Invented by Praduman Jain, Josh Schilling, Dave Klein, Vignet Inc

The market for monitoring infectious diseases using location data and surveys has gained significant momentum in recent years. With the increasing prevalence of global pandemics and the need for accurate and timely data, this market has become a crucial tool for public health officials, researchers, and policymakers. One of the key drivers of this market is the availability of location data. With the widespread use of smartphones and other mobile devices, individuals are constantly generating data about their whereabouts. This data can be collected and analyzed to track the spread of infectious diseases. By monitoring the movement patterns of individuals, health officials can identify high-risk areas and implement targeted interventions to prevent the further spread of diseases. Surveys also play a vital role in monitoring infectious diseases. By collecting data on symptoms, exposure, and other relevant information, surveys provide valuable insights into the prevalence and impact of diseases. Surveys can be conducted through various channels, including online platforms, phone calls, and in-person interviews. The data collected through surveys can be used to identify trends, assess the effectiveness of interventions, and inform public health policies. The market for monitoring infectious diseases using location data and surveys is driven by several factors. Firstly, the increasing globalization and interconnectedness of the world have made it easier for diseases to spread across borders. This has heightened the need for real-time data to track and respond to outbreaks effectively. Secondly, advancements in technology have made it easier to collect, analyze, and visualize data. With the development of sophisticated data analytics tools and platforms, health officials can now process large volumes of data quickly and derive meaningful insights. This has enabled them to make informed decisions and take proactive measures to control the spread of diseases. Furthermore, the COVID-19 pandemic has highlighted the importance of monitoring infectious diseases using location data and surveys. The pandemic has demonstrated the devastating impact that a highly contagious disease can have on global health, economies, and societies. As a result, there is now a greater emphasis on investing in disease surveillance systems to prevent and mitigate future outbreaks. The market for monitoring infectious diseases using location data and surveys is expected to witness significant growth in the coming years. According to a report by Grand View Research, the global disease surveillance market is projected to reach $10.5 billion by 2027, growing at a compound annual growth rate of 8.1%. However, there are challenges that need to be addressed to fully realize the potential of this market. One of the key challenges is ensuring data privacy and security. As location data and survey responses contain sensitive information, it is crucial to establish robust data protection measures to safeguard individuals’ privacy. Additionally, there is a need for standardization and interoperability of data across different systems and platforms. This would enable seamless integration and sharing of data between different stakeholders, facilitating collaboration and enhancing the effectiveness of disease surveillance efforts. In conclusion, the market for monitoring infectious diseases using location data and surveys is a rapidly growing sector. With the increasing need for real-time data to track and respond to outbreaks, this market has become an essential tool for public health officials and researchers. However, addressing challenges related to data privacy and standardization is crucial to fully harness the potential of this market and effectively combat infectious diseases.

The Vignet Inc invention works as follows

Methods and systems for automating contact tracking using multiple data sources, including computer programs stored on computer-storage medium.” In some implementations a system can use location data based on signals such as GPS, WIFI, signals of cellular base stations or signals from short range wireless technology, e.g. Bluetooth. Users are also asked to provide information about their location and conditions at those locations. This can be done at the moment the user is there or at a later time. The system uses this information to compare the tracked locations of different individuals in order to identify contacts that meet criteria for disease transmission, such as when two people are close enough and at the right time. The detected instances of contact can be used by individuals to alert them to exposure to a particular disease as well as public health authorities.

Background for Monitoring infectious diseases using location data and surveys

Contact tracing can be one of the most effective tools to control the spread of infectious disease, like COVID-19. Contact tracing is used to identify individuals who were in close contact with someone who has a disease. It also identifies those who may have been exposed and could be at risk of infecting other people. Many contact tracing methods require manual labor by workers who are tasked with tracing contacts. They also have a limited range of information that can be collected and used. People’s memories of their past travels and interactions with other people are often limited. This is especially true if they are asked about the events hours or even days later.

In some implementations, computer systems use a combination multiple data sources in order to track down individuals. Mobile phones and other devices can detect wireless signals coming from a wide range of sources. These include GPS, Wi-Fi networks, cell towers, beacons for location, etc. These data can be used to determine the location of a phone, or the proximity of a phone with other devices. The system also collects data from users via surveys, forms or other input prompts. The system can initiate these user interactions, and prompts to provide information are aimed at obtaining information about the context or situation that the user is currently in. The system can, for example, initiate selective requests for information based upon the proximity and location data detected by an individual device. Information requests can be tailored to individual users based on their history, attributes, context and other factors. The system uses responses from users to confirm the users’ locations, refine location data (e.g. increase accuracy and precision), confirm and provide context to instances of detected proximity to other individuals, add instances of contact that were not captured in sensed information, etc. In order to achieve a more accurate and comprehensive contact tracking, the system uses both automatically sensed data and user-submitted information. The information about detected contacts is available to both the people involved in the contact as well as to the public health authorities.

In general, contact between individuals is not based on physical contact but rather on proximity, which can be defined as being in the same room, or within a specific distance (e.g. 6 ft., 10 ft., 20 ft., etc.). Contacts may also be governed by a time requirement, such as the minimum amount of time for which the contact must continue. Interaction between two individuals (e.g. talking together, shaking hand, etc.) can result in a contact that is detected. Contact can be detected without any interaction, but it is possible. Two people, for example, who are within a specified distance (e.g. 10 ft), and have been in that proximity for a specific amount of time (5 minutes, 15 minutes or 30 minutes) can be considered to be in contact. It is possible to be in contact even when you are unaware of the other person’s presence.

The system can be configured in a variety of ways to detect contacts. For example, it could only detect two-person contact or based solely on the distance between them. It could also take into account both the duration of proximity as well as their proximity. The system can be configured to detect different types of contacts based on proximity or duration. The sliding scale can also be used to assess proximity and duration together. For example, a very short duration (e.g. 1 minute) that normally would not trigger contact would still trigger detection if it were close enough (e.g. within 5 minutes). A distance of 20 feet would not normally trigger a registered contact, but if co-location lasts a long time (e.g. 20 minutes), a contact will be detected. A contact can be detected in different conditions, such as a close proximity (e.g. 5 feet) for a short period of time (e.g. within 10 feet) for a medium time period (10 minutes), or a low proximity (e.g. within 20 feet) for a longer period (20 minutes).

Traditional contact tracking focuses on instances where individuals are co-located in a space. For example, when people are simultaneously present in a shared location. This system is able to detect and report such contacts. COVID-19, and other diseases, can spread via airborne transmission. However, the co-location of people to overlap in space and time is not required to transmit disease. A person who visits a place can leave infectious particles on surfaces or in the air that persist hours after they have left. The system can detect potential disease transmissions or contacts that happen when there is no simultaneous presence of people but someone enters a space where an infected individual was located. If a person enters a room and stays there for 30 minutes, then leaves and a second person arrives, the system will detect and register the contact due to the residual infectious particles. This is true even if the two people are not in the same place at the time. The system can determine the likelihood of such events and the degree of contact that took place by analyzing the information available about the surrounding environment and conditions at the time. (e.g. whether both users were wearing masks, the size of the room, the ventilation level, etc.).

The system can detect and track contacts between individuals using several different techniques. These techniques may be used alone or together. The transmission and reception wireless messages between devices (e.g. via BLUETOOTH including BLUETOOTH Low Energy (BLE) or other communication channels), e.g. phones, smartwatches etc. is one technique. Devices can broadcast messages with identifiers so that, when two devices are in proximity to each other, they receive the broadcasted messages and receive the identifier of the other device. This exchange of information between devices is valuable, but does not capture every possible contact, especially when some devices disable the wireless communication channel (e.g. to conserve battery life), there is interference or if the signal strength is variable. Other types of signals and locations data can be used to detect contacts.

In some implementations, very precise location tracking with accuracy of less than a meter can be performed using techniques such as real time kinematics (RTK) services from cellular service providers, leveraging data from survey-grade multi-constellation multi-frequency reference stations with geodetic antennas and potentially 3GPP standards like the Location Positioning Protocol. Some implementations can achieve very accurate location tracking of less than one meter using real-time kinematics services provided by cellular service providers. These services leverage data from survey-grade, multi-frequency, multi-constellation reference stations equipped with geodetic antenas and possibly 3GPP standards such as the Location Positioning Protocol.

In general, not all types of location data are available or accurate in every situation. GPS signals are less accurate when in densely populated city centers, with high skyscrapers. The arrangement and density of Wi-Fi and cellular base station access points also vary. The present system integrates the location data of these different sources in order to achieve the highest possible accuracy and maintain location tracking under a variety of conditions and places. Location data can be aggregated on a user-device level (e.g. mobile phone) or at a server system. Together, the most accurate and reliable sources of location data available at any time can be combined to pinpoint a person’s exact location. The system can track the device’s location over time to determine the route taken and the locations visited. Location tracking data can include timestamps in order to align and coordinate readings from various location measurement techniques. It also allows users to compare their location tracking data with other users.

In some implementations the location tracking data of different users can be used to improve the accuracy and precision and fill in any gaps in the location tracking records. A first user’s mobile phone might have accurate location services available from its mobile service provider, but a second users’ phone service could provide much lower accuracy in determining location. If the two phones are in close proximity, they can exchange wireless messages to identify each other. The high-accuracy data from the first device can be used in conjunction with the data for a second device to pinpoint the exact location at the time. A smartwatch without a GPS receiver can receive wireless messages that indicate the presence of devices with GPS location data. The system can use the presence of devices at certain times to fill in the location of the smartwatch. Location data can then be transitive, in that it can be attributed or inferred to other devices based on the fact they were nearby or co-located.

The system can send messages to users in order to initiate interactions and collect user-reported data about a user’s situation (e.g., location, activity, environment, disease prevention measures, number of people present, identities of people present, etc.). The system can send messages to users in order to start interactions and collect data from the user (e.g. location, activity, environmental factors, disease prevention measures or number of people). The system may ask the user to provide information on their current situation or a previous situation (e.g. an hour earlier, a day prior, etc.). The system can ask the user for information about their current situation, a previous situation (e.g. an hour before, a day before etc.) or a future scenario (e.g. a planned action or prospective action by the user). The system can initiate automatic requests for information when it detects certain triggers, conditions or patterns in the data collected for an individual user. Requests can also be made selectively based on certain contexts, patterns or measurements. Location data can be used to determine whether or not a request is made for information by a user. For example, if the user enters or remains in a certain location. The request can also be made in response to a user’s information regarding their disease status, for example, a COVID-19 positive test result.

The system can prompt users to provide information in real-time or in a manner that is close to real-time about their current state. Sending data for an eco-momentary assessment (EMA), to get information from the user about their current situation, e.g. location, environment and behavior, experiences, observations or context, while still in that situation, is one example. The ability to ask users for information automatically and programmatically can improve the accuracy and depth information used in contact tracing. This method of gathering data from users can reduce recall bias, and also allow the user observe and report details that may have otherwise gone unnoticed. This prompt can be given before the detection of a possible contact with someone infected by COVID-19. The system can prompt the user to describe their movements and activities at different times or locations, regardless of the disease status of the people around them.

The prompts can be used for a variety of purposes. For example, they could gather data in order to track the location of a user, either in conjunction with or instead other sources of location data (e.g. to fill in any gaps, or to identify a specific room or floor in which a person is located within a building). Responses to prompts may be used to verify that a user is actually in the location shown by their phone. The location data of a device can sometimes not reflect the true location of a person. For example, someone may have borrowed the phone or left it at home, but then gone to another location. Or, they may have forgotten the phone on her desk and went into a meeting room. The responses to prompts can also indicate the conditions of the locations (e.g. whether masks are being worn, what type of building it is, ventilation levels, how many people there are, etc.) in order to assess exposure risks.

Prompting users to interact can help generate an accurate record of a user’s movement and interactions. This is generated in small increments throughout the day. The prompts could ask for the most important visits and activities, such as the areas of destination where most time was spent. In this way, the user’s location is verified by user feedback and can be made more precise close to their actual visit. The user’s location and activities, determined in this way through a combination between location tracking and data submitted by the user, can also be compared accurately with other users’ movements and location data to detect contacts with COVID-19 individuals. Consider, for example, a scenario in which a person who was at a particular location with the user later on (e.g. later that day or the following day) is determined to have an infectious COVID-19 at the time they were together. The system has already collected the information needed to determine whether or not a contact took place.

In some implementations, prompts are sent to users regarding previous visits and locations. In response to information received about the movement of an individual with a COVID-19 case, or other location tracking information, or to new information regarding disease status for individuals (e.g. positive test results, symptoms of disease, etc.), the system may prompt users to provide information. The system can determine that a person infected was in close contact with another user. The system can compare movement patterns and timings of individuals to determine if there was a risk of infection. This could be due to an overlap or close proximity of two individuals’ location data, if one of them is a COVID-19 patient. The system can use the similarity of timing and location to send a prompt (e.g. the user with COVID-19, or the user who was potentially exposed), requesting information such as location data and confirmation. The system can send a request for the current conditions detected, or prior conditions such as an earlier visit or one that occurred a day before. Even if the system gathers information from users in general daily interactions, it can ask for prior situations or locations that had a high probability or potential of a COVID-19 contact. The system may also prompt users to provide additional information such as the user’s disease status (e.g. test results, symptoms, etc .).

The system can be used to gather information about the disease status (e.g. positive test results or disease symptoms) and predict disease status using machine-learning models. Location tracking data can be used in conjunction with COVID-19 to identify cases where the virus has spread. Once a person has been identified as having COVID-19 confirmed or probable, the system will compare location tracking data. (e.g. travel paths, times, and locations visited, etc.). Comparing the data from other users’ location tracking to determine if there is a time and space overlap. The system can ask users to provide additional information if it finds that there is overlap between the paths taken and the locations visited. The system can identify instances of contact if people are in close proximity, for example, at the same location and time. It may also find instances when a person enters an area that a COVID-19-infected person has recently visited, even if their visits do not overlap or coincide in time. Location data can be compared in real-time, such as when users provide their location, respond to prompts and report disease status (e.g. test results, symptoms reports, etc.). The system can alert users to instances of contact.

The system can combine information from multiple users to determine the conditions present at a particular location and the possibility of disease-transmitting contacts. A first user, second user and third user might visit the same location at different times. The data from user responses for one or more of these users can be used to determine if a contact took place and assess the risk posed by contacts. The first user, for example, may indicate the number of people in a shop at a specific time. This information can be used to determine the risk of other users present at the time. The second user can indicate whether or not people are wearing masks at the location. This information is used to determine the level of risk for everyone present. Another example is that the first and second user may receive an identifier on the phone of the other user. This would indicate their proximity to the other user. The fact that both the first and the second user received the message at the same moment can indicate they were close to each other. Even if the location tracking information for the second and third users is unknown, the known location of the other user can be deduced from the data.

The system can contact individuals involved once contacts between individuals have been identified. The system could send a warning or notification to a person if it determines that they have been in contact with someone having a confirmed or likely case of COVID-19. The system can also send instructions or suggestions to the person, such as recommending that they visit a doctor or get a disease-testing kit or recommend a behavior modification or medication in order to avoid or limit symptoms. These recommendations can also be tailored to each user based on their age, comorbidities and other attributes.

The method can be performed by one computer or several computers. It includes the following: obtaining, from the one-or-more computers, location information for a user’s device, which is associated with that user.

In some cases, the disease is COVID-19.

In some implementations the device that is associated with the person may be a mobile phone or wearable device.

In some implementations, receiving location data includes receiving location data from the device that is associated with the user over a communications network. This data indicates a specific location that is the current location of that device. The data to be used for the prompt is generated by sending one or more information requests to the user to confirm the presence of the person at the location. The data for the alert is provided while the device remains at the location. The method involves causing the device that is associated with the user, to display the prompt, or to send a notification to inform the user of this prompt, while it is at the location.

Click here to view the patent on Google Patents.