Artificial Intelligence Applied to Forced Spirometry in Primary Care.

Introduction: This study aims to create an artificial intelligence (AI) based machine learning (ML) model capable of predicting a spirometric obstructive pattern using variables with the highest predictive power derived from an active case-finding program for COPD in primary care. Material and methods: A total of 1190 smokers, aged 30-80 years old with no prior history of respiratory disease, underwent spirometry with bronchodilation. The sample was analyzed using AI tools. Based on an exploratory data analysis (EDA), independent variables (according to mutual information analysis) were trained using a gradient boosting algorithm (GBT) and validated through cross-validation. Results: With an area under the curve close to unity, the model predicted a spirometric obstructive pattern using variables with the highest predictive power: FEV1_theoretical_pre values. Sensitivity: 93%. Positive predictive value: 94%. Specificity: 97%. Negative predictive value: 96%. Accuracy: 95%. Precision: 94%. Conclusion: An ML model can predict the presence of an obstructive pattern in spirometry in a primary care smoking population with no prior diagnosis of respiratory disease using the FEV1_theoretical_pre values with an accuracy and precision exceeding 90%. Further studies including clinical data and strategies for integrating AI into clinical workflow are needed.

Introducción: Este estudio tiene como objetivo crear un modelo de aprendizaje automático (ML) basado en inteligencia artificial (IA) capaz de predecir un patrón obstructivo espirométrico utilizando variables con el mayor poder predictivo derivado de un programa activo de búsqueda de casos de enfermedad pulmonar obstructiva crónica (EPOC) en Atención Primaria. Materiales y métodos: Un total de 1.190 fumadores, de entre 30 y 80 años, sin antecedentes de enfermedad respiratoria, fueron sometidos a espirometría con IA artificial. Sobre la base de un análisis de datos exploratorio (EDA), las variables independientes (según el análisis de información mutua) se entrenaron utilizando un algoritmo de gradiente de aumento (GBT) y se validaron mediante validación cruzada. Resultados: Con un área bajo la curva cercana a la unidad, el modelo predijo un patrón obstructivo espirométrico utilizando los valores del FEV1 prebroncodilatador. Sensibilidad: 93%. Valor predictivo positivo: 94%. Especificidad: 97%. Valor predictivo negativo: 96%. Precisión: 95%. Precisión: 94%. Conclusión: Un modelo ML puede predecir la presencia de un patrón obstructivo en la espirometría en una población fumadora de atención primaria sin diagnóstico previo de enfermedad respiratoria utilizando los valores FEV1 prebroncodilatadores con una exactitud y precisión superiores al 90%. Se necesitan más estudios que incluyan datos clínicos y estrategias para integrar la IA en el flujo de trabajo clínico.

Cascading effects of insecticides and road salt on wetland communities.

Novel stressors introduced by human activities increasingly threaten freshwater ecosystems. The annual application of more than 2.3 billion kg of pesticide active ingredient and 22 billion kg of road salt has led to the contamination of temperate waterways. While pesticides and road salt are known to cause direct and indirect effects in aquatic communities, their possible interactive effects remain widely unknown. Using outdoor mesocosms, we created wetland communities consisting of zooplankton, phytoplankton, periphyton, and leopard frog (Rana pipiens) tadpoles. We evaluated the toxic effects of six broad-spectrum insecticides from three families (neonicotinoids: thiamethoxam, imidacloprid; organophosphates: chlorpyrifos, malathion; pyrethroids: cypermethrin, permethrin), as well as the potentially interactive effects of four of these insecticides with three concentrations of road salt (NaCl; 44, 160, 1600 Cl- mg/L). Organophosphate exposure decreased zooplankton abundance, elevated phytoplankton biomass, and reduced tadpole mass whereas exposure to neonicotinoids and pyrethroids decreased zooplankton abundance but had no significant effect on phytoplankton abundance or tadpole mass. While organophosphates decreased zooplankton abundance at all salt concentrations, effects on phytoplankton abundance and tadpole mass were dependent upon salt concentration. In contrast, while pyrethroids had no effects in the absence of salt, they decreased zooplankton and phytoplankton density under increased salt concentrations. Our results highlight the importance of multiple-stressor research under natural conditions. As human activities continue to imperil freshwater systems, it is vital to move beyond single-stressor experiments that exclude potentially interactive effects of chemical contaminants.

Gentian violet and ferric ammonium citrate disrupt Pseudomonas aeruginosa biofilms.

OBJECTIVE/HYPOTHESIS: Bacterial biofilms are resistant to antibiotics and may contribute to persistent infections including chronic otitis media and cholesteatoma. Discovery of substances to disrupt biofilms is necessary to treat these chronic infections. Gentian violet (GV) and ferric ammonium citrate (FAC) were tested against Pseudomonas aeruginosa biofilms to determine if either substance can reduce biofilm volume. STUDY DESIGN: The biofilm volume and planktonic growth of PAO1 and otopathogenic P. aeruginosa (OPPA8) isolated from an infected cholesteatoma was measured in the presence of GV or FAC. METHODS: OPPA8 and PAO1 expressing a green fluorescent protein plasmid (pMRP9-1) was inoculated into a glass flow chamber. Biofilms were grown under low flow conditions for 48 hours and subsequently exposed to either GV or FAC for an additional 24 hours. Biofilm formation was visualized by confocal laser microscopy and biofilm volume was assayed by measuring fluorescence. Planktonic cultures were grown under standard conditions with GV or FAC. Statistical analysis was performed by Student t test and one-way ANOVA. RESULTS: GV reduced PAO1 and OPPA8 biofilm volume (P < .01). GV delayed the onset and rate of logarithmic growth in both strains. FAC reduced OPPA8 biofilm volume (P < .01), but did not effect of PAO1 biofilms. FAC had no effect on planktonic growth. CONCLUSIONS: The efficacy of GV in disrupting biofilms in vitro suggests that it may disrupt biofilms in vivo. The effect of FAC on Pseudomonas aeruginosa biofilms is strain dependent. Strain differences in response to increasing iron concentration and biofilm morphology stress the importance of studying clinically isolated strains in testing antibiofilm agents.