Maps Application Programming Interface Research Articles

Weather Patterns, Patient, and Appointment Characteristics Associated with Cancellations and No-Shows in a Glaucoma Clinic

ABSTRACT Purpose To identify factors that are associated with no-shows and cancellations in a glaucoma clinic. Methods Retrospective observational study of patients seen at a glaucoma clinic over a two-year period (6/2017–5/2019). Demographics and clinic information were recorded from the electronic medical record. A total of 36,810 visits from 7,383 patients were studied. Weather data was collected from the National Centers for Environmental Information. Distance analysis was calculated utilizing Bing Maps application programming interface (API) on Microsoft Excel. Visits were divided into three groups based on appointment status: kept, cancelled, and no-show. Results Bivariate analysis found a statistically significant difference in various factors amongst patients based on appointment status. Patients <15 miles from clinic had a higher rate of no-show, but a lower rate of cancellations compared to those farther (p < 0.0001) Using multivariable logistic regression, the following factors were associated with the likelihood of patient cancellation: average snowfall (Odds Ratio = 1.37); presence of storm event (OR = 1.12), new visit (OR = 1.82), follow-up appointments (OR = 1.90), and travel distance > 15 miles (OR = 1.11). The following factors were associated with patient no-show: resident clinic (OR = 1.79), new visit (OR = 2.24), follow-up appointments (OR = 2.18), age (OR = 0.99), average snowfall (OR = 1.27), presence of storm event (OR = 1.41), average windspeed (OR = 0.98), and travel distance > 15 miles (OR = 0.67). Conclusion Patient age, gender, travel distance, appointment type, and weather were all significantly associated with rates of patient cancellations and no-shows. These risk factors could lead to interventions to improve appointment adherence and patient retention. Weather is an under-analyzed factor in patient follow-up rates that warrants further investigation.

CO2 emission heat map of Gulf Cooperation Council region using Python for Geographic Information Systems

Abstract As part of the efforts to ensure a place in the global competitive landscape, Oman is aligning itself with sustainable development through diversified economic measures. To address the United Nations thirteenth Sustainable Development Goal (SDG) which is climate action, the stakeholders of Oman need to understand the carbon dioxide (CO2) emissions and compare the amount of CO2 with the emissions in neighbouring Gulf Cooperation Council (GCC) countries such as United Arab Emirates (UAE), Bahrain, Qatar, Kuwait, and Kingdom of Saudi Arabia (KSA). In this research, an attempt is being made to collect the CO2 emission for all these countries and show them on a web map using python programming language. The data ranging from year 1964 to 2021 is collected from CO2 and Greenhouse Gas Emissions in Comma Separated Values (csv) format. For each country, an approximate location for Capital in terms of Latitude and Longitude is taken from google maps. Using folium library of python, these locations and CO2 emission for a particular year is plotted on google map Application Programming Interface (API). The findings reveal that Oman’s CO2 emissions from fossil fuels and industry in 2022 year is 72 million tonnes which is relatively lower when compared to those of smaller GCC countries such as Qatar (101 million tonnes) and the UAE (244 million tonnes). Nonetheless, a gradual upward trend of 12 million tonnes of CO2 emissions has been observed in Oman between the years 2019 to 2022. The python program provides an easy way to visualise the CO2 emission heatmap without the need of any proprietary software or program.

Analyzing Land Shape Typologies in South Korean Apartment Complexes Using Machine Learning and Deep Learning Techniques

In South Korea, the configuration of land parcels within apartment complexes plays a pivotal role in optimizing land use and facility placement. Given the significant impact of land shape on architectural and urban planning outcomes, its analysis is essential. However, studies on land shape have been limited due to the lack of definitive survey criteria. To address these challenges, this study utilized a map application programming interface (API) to gather raw data on apartment complex layouts in South Korea and processed these images using a Python-based image library. An initial analysis involved categorizing the data through K-means clustering. Each cluster’s average image was classified into four distinct groups for comparison with the existing literature. Shape indices were employed to analyze land configurations and assess consistency across classes. These classes were annotated on a parcel level using the Roboflow API, and YOLOv8s-cls was developed to classify the parcels effectively. The evaluation of this model involved calculating accuracy, precision, recall, and F1-score from a confusion matrix. The results show a strong correlation between the identified and established classes, with the YOLO model achieving an accuracy of 86% and demonstrating robust prediction capabilities across classes. This confirms the effective typification of land shapes in the studied apartment complexes. This study introduces a methodology for analyzing parcel shapes through machine learning and deep learning. It asserts that this approach transcends the confines of South Korean apartment complexes, extending its applicability to architectural and urban design planning on a global scale. Analyzing land shapes earmarked for construction enables the formulation of diverse design strategies for building placement and external space arrangement. This highlights the potential for innovative design approaches in architectural and urban planning worldwide.

Mobile application to tackle infection disease in Indonesia

Infectious diseases often occur, especially as diseases such as COVID-19 have claimed many lives in the years between 2019–2021. That’s why it’s called COVID-19, considering that this infectious disease outbreak started in 2019, and its consequences and effects are devastating. Like other countries’ governments, the Indonesian government always announces the latest data on this infectious disease, such as death rates and recoveries. Infectious diseases are transmitted directly through disease carriers to humans through infections such as fungi, bacteria, viruses and parasites. In this research, we offer a contagious illness monitoring application to help the public and government know the zone’s status so that people are more alert when travelling between regions. This application was created based on Web Application Programming Interface (API) data and configured on the Google Map API to determine a person’s or user’s coordinates in a particular zone. We made it using the prototype method to help users understand this application well. This research is part of the Automatic Identification System (AIS) research, where the use of mobile technology is an example of implementation options that can be made to implement this system.

Quantitative evaluation of urban green exposure and its impact on human health: A case study on the 3–30-300 green space rule

Background and aims.Urban green spaces offer various health benefits, yet the impact of comprehensive green exposure criteria on multidimensional health remains unclear. The 3–30-300 green space rule represents the green exposure indicators with specific thresholds. This study aims to quantitatively evaluate urban green exposure in cities and can support investigation of its relationship with human health. MethodsWe conducted a cross-sectional study based on 902 investigated individuals in 261 residential locations aged 11–95 years from Xiamen City, China. 3–30-300 green exposure was calculated using field surveys, GIS, and Baidu Maps Application Programming Interface (API). Physical health data was based on Occupational Stress Indicator (OSI)-2. Mental health was from the 12-item General Health Questionnaire (GHQ-12). Social health was from a self-constructed evaluation questionnaire. Statistical analyses were conducted using Geographically Weighted Regression and Geographically Weighted Logistic Regression for global and local effects on green exposure and multidimensional health. ResultAmong the investigated individuals, only 3.55 % (32/902) fully meet the 3–30-300 rule in Xiamen. Global results show that individuals achieved at least 30 % vegetation coverage (Yes) is associated with better physical (β: 0.76, p < 0.01) and social (β: 0.5, p < 0.01) health. GWLR global results indicate that individuals can “see at least 3 trees from home” meeting one (OR = 0.46, 95%CI: 0.25–0.86, p < 0.05) or two (OR = 0.41, 95%CI: 0.22,0.78, p < 0.01; OR = 0.24, 95%CI: 0.07–0.77, p < 0.05) 3–30-300 rule components are significantly associated with reduced medical visits and hospitalizations refer to not met these criterias. In the GWR local analysis, achieved 30 % vegetation cover is significantly related to improved social health at all locations. Meeting any two indicators also contribute to improved social health (n = 511, β: 0.46–0.51, P < 0.05). ConclusionGreen exposure indicators based on the 3–30-300 rule guiding healthy urban green space development. We observed multidimensional health benefits when 1/3 or 2/3 of the indicators were met.

Factors Influencing Compliance to Follow-up Visits in Orthopaedic Surgery.

Orthopaedic procedures require postoperative follow-up to maximize recovery. Missed appointments and noncompliance can result in complications and increased healthcare costs. This study investigates the relationship between patient postoperative visit attendance and the distance traveled to receive care. A retrospective review of all surgeries performed by a single orthopaedic surgeon in 2019 at level 1 trauma center in a midsized city serving a largely rural population was completed. We excluded patients who underwent another subsequent procedure. Distance to care and time traveled were determined by the patient's address and the clinic address using Google Maps Application Programming Interface. Other variables that may affect attendance at follow-up visits were also collected. Univariate and multivariate logistic regression was done with purposeful selection. We identified 518 patients of whom 32 (6%) did not attend their first scheduled follow-up appointment. An additional 47 (10%) did not attend their second follow-up. In total, 79 patients (15%) did not attend one of their appointments. Younger age, male sex, Black or African American race, self-pay, Medicaid insurance, accident insurance, and increased distance were individual predictors of missing an appointment. In the final multivariate logistic regression model, male sex (OR 1.74), Black or African American race (OR 2.78), self-pay (OR 3.12), Medicaid (OR 3.05), and traveling more than 70 miles to clinic (OR 2.02) markedly predicted missing an appointment, while workers' compensation (OR 0.23) predicted attendance. Several nonmodifiable patient factors predict patient noncompliance in attending orthopaedic postoperative visits. When patients are considered at high risk of being lost to follow-up, there may be an opportunity to implement interventions to improve follow-up rate and patient outcomes, minimize patient costs, and maximize profitability for the hospital.

ISpot: An intelligent real-time pothole spot identification model using a CNN algorithm

Maintaining roads is a very intricate and significant global concern. Detecting road abnormalities, including potholes, is crucial in road monitoring and management. Identifying potholes is essential to minimize road accidents and car damage and improve travel comfort. Authorities have long seen road maintenance as a significant concern. However, the absence of accurate identification and connecting of road potholes exacerbates the problem. An end-to-end system named Intelligent Spotting (iSpot) of Pathole has been developed to address this issue by providing real-time identification, tracking, and geographical mapping of potholes around the city. A Convolutional Neural Network (CNN) framework is suggested and assessed using a real-world dataset for detecting potholes. Real-time maps displaying pothole locations are created using the Google Maps Application Programming Interface (API). Both pothole identification and mapping are combined into an Android application to offer a comprehensive service via this technology. The suggested model outperforms the baseline techniques regarding accuracy, precision, and F score.

A Malware Detection Framework Based on Semantic Information of Behavioral Features

As the amount of malware has grown rapidly in recent years, it has become the most dominant attack method in network security. Learning execution behavior, especially Application Programming Interface (API) call sequences, has been shown to be effective for malware detection. However, it is troublesome in practice to adequate mining of API call features. Among the current research methods, most of them only analyze single features or inadequately analyze the features, ignoring the analysis of structural and semantic features, which results in information loss and thus affects the accuracy. In order to deal with the problems mentioned above, we propose a novel method of malware detection based on semantic information of behavioral features. First, we preprocess the sequence of API function calls to reduce redundant information. Then, we obtain a vectorized representation of the API call sequence by word embedding model, and encode the API call name by analyzing it to characterize the API name’s semantic structure information and statistical information. Finally, a malware detector consisting of CNN and bidirectional GRU, which can better understand the local and global features between API calls, is used for detection. We evaluate the proposed model in a publicly available dataset provided by a third party. The experimental results show that the proposed method outperforms the baseline method. With this combined neural network architecture, our proposed model attains detection accuracy of 0.9828 and an F1-Score of 0.9827.

Geographical challenges and inequity of healthcare access for high-risk paediatric heart disease.

Geographical context is an important consideration for health system design to promote equality in access to care for patients with childhood heart disease (CHD), particularly those living in regional, rural, and remote areas. To help inform future policy and practice recommendations, this study aimed to (i) describe the geographic distribution of high-risk CHD patients accessing an Australian state-wide specialist service and (ii) estimate travel time for accessing healthcare via general practitioners (primary), nearest paediatric centre (secondary) and specialist paediatric cardiac centre (tertiary). Participants included a cohort of children (0-18year) who accessed state-wide specialist CHD services over a 3-year period (2019-2021) in Queensland, Australia. Locations for patient residence, general practitioner, closest paediatric centre and tertiary cardiac centre were mapped using geographical information system (GIS) software (ArcGIS Online). Travel distance and times were estimated using a Google Maps Application Programming Interface (API). 1019 patients (median age 3.8 years) had cardiac intervention and were included in the sample. Of this cohort, 30.2% lived outside the heavily urbanised South East Queensland (SEQ) area where the tertiary centre is located. These patients travel substantially further and longer to access tertiary level care (but not secondary or primary level care) compared to those in SEQ. Median distance for patients residing outside SEQ to access tertiary care was 953km with a travel time of 10h 43min. This compares to 5.5km to the general practitioner and 20.6km to a paediatric service (8.9 and 54min respectively). This geographical mapping of CHD services has demonstrated a key challenge inherent in providing specialist cardiac care to children in a large state-based healthcare system. A significant proportion of high-risk patients live large distances from tertiary level care. The greater accessibility of primary care services highlights the importance of supporting primary care physicians outside metropolitan areas to acquire or build the ability and capacity to care for children with CHD. Strengthening local primary and secondary services not only has the potential to improve the outcomes of high-risk patients, but also to reduce costs and burden associated with potentially avoidable travel from regional, rural, or remote areas to access specialist CHD services.

The Seasonal Migrants Spatially Affect the Park Green Space Accessibility and Equity under Different Travel Modes: Evidence from Sanya, China

The influx of seasonal migrants has a significant impact on public services in destination places and may reshape the spatial accessibility and equity patterns of park green space (PGS). However, the two-step floating catchment area (2SFCA) method and its extended forms neglect discrepancies between the travel behaviors of seasonal migrants and native residents and thus fail to delineate variations in PGS accessibility and equity in areas with seasonal migrants. To avoid this issue, this study drew on the case of Sanya, a city with large numbers of Houniao, who are primarily retirees leading seasonal migration between the north and the south of China. A multi-group, multi-mode Gaussian-based 2SFCA method was also proposed to evaluate the PGS accessibility and equity before and after the Houniao influx. The method considered the changes in the COVID-19 restrictions from a refined perspective, with fine-scale residential areas being the research units and travel time requested from the web map application programming interface. The results showed that most residential areas were found to have relatively low PGS accessibility and equity levels, except for those in the south-central and southwestern urban areas of Sanya. Both the Houniao influx and lifted COVID-19 restrictions affected the spatial patterns of PGS accessibility and equity. PGS accessibility and equity were decreased by the Houniao influx, whereas walking and public transport within a few residential areas outside Houniao gathering spots improved. This study can serve as a basis for the reasonable planning of PGS and other public services in cities receiving seasonal migrants, such as Sanya.

Rate of Emergency Lower Extremity Amputations in the United States Among Medicare Beneficiaries.

To determine the rate of emergency versus elective lower extremity amputations in the United States. Lower extremity amputation is a common endpoint for patients with poorly controlled diabetes and multilevel peripheral vascular disease. Although the procedure is ideally performed electively, patients with limited access may present later and require an emergency operation. To what extent rates of emergency amputation for lower extremities vary across the United States is unknown. Evaluation of Medicare beneficiaries who underwent lower extremity amputation between 2015 and 2020. The rate was determined for each zip code and placed into rank order from lowest to highest rate. We merged each beneficiary's place of residence and location of care with the American Hospital Association Annual Survey using Google Maps Application Programming Interface to determine the travel distance for patients to undergo their procedure. Of 233,084 patients, 66.3% (154,597) were men, 69.8% (162,786) were White. The average age (SD) was 74 years (8). There was wide variation in rates of emergency lower extremity amputation. The lowest quintile of zip codes demonstrated an emergency amputation rate of 3.7%, whereas the highest quintile demonstrated 90%. The median travel distance in the lowest emergency surgery rate quintile was 34.6 miles compared with 10.5 miles in the highest quintile of emergency surgery ( P < 0.001). There is wide variation in the rate of emergency lower extremity amputations among Medicare beneficiaries, suggesting variable access to essential vascular care. Travel distance and rate of amputation have an inverse relationship, suggesting that barriers other than travel distance are playing a role.

Online Destinations Map using Google Maps API Based on the Private Database

Online mapping applications have undergone a radical change as a result of the widespread use of the Internet,and an interested in the developing of the online mapping services due to the use of the Google Maps Application Programming Interface (API), Yahoo Maps API, and ESRI ArcGIS API, as well as the support for maps by operating systems on tablets and smartphones. One of the most helpful technologies for identifying locations and providing information about roads is online mapping. Although these applications are simple to use, they have a limited amount of the data that may be inaccurate, and the mapping technology does not have sophisticated or detailed characteristics of the required places. As a result, developers and programmers use maps as a platform to create features that are tailored to the needs of the user by using various programming languages. The goal of this paper is to develop the Google API by connecting it to a local, private database that houses data that is regularly gathered and developed. It also aims to create opportunities that make it easier for clients to access information stored on particular servers that can provide a variety of locations and details in order to meet their needs.

An Internet of Things (IoT) Based Neighbourhood Distress Alert System

To acquiesce to the increase in territorial invasion of communities by hoodlums, bandits and kidnappers every day, some communities have resorted to engage the services of security agents or guards to watch over and alert them in the case of any security breach. However, the neighbourhood s found in some locations especially, in the rural areas impact on the cost of employing guards, and the consequent disagreement amongst residents in the neighbourhood security meeting. This paper proposes an Internet of Things (IoT) based system for alerting residents in a neighbourhood as well as reporting the actual location of a particular neighbour in distress. To achieve this, a hardware system based on NodeMCU with built-in Wi-Fi chip for internet routing is designed. Communication is established remotely between the hardware system and the cloud through the server Application Programming Interface (API) that utilizes cloud resources such as Short Message Service (SMS) gateway and Google map API to craft SMS and fetch location coordinate from Google map Uniform Resource Location (URL) respectively. This piece of information is then displayed on the Liquid Crystal Display (LCD) device on users’ machine and mobile phones in real time for notification. The test carried out shows that the developed system is reliable and affordable for use in a neighbourhood.

GIS for Real-Time Mapping in Field Surveys

ABSTRACT Context: A geographic information system (GIS) is a framework for gathering, managing, and analyzing data. Department of Community Medicine was tasked with SARS-CoV2-IgG antibody serosurvey by Pimpri Chinchwad Municipal Corporation, sampling 5000 people spread over an area of 181 sq. km. There were no real-time mapping apps available for field surveys. Aims: Our aim was to develop an easy-to-use GIS system with a shallow learning curve and real-time mapping for field surveys which could be easily deployed. Materials and Methods: The program was developed using PHP hosted on a virtual private server and using Google Maps Application Programming Interface (API). The field investigator shares location through telegram to a bot which parses message, decodes geo-coordinates, team information, and time stamp. The program then passes the information for further processing, viewing, or analyzing. The map is generated using Google Maps API at user request. The teams are segregated using color coding. Results: The data can be accessed at http://test.techlabel.in/. Over 638 households from which samples were taken were plotted by the data from ten teams over ten days. Real-time feedbacks were possible as the study progressed. Households plotted on the maps were verified by the respective field investigators after the study had completed and showed good accuracy. Conclusion: The introduction of GIS software such as ours could bring about a positive impact on small- and medium-scale field researches. The quality and internal validity of small-scale field researches could certainly be improved by using GIS programs.

Twitter-based classification for integrated source data of weather observations

&lt;span lang="EN-US"&gt;Meteorology and weather forecasting are crucial for predicting future climate conditions. Forecasts can be helpful when they provide information that can assist people in making better decisions. People today use big data to analyze social media information accurately, including those who rely on the weather forecast. Recent years have seen the widespread use of machine learning and deep learning for managing messages on social media sites like Twitter. In this study, authors analyzed weather-related text in Indonesia based on the searches made on Twitter. A total of three machine learning algorithms were examined: support vector machine (SVM), multinomial logistic regression (MLR), and multinomial Naive Bayes (MNB), as well as the pretrained bidirectional encoder representations of transformers (BERT), which was fine-tuned over multiple layers to ensure effective classification. The accuracy of the BERT model, calculated using the F1-score of 99%, was higher than that of any other machine learning method. Those results have been incorporated into a web-based weather information system. The classification result was mapped using Esri Maps application programming interface (API) based on the geolocation of the data.&lt;/span&gt;

LocateUAV: Unmanned Aerial Vehicle Location Estimation via Contextual Analysis in an IoT Environment

Object detection supported by unmanned aerial vehicles (UAVs) has generated significant interest in recent years including applications, such as surveillance, search for missing persons, traffic, and disaster management. Location awareness is a challenging task, particularly, the deployment of UAVs in a global positioning system (GPS) restricted environment or GPS sensor failure. To mitigate this problem, we propose LocateUAV, a novel location awareness framework, to detect UAV’s location by processing the data from the visual sensor in real time using a lightweight convolutional neural network (CNN). Assuming that the drone is in an IoT environment, first, the object detection technique is applied to detect the object of interest (OOI), namely, signboard. Subsequently, optical character recognition (OCR) is applied to extract useful contextual information. In the final step, the extracted information is forwarded to the map application programming interface (API) to locate the UAV. We also present a newly created data set for LocateUAV, which comprises challenging scenarios for context analysis. Moreover, we also compress an existing lightweight model up to 45 MB for efficient processing over UAV, which is 19.5% when compared with the size of the original model. Finally, an in-depth comparison of various trained and efficient object detection and OCR techniques is presented to facilitate future research on the development of flex drone that can extract information from the surroundings of a location in a GPS-restricted environment.

Implementation of Geographic Information System for Tourist Locations and Lodging Services in Lhokseumawe City Based on Android

The advancement of information technology is now increasingly widespread and very rapidly growing so that it can help people to enjoy the various conveniences that have been produced by this technology. One aspect of technology currently developing rapidly is mobile technology on smartphone devices (smartphones). This android-based geographic information system application is one of the results of these technological developments, which have the benefits and uses that are needed in this day and age. So with the development of the world of technology, people prefer the way of convenience and efficiency, for example, by utilizing the sophistication of smartphones. Implementing the Geographic Information System (GIS) for tourism and lodging services in Lhokseumawe aims to build tourism applications and lodging services in Lhokseumawe based on Android and implement Google services. Maps Application Programming Interface (API) to facilitate tourists in obtaining information on mapping the location of tourist attractions and lodging, routes, and tourist support facilities in Lhokseumawe City. The method used is a waterfall process model. Implementing the Lhokseumawe Tourism Application and lodging services using Javascript programming with Android Studio, MySQL database, and maps sourced from the Google Maps API. The result is an Android-based Lhokseumawe City Tourism and lodging service application that helps make it easier for tourists to obtain information about tourist attractions, lodging, and routes from their current location to the desired tourist and lodging locations in Lhokseumawe City with the help of the Global Positioning System (GPS). Tourist information and lodging services are entirely related only to data entered into the database server. The results of this application display a list and location of tourist and lodging services as well as the shortest route to the nearest tourist or inn to the user's location point. It is also hoped that this system can be developed to produce a better system than the previous one.

Assessing the Accessibility of Swimming Pools in Nanjing by Walking and Cycling Using Baidu Maps

Frequent severe heat waves have caused a series of health problems for urban dwellers. Swimming, an exercise that combines both cooling off and moderate to vigorous physical activity (MVPA), is one solution for alleviating the conflict between urban heat problems and public health. Therefore, the distribution and spatial accessibility of swimming pools are worth examining. Using open-source data we scraped from the Baidu Map API (Application Programming Interface), we designed and constructed a grid-based accessibility index. We analyzed pool accessibility in three aspects: distribution of pools, catchment area of pools, and spatial disparities of the accessibility index. The results are as follows. (a) The pools are clustered, dense in the central area, and sparse in the peripheral areas. (b) 53.16% of the residents can access a pool within 5 minutes by cycling, and the number is only 12.03% when they travel on foot. The poor situation is highly improved with the extension of time, these figures are up to 97.62% and 70.71% when the time cost is 15 minutes. The overall circular buffer significantly mismatches the real catchment area of the pools. (c) The spatial disparity in accessibility is significant and shows a sharply decreasing trend outward from the center. (d) Pool accessibility is mainly influenced by the distribution of pools and ground obstacles such as rivers, mountains, and elevated roads. The method used here has high precision and can be used for accessibility assessments of other facilities in the city.

SOS Application Under Android: Help Pro

Information and Communication Technologies are regularly used in medical services and associations around the world. An increasing number of devices running Android as Smartphones, smart TV and tablets, are comprehensively utilized for numerous purposes. For these devices, there are distinctive types of health and medical applications that provide an easy access to patients and their caretakers to save time [1]. In this work, we develop an Android application named Help Pro with an important goal: save lives by a single tap. In case of emergency, Help Pro users could have an ambulance available within 100 m of the user’s real-time location. Through the Dijkstra algorithm, this application employs Google Maps API (Application Programming Interface) to trace the nearest way in order to an available ambulance arrives on time. Consequently, not only time is efficiently saved but also precious lives.

Association between neighborhood food environment and dietary diversity score among older people in Beijing, China: A cross-sectional study.

ObjectiveTo examine the association between the neighborhood food environment and dietary diversity score (DDS) among elderly people in China.MethodsParticipants were recruited from 12 communities in Beijing, China, in 2019, using a multi-stage stratified random sampling method. Participants (n = 1,764, 730 men) in this study were elderly people aged 65 to 80. A questionnaire survey was used to investigate the intake of various foods in the past 3 days, and their dietary diversity score (DDS) was calculated. Baidu Map Application Programming Interface was used to measure the neighborhood food environments, including the density of and proximity to different food outlets. Adjusted multiple linear regression was performed to estimate the association between the neighborhood food environment and DDS.ResultsA total of 1,800 questionnaires were distributed, and 1,775 questionnaires were returned. The questionnaire response rate was 98.6%. Among them, the number of valid questionnaires was 1,764, and the valid rate was 99.4%. The mean age of the participants was 69.7 ± 4.3, and the average DDS was 7.2 ± 1.4. Among the three types of stores, convenience stores had the best access, followed by greengrocers, and finally supermarkets. Sit-down restaurants had the nearest walking distance, Chinese fast-food restaurants had the largest number, and western fast-food restaurants were the most difficult to access. Better access to supermarkets tended to be associated with higher DDS score within all the buffer zones (250 m buffer zone: β = 0.495, P < 0.001; 500 m buffer zone: β = 0.341, P < 0.001; 800 m buffer zone: β = 0.163, P < 0.001; 1,000 m buffer zone: β = 0.243, P < 0.001). However, greengrocers were negatively associated with DDS score within all the buffer zones (250 m buffer zone: β = −0.475, P < 0.001; 500 m buffer zone: β = −0.161, P < 0.001; 800 m buffer zone: β = −0.090, P < 0.001; 1000 m buffer zone: β = −0.112, P < 0.001). As for convenience stores, we only found significant results within the 250 m buffer zone (β = 0.075, P = 0.002). Among the three types of restaurants, the results were inconsistent within different buffer zones. Sit-down restaurants were negatively associated with DDS score within 250 m buffer zone (β = −0.257, P < 0.001), and positively associated with DDS score within 1,000 m buffer zone (β = 0.018, P < 0.001). Living in areas with more Chinese fast-food restaurants tended to have higher DDS within 250 m buffer zone (β = 0.357, P < 0.001); however, there was a opposite result within 1,000 m buffer zone (β = −0.044, P < 0.001). Better access to western fast-food restaurants tended to be associated with lower DDS score within 500 m buffer zone (β = −0.235, P < 0.001) and higher DDS score within 1,000 m buffer zone (β = 0.189, P < 0.001). There was a negative correlation between the nearest distance to the supermarket and the DDS score (β = −0.002, P < 0.001), and the nearest distance to the greengrocer was directly positively correlated with the DDS score (β = 0.004, P < 0.001).ConclusionThis study suggests that supermarkets may increase the DDS score among older adults in Beijing, while greengrocers may reduce the DDS score. However, the current results are not strong enough to draw specific conclusions. Policymakers need to rely on more evidence to make specific policy recommendations.