Learning a Battery of COVID-19 Mortality Prediction Models by Multi-objective Optimization

The COVID-19 pandemic is continuously evolving with drastically changing epidemiological situations which are approached with different decisions: from the reduction of fatalities to even the selection of patients with the highest probability of survival in critical clinical situations. Motivated by this, a battery of mortality prediction models with different performances has been developed to assist physicians and hospital managers. Logistic regression, one of the most popular classifiers within the clinical field, has been chosen as the basis for the generation of our models. Whilst a standard logistic regression only learns a single model focusing on improving accuracy, we propose to extend the possibilities of logistic regression by focusing on sensitivity and specificity. Hence, the log-likelihood function, used to calculate the coefficients in the logistic model, is split into two objective functions: one representing the survivors and the other for the deceased class. A multi-objective optimization process is undertaken on both functions in order to find the Pareto set, composed of models not improved by another model in both objective functions simultaneously. The individual optimization of either sensitivity (deceased patients) or specificity (survivors) criteria may be conflicting objectives because the improvement of one can imply the worsening of the other. Nonetheless, this conflict guarantees the output of a battery of diverse prediction models. Furthermore, a specific methodology for the evaluation of the Pareto models is proposed. As a result, a battery of COVID-19 mortality prediction models is obtained to assist physicians in decision-making for specific epidemiological situations. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Derivation of a Cost-Sensitive COVID-19 Mortality Risk Indicator Using a Multistart Framework

The overall global death rate for COVID-19 patients has escalated to 2.13% after more than a year of worldwide spread. Despite strong research on the infection pathogenesis, the molecular mechanisms involved in a fatal course are still poorly understood. Machine learning constitutes a perfect tool to develop algorithms for predicting a patient's hospitalization outcome at triage. This paper presents a probabilistic model, referred to as a mortality risk indicator, able to assess the risk of a fatal outcome for new patients. The derivation of the model was done over a database of 2,547 patients from the first COVID-19 wave in Spain. Model learning was tackled through a five multistart configuration that guaranteed good generalization power and low variance error estimators. The training algorithm made use of a class weighting correction to account for the mortality class imbalance and two regularization learners, logistic and lasso regressors. Outcome probabilities were adjusted to obtain cost-sensitive predictions by minimizing the type II error. Our mortality indicator returns both a binary outcome and a three-stage mortality risk level. The estimated AUC across multistarts reaches an average of 0.907. At the optimal cutoff for the binary outcome, the model attains an average sensitivity of 0.898, with a 0.745 specificity. An independent set of 121 patients later released from the same consortium attained perfect sensitivity (1), with a 0.759 specificity when predicted by our model. Best performance for the indicator is achieved when the prediction's time horizon is within two weeks since admission to hospital. In addition to a strong predictive performance, the set of selected features highlights the relevance of several underrated molecules in COVID-19 research, such as blood eosinophils, bilirubin, and urea levels. © 2021 IEEE.

Experience of breast cancer surgery during the COVID-19 pandemic

Introduction: The COVID-19 pandemic has had an important impact in all areas;health service has been one of the most affected. The pandemic has led to a reorganization of human and material resources and has caused a saturation of the health service. As specialists in breast cancer, we have adapted to this situation by reorganizing and adapting care to the professional environments and infrastructures that were available when necessary. The incidence has varied during 2020 and it has made possible to normalize the work on some occasions. We would like to describe our experience in breast cancer surgery during this COVID-19 pandemic year. Material and methods: Retrospective observational study of patients operated on breast cancer from 14th March 2020 to 14th March 2021. Result: A number of 138 breast cancer have been operated on 136 women. The average age is 62 years (36-8);there were 86 patients operated on major ambulatory surgery regimen (63.2%) and 50 patients (36.8%) were hospitalized. The average time from diagnosis to outpatient visit was 5.7 days and the average time from diagnosis to the beginning of the treatment of 45 days. Conclusions: During this COVID-19 pandemic year, we have been able to ensure the care and treatment of women with breast cancer with adequate time intervals between diagnosis and treatment. This process has also been favored by the prior establishment of major ambulatory surgery in our medical center. © 2021 SESPM

Experiencia De La Cirugía Del Cáncer De Mama Durante La Pandemia Covid-19

RESUMEN Introducción: La pandemia por la enfermedad COVID-19 ha tenido un importante impacto en todos los ámbitos, siendo uno de los más afectados la sanidad. La pandemia ha supuesto una reorganización de los recursos tanto humanos como materiales, dando lugar a una saturación del sistema sanitario. Como especialistas en el cáncer de mama hemos tenido que adaptarnos a esta situación, reorganizando y ajustando los cuidados a los medios profesionales e infraestructuras de los que disponíamos en cada momento. La incidencia variable a lo largo del año ha permitido desarrollar una actividad normalizada en algunas ocasiones. Nos proponemos describir nuestra experiencia en la cirugía del cáncer de mama durante este año de pandemia COVID-19. Material y Métodos: Estudio observacional retrospectivo de pacientes intervenidas de neoplasia de mama desde el 14 de Marzo de 2020 hasta el 14 de Marzo de 2021. Resultados: Se han intervenido 138 neoplasias de mama en 136 mujeres. La edad media de 62 años (36-88), 86 pacientes (63,2%) en régimen de cirugía mayor ambulatoria y 50 pacientes (36,8%) con ingreso. El tiempo medio desde el diagnóstico hasta la visita en consultas externas 5,7 días y el tiempo medio desde el diagnóstico hasta el inicio del tratamiento 45 días. Conclusiones: Durante este año de pandemia COVID-19 hemos podido asegurar la asistencia y tratamiento de las mujeres con cáncer de mama con adecuados intervalos entre el diagnóstico y el tratamiento. A este proceso ha contribuido la implementación de la cirugía mayor ambulatoria en el cáncer de mama. ABSTRACT Introduction: The COVID-19 pandemic has had an important impact in all areas, health service has been one of the most affected. The pandemic has led to a reorganization of human and material resources and has caused a saturation of the health service. As specialists in breast cancer, we have adapted to this situation by reorganizing and adapting care to the professional environments and infrastructures that were available when necessary. The incidence has varied during 2020 and it has made possible to normalize the work on some occasions. We would like to describe our experience in breast cancer surgery during this COVID-19 pandemic year. Material and Methods: Retrospective observational study of patients operated on breast cancer from 14th March 2020 to 14th March 2021. Results: 138 breast cancer have been operated on 136 women. The average age is 62 years (36-88), 86 patients (63,2%) are operated on major ambulatory surgery regimen and 50 patients (36,8%) are hospitalized. The average time from diagnosis to outpatient visit is 5,7 days and the average time from diagnosis to the beginning of the treatment is 45 days. Conclusions: During this COVID-19 pandemic year, we have been able to ensure the care and treatment of women with breast cancer with adequate time intervals between diagnosis and treatment. This process has also been favored by the prior establishment of major ambulatory surgery in our medical center.

SEPAR Recommendations for COVID-19 Vaccination in Patients With Respiratory Diseases

The Spanish Society of Pneumonology and Thoracic Surgery (SEPAR) has elaborated this document of recommendations for COVID-19 vaccination in patients with respiratory diseases aimed to help healthcare personnel make decisions about how to act in case of COVID-19 vaccination in these patients. The recommendations have been developed by a group of experts in this field after reviewing the materials published up to March 7, 2021, the information provided by different scientific societies, drug agencies and the strategies of the governmental bodies up to this date. We can conclude that COVID-19 vaccines are not only safe and effective, but also prior in vulnerable patients with chronic respiratory diseases. In addition, an active involvement of healthcare professionals, who manage these diseases, in the vaccination strategy is the key to achieve good adherence and high vaccination coverage.

Monitoring of COVID-19 patients by telemedicine with telemonitoring. / Telemedicina con telemonitorización en el seguimiento de pacientes con COVID-19.

AIM: To asses if telemedicine with telemonitoring is a clinically useful and secure tool in the tracking of patients with COVID-19. METHODS: A prospective observational study of patients with COVID-19 diagnosis by positive PCR considered high-risk tracked with telemedicine and telemonitoring was conducted in the sanitary area of Lugo between March 17th and April 17th, 2020. Two groups of patients were included: Outpatient Tracing from the beginning and after discharge. Every patient sent a daily clinical questionnaire with temperature and oxygen saturation 3 times a day. Proactive monitoring was done by getting in touch with every patient at least 11a day. RESULTS: 313 patients (52.4% female) with a total average age of 60.9 (DE 15.9) years were included. Additionally, 2 patients refused to join the program. Since the beginning, 224 were traced outpatient and 89 after being discharged. Among the first category, 38 (16.90%) were referred to Emergency department on 43 occasions; 18 were hospitalized (8.03%), and 2 deceased. Neither deaths nor a matter of vital emergency occurred at home. When including patients after admissions monitoring was done in 304 cases. One patient re-entered (0.32%) to the hospital, and another one left the program (0.32%). The average time of monitoring was 11.64 (SD 3.58) days, and 224 (73.68%) patients were discharged during the 30 days of study. CONCLUSIONS: Our study suggests that telemedicine with home telemonitoring, used proactively, allows for monitoring high-risk patients with COVID-19 in a clinically useful and secure way.

Tracing of COVID-19 patients by telemedicine with telemonitoring

Aim To asses if telemedicine with telemonitoring is a clinically useful and secure tool in the tracking of patients with COVID-19. Methods A prospective observational study of patients with COVID-19 diagnosis by positive PCR considered high-risk tracked with telemedicine and telemonitoring was conducted in the sanitary area of Lugo between March 17th and April 17th, 2020. Two groups of patients were included: Outpatient Tracing from the beginning and after discharge. Every patient sent a daily clinical questionnaire with temperature and oxygen saturation 3 times a day. Proactive monitoring was done by getting in touch with every patient at least 11a day. Results 313 patients (52.4% female) with a total average age of 60.9 (DE 15.9) years were included. Additionally, 2 patients refused to join the program. Since the beginning, 224 were traced outpatient and 89 after being discharged. Among the first category, 38 (16.90%) were referred to Emergency department on 43 occasions;18 were hospitalized (8.03%), and 2 deceased. Neither deaths nor a matter of vital emergency occurred at home. When including patients after admissions monitoring was done in 304 cases. One patient re-entered (0.32%) to the hospital, and another one left the program (0.32%). The average time of monitoring was 11.64 (SD 3.58) days, and 224 (73.68%) patients were discharged during the 30 days of study. Conclusions Our study suggests that telemedicine with home telemonitoring, used proactively, allows for monitoring high-risk patients with COVID-19 in a clinically useful and secure way. Resumen Objetivo Evaluar si la telemedicina con telemonitorización es una herramienta clínicamente útil y segura para el seguimiento de pacientes con COVID-19. Métodos Estudio observacional prospectivo de los pacientes con diagnóstico de COVID-19 por PCR positiva y considerados de alto riesgo que se siguieron con telemedicina y telemonitorización en el Área Sanitaria de Lugo entre el 17 de marzo y el 17 de abril del 2020. Se incluyeron 2grupos de pacientes: seguimiento ambulatorio desde el inicio y tras el alta hospitalaria. Cada paciente remitió un cuestionario clínico al día con su temperatura y saturación de oxígeno 3 veces al día. El seguimiento fue proactivo, contactando con todos los pacientes al menos una vez al día. Resultados Se incluyó a 313 pacientes (52,4% mujeres) con edad media 60,9 (DE 15,9) años. Otros 2 pacientes rehusaron entrar en el programa. Desde el inicio, se siguió ambulatoriamente a 224 pacientes y a 89 pacientes tras su alta hospitalaria. Entre los primeros, 38 (16,90%) se remitieron a Urgencias en 43 ocasiones con 18 (8,03%) ingresos y 2 fallecidos. En los domicilios no hubo fallecimientos ni urgencias vitales. Incluyendo a los pacientes tras hospitalización, el seguimiento se realizó en 304 casos. Un paciente reingresó (0,32%) y otro abandonó (0,32%). El tiempo medio de seguimiento fue 11,64 (DE 3,58) días y en los 30 días del estudio 224 (73,68%) pacientes fueron dados de alta. Conclusiones Nuestros datos sugieren que la telemedicina con telemonitorización domiciliaria, utilizada de forma proactiva, permite un seguimiento clínicamente útil y seguro en pacientes con COVID-19 de alto riesgo.