificadoras de risco (indicadores e fatores de risco) que têm sido estudadas na população latino-americana e propor recomendações para pesquisas futuras que permitam revisões sistemáticas nesta região. Com base nos resultados desta revisão, os autores consideram que é necessário aumentar as publicações científicas, e principalmente as pesquisas analíticas sobre os fatores de risco e suas interações com as particularidades de cada país latino-americano, seguindo metodologias padronizadas baseadas na nova classificação da doença periodontal para que futuramente seja possível coletar essas informações em revisões sistemáticas sobre fatores de risco.

Tdnn-Based Engine In-Cylinder Pressure Estimation from Shaft Velocity Spectral Representation.

Pressure is one of the essential variables to give information about engine condition and monitoring. Direct recording of this signal is complex and invasive, while angular velocity can be measured. Nonetheless, the challenge is to predict the cylinder pressure using the shaft kinematics accurately. In this paper, a time-delay neural network (TDNN), interpreted as a finite pulse response (FIR) filter, is proposed to estimate the in-cylinder pressure of a single-cylinder internal combustion engine (ICE) from fluctuations in shaft angular velocity. The experiments are conducted over data obtained from an ICE operating in 12 different states by changing the angular velocity and load. The TDNN's delay is adjusted to get the highest possible correlation-based score. Our methodology can predict pressure with an R2 >0.9, avoiding complicated pre-processing steps.

Possible association of periodontal disease with oral cancer and oral potentially malignant disorders: a systematic review.

Background: Periodontitis has been associated with several systemic diseases and medical conditions, including oral cancer (OC). However, most studies reporting an association between OC and periodontal disease have used different clinical and radiographic criteria to define periodontal disease. This review aimed to evaluate the currently available evidence to determine an association between periodontal disease (extension and severity), OC, and oral potentially malignant disorders (OPMDs).Material and methods: A systematic search of studies published up to August 2018 was performed following the PRISMA guidelines in the electronic databases MEDLINE (PubMed) and COCHRANE (OVID). A methodological evaluation was made using the Strengthening the Reporting of Observational studies in Epidemiology (STROBE) checklist.Results: Eight studies (case-control, cross-sectional and cohort) were included. An increased clinical attachment loss, plaque index, bleeding on probing, and radiographic bone loss was found in patients with OC and OPMDs. Differences in the methodological characteristics, case definition used for periodontal diseases, and OC location did not allow estimating the odds ratio required to conduct a meta-analysis.Conclusion: Some studies suggest a positive relationship between periodontal disease, OC, and OPMDs; however, the currently available evidence is insufficient to draw solid conclusions.

Strategies for the prevention of periodontal disease and its impact on general health in Latin America. Section III: Prevention.

Dental plaque removal and the understanding of risk factors, risk indicators and social determinants are important components in the prevention of periodontal disease. Periodontal diseases and dental caries are largely preventable conditions, but require a "common risk factor approach" with non-communicable diseases with the purpose of improving their prevention and control, and positive impact on health. The aim of this consensus was to identify the evidence and gaps in periodontal prevention in Latin American, and to propose individual and collective recommendations for the population, health professionals, dental practice and government. The prevention of periodontal diseases in Latin America has mainly been focused on oral hygiene instruction, use of toothbrushes and interproximal devices, but in some patients, it is necessary to use adjuncts to these measures, such as antimicrobial and/or probiotic products that are backed by broad scientific evidence. Some evidence has shown that there are inadequate knowledge, attitudes and practices among patients, dentist and other health professionals. The prevention of periodontal diseases and caries should be adopted as a healthy lifestyle routine, because of their local and systemic effects. Recently, new empowerment strategies have been proposed in order to generate behavioral changes. Periodontal diseases can often be prevented, or controlled by joined efforts between government health systems, scientific associations, universities, health professionals, private companies and communities. In conclusion, the relations between periodontal diseases, caries, healthy lifestyles and NCD's offer an ideal opportunity to change Latin American prevention strategies at both the individual level and population levels.