Application of machine learning methodology to assess the performance of DIABETIMSS program for patients with type 2 diabetes in family medicine clinics in Mexico.

BACKGROUND: The study aimed to assess the performance of a multidisciplinary-team diabetes care program called DIABETIMSS on glycemic control of type 2 diabetes (T2D) patients, by using available observational patient data and machine-learning-based targeted learning methods. METHODS: We analyzed electronic health records and laboratory databases from the year 2012 to 2016 of T2D patients from six family medicine clinics (FMCs) delivering the DIABETIMSS program, and five FMCs providing routine care. All FMCs belong to the Mexican Institute of Social Security and are in Mexico City and the State of Mexico. The primary outcome was glycemic control. The study covariates included: patient sex, age, anthropometric data, history of glycemic control, diabetic complications and comorbidity. We measured the effects of DIABETIMSS program through 1) simple unadjusted mean differences; 2) adjusted via standard logistic regression and 3) adjusted via targeted machine learning. We treated the data as a serial cross-sectional study, conducted a standard principal components analysis to explore the distribution of covariates among clinics, and performed regression tree on data transformed to use the prediction model to identify patient sub-groups in whom the program was most successful. To explore the robustness of the machine learning approaches, we conducted a set of simulations and the sensitivity analysis with process-of-care indicators as possible confounders. RESULTS: The study included 78,894 T2D patients, from which 37,767patients received care through DIABETIMSS. The impact of DIABETIMSS ranged, among clinics, from 2 to 8% improvement in glycemic control, with an overall (pooled) estimate of 5% improvement. T2D patients with fewer complications have more significant benefit from DIABETIMSS than those with more complications. At the FMC's delivering the conventional model the predicted impacts were like what was observed empirically in the DIABETIMSS clinics. The sensitivity analysis did not change the overall estimate average across clinics. CONCLUSIONS: DIABETIMSS program had a small, but significant increase in glycemic control. The use of machine learning methods yields both population-level effects and pinpoints the sub-groups of patients the program benefits the most. These methods exploit the potential of routine observational patient data within complex healthcare systems to inform decision-makers.

Understanding public perception of the need for major change in Latin American healthcare systems.

The opinions and experiences of the public regarding health services are valuable insights into identifying opportunities to improve healthcare systems. We analyzed the 2012-2013 Public Opinion Health Policy Survey carried out in Brazil (n = 1486), Colombia (n = 1485), El Salvador (n = 1460), Jamaica (n = 1480), México (n = 1492) and Panama (n = 1475). In these countries between 82 and 96% of participants perceived that their health systems needed fundamental changes. The most frequent barrier to access to healthcare was lack of the primary medical home, difficulties in obtaining medical care during the weekends and financial barriers. Type of health insurance and challenges in obtaining medical care during the weekends were associated with an increased opinion for the need for fundamental changes in healthcare systems, whereas having a primary medical home showed a protective effect. Focusing on tackling organizational and financial barriers and ensuring access to a primary medical home should be placed on the agenda of Latin American countries.

La carga económica de la depresión en Colombia: costos directos del manejo intrahospitalario / The Economic Burden of Depression in Colombia: Direct Costs of Intrahospital Management

Introducción: En Colombia se desconoce la magnitud del impacto económico de la depresión. Objetivo: Determinar los costos directos del tratamiento hospitalario de la depresión en pacientes con trastornos depresivos de ambos géneros entre los 18 y 65 años de edad. Método: Estudio de costos directos de la enfermedad, a partir de datos consignados en 279 historias clínicas de pacientes hospitalizados por depresión en ocho instituciones de seis ciudades colombianas entre 2007-2008. Se obtuvieron medias o medianas para datos continuos y proporciones para datos categóricos, con sus respectivas medidas de dispersión. Resultados: El costo total promedio de la hospitalización por depresión se encontró en 1.680.000 pesos. La estancia representa el 74,1% del costo de la hospitalización. El costo promedio por día es 150.000 pesos. Bajo condiciones de acceso a los servicios de salud mental restringidas, el costo total directo de hospitalización por depresión severa o moderada está alrededor de 54.000 millones, en la seis ciudades, y en el país, 162.000 millones de pesos. Bajo condiciones de acceso observadas en el ámbito internacional, el costo total es de 134.000 millones de pesos en las seis ciudades y 399.000 millones en el país. Conclusiones: El presente estudio se constituye en un punto de partida hacia la cuantificación de la carga económica de la depresión en Colombia, concretamente en términos de los recursos monetarios destinados al manejo de la enfermedad en hospitales. Los hallazgos deben ser complementados con información sobre otros costos directos e indirectos de la depresión en la población adulta de Colombia.

Introduction: The magnitude of the economic burden of depression in Colombia is unknown. Objective: To determine the direct costs of hospitalary management of male and female patients with depressive disorders aged 18 to 65. Methods: Study of the costs of the illness, using data from 279 clinical records of patients hospitalized with a diagnosis of depression, in 2007-2008, in eight institutions of six cities in Colombia. Means or medians were estimated for continuous data and proportions for categorical data, along with dispersion measures. Results: The total average cost of hospitalization was 1,68 million Colombian pesos. Hospital stay represents 74.1% of the total cost of hospitalization. The average daily cost was 150,000 pesos. Under restricted access conditions the total direct cost of hospitalization for moderate to severe depression was estimated to be around 54,000 million pesos in the six cities included in the study, and 162,000 million pesos at the national level. Under the access conditions observed at the international level, the cost is 134,000 million pesos in the six cities and 399.000 million at the national level. Conclusions: This study is a starting point towards the quantification of the economic burden of depression in Colombia. Specifically, it provides information about the monetary resources used for depression management at the hospital level. These findings need to be complemented with information about other direct and indirect costs related to depression in the adult population of Colombia.

[The prevalence of and factors associated with depression in Colombia]. / Prevalencia de depresión y factores asociados con ella en la población colombiana.

OBJECTIVES: To analyze the prevalence of depression and the factors associated with it in Colombia in 2000 and 2001. METHODS: For this descriptive cross-sectional study a survey was conducted between November 2000 and January 2001 with 1,116 men and women 18 years of age or older who were living in private homes that were selected through a multistage national representative sampling, stratified according to the degree of urbanization of the area included in the sampling. Depression was classified as brief recurrent depression, subclinical depression, or mild, moderate, or serious clinical depressive episodes in the 30 days and in the 12 months prior to the interview. Simple and stratified frequencies of over 500 variables, along with their 95% confidence intervals (95% CIs), were calculated by age and gender. The association that the selected variables had with depressive episodes was evaluated through a multivariate logistic regression model. RESULTS: Of the persons studied, 10.0% of them (95% CI: 9.2% to 10.7%) had had a depressive episode in the 12 months prior to the survey, and 8.5% (95% CI: 7.8% to 9.2%) had suffered a depressive episode in the preceding month. There was a higher proportion of women with depression in both of the periods. More than 50% of the episodes were moderate, in both men and women. There were higher prevalences of depression in persons older than 45 years. The factors associated with depression in the preceding month were: female gender; considering one's health to be moderate or bad; suffering from pain or discomfort; having difficulties in interpersonal relations; consuming marijuana, addictive substances, stimulants, or tranquilizers; being dependent on alcohol; and being unemployed and unable to work. CONCLUSIONS: Depression is a frequent disorder in Colombia. Measures directed at reducing the risk of depression should be implemented, especially among women and in persons over 45 years old.

La certificación como indicador de descentralización en salud. Una mirada a la luz del cumplimiento de requisitos en municipios colombianos / The certification as indicator of decentralization in health. A look in the light of the fulfillment of requirements in Colombian municipalities

En este artículo se describen los resultados de una encuesta llevada a cabo durante los años 2003-2004 para determinar el cumplimiento de los criterios para la certificación de descentralización en salud otorgada por el Ministerio de la Protección Social en una muestra representativa de municipios colombianos.

En el sistema general de seguridad social colombiano: caracterización de los cobros por tutelas y medicamentos no incluidos en los planes obligatorios de salud / In the Colombian general system of social safety: Characterization of the collections for guardianships and medicines not included in the obligatory plans of health

Este estudio caracteriza los recobros por parte de las empresas aseguradoras al fondo de solidaridad y garantía (Fosyga) del Ministerio de la Protección Social, de los gastos incurridos en medicamentos no cubiertos por los planes obligatorios de salud o en intervenciones ordenadas por fallos de tutela.

Prevalencia de depresión y factores asociados con ella en la población colombiana / The prevalence of and factors associated with depression in Colombia

OBJETIVOS: Analizar la prevalencia del síndrome depresivo y los factores asociados con la depresión en Colombia entre los años 2000 y 2001. MÉTODOS: Para este estudio descriptivo de corte transversal se aplicó una encuesta entre noviembre de 2000 y enero de 2001 a 1 116 adultos de 18 años de edad o más de uno u otro sexo que residían en viviendas particulares seleccionadas mediante un muestreo representativo nacional polietápico, estratificado según el grado de urbanización del área incluida en el muestreo. La depresión se clasificó en breve, subclínica o clínica (leve, moderada o grave) en los 30 días y los 12 meses previos a la entrevista. Se calcularon las frecuencias simples y estratificadas por la edad y el sexo, y los intervalos de confianza de 95 por ciento (IC95 por ciento) de más de 500 variables. La asociación de las variables seleccionadas con episodios depresivos se evaluó mediante un modelo de regresión logística con múltiples variables. RESULTADOS: De las personas estudiadas, 10,0 por ciento (IC95 por ciento: 9,2 a 10,7) presentaron algún episodio depresivo en los 12 meses previos a la encuesta y 8,5 por ciento (IC95 por ciento: 7,8 a 9,2) sufrieron alguno durante el último mes. Hubo una mayor proporción de mujeres con depresión en ambos períodos. Más de 50 por ciento de los episodios fueron moderados, tanto en hombres como en mujeres, y las mayores prevalencias se encontraron en las personas mayores de 45 años. Los factores asociados con la depresión en el último mes fueron ser mujer, considerar el estado de salud propio como regular o malo, sufrir de dolores o molestias, tener dificultades en las relaciones interpersonales, consumir marihuana o sustancias adictivas, medicamentos estimulantes o calmantes, tener dependencia del alcohol, o estar desempleado con discapacidad. CONCLUSION: La depresión es una afección frecuente en Colombia. Se deben poner en marcha medidas dirigidas a reducir el riesgo de depresión, especialmente en mujeres y en personas mayores de 45 años de edad.