TY - JOUR T1 - Street images classification according to COVID-19 risk in Lima, Peru: a convolutional neural networks feasibility analysis JF - BMJ Open JO - BMJ Open DO - 10.1136/bmjopen-2022-063411 VL - 12 IS - 9 SP - e063411 AU - Rodrigo M Carrillo-Larco AU - Manuel Castillo-Cara AU - Jose Francisco Hernández Santa Cruz Y1 - 2022/09/01 UR - http://bmjopen.bmj.com/content/12/9/e063411.abstract N2 - Objectives During the COVID-19 pandemic, convolutional neural networks (CNNs) have been used in clinical medicine (eg, X-rays classification). Whether CNNs could inform the epidemiology of COVID-19 classifying street images according to COVID-19 risk is unknown, yet it could pinpoint high-risk places and relevant features of the built environment. In a feasibility study, we trained CNNs to classify the area surrounding bus stops (Lima, Peru) into moderate or extreme COVID-19 risk.Design CNN analysis based on images from bus stops and the surrounding area. We used transfer learning and updated the output layer of five CNNs: NASNetLarge, InceptionResNetV2, Xception, ResNet152V2 and ResNet101V2. We chose the best performing CNN, which was further tuned. We used GradCam to understand the classification process.Setting Bus stops from Lima, Peru. We used five images per bus stop.Primary and secondary outcome measures Bus stop images were classified according to COVID-19 risk into two labels: moderate or extreme.Results NASNetLarge outperformed the other CNNs except in the recall metric for the moderate label and in the precision metric for the extreme label; the ResNet152V2 performed better in these two metrics (85% vs 76% and 63% vs 60%, respectively). The NASNetLarge was further tuned. The best recall (75%) and F1 score (65%) for the extreme label were reached with data augmentation techniques. Areas close to buildings or with people were often classified as extreme risk.Conclusions This feasibility study showed that CNNs have the potential to classify street images according to levels of COVID-19 risk. In addition to applications in clinical medicine, CNNs and street images could advance the epidemiology of COVID-19 at the population level.Data may be obtained from a third party and are not publicly available. Outcome (ie, labels: moderate and extreme COVID-19 risk) data are available online: https://sistemas.atu.gob.pe/paraderosCOVID; this information was systematised at https://github.com/jmcastagnetto/lima-atu-covid19-paraderos. The images were downloaded from Google Street View through the API with a personal account; images cannot be shared with third parties. All analysis codes are available as Python Jupyter Notebooks in the online supplemental materials. JupyterLab Notebooks and the final model (weights) are available at: https://figshare.com/articles/online_resource/Street_images_classification_according_to_COVID-19_risk_in_Lima_Peru_A_convolutional_neural_networks_feasibility_analysis/17321021. ER -