Description:
BACKGROUND
Field of Invention
[001] Embodiments of the present invention generally relate to an epidemic monitoring system and particularly to a computer-implemented system for real-time surveillance and intervention for low-incidence infectious disease outbreaks.
Description of Related Art
[002] Public health surveillance systems serve as the foundation for monitoring infectious diseases at regional and global levels. Conventional systems depend largely on clinical diagnosis, laboratory testing, and manual reporting procedures. Such systems often remain limited to common and high-incidence diseases that follow predictable patterns. When diseases fall outside expected behavior, the established systems usually fail to capture anomalies at an early stage. This delay creates significant risks, especially in the case of rare infections where the window for effective intervention is narrow.
[003] Several digital health tools and integrated disease programs attempt to strengthen epidemic control by introducing mobile-based reporting and centralized databases. These tools, however, remain primarily reactive in nature, addressing outbreaks only after clinical cases appear in substantial numbers. In addition, most of the existing tools rely on structured data inputs while ignoring valuable unstructured information such as environmental shifts, population movements, or animal vectors. The result is a fragmented surveillance network with limited predictive value for public health agencies.
[004] Patents and prior art in this domain include IN202011017336 titled ‘Disease Surveillance System using Mobile and Web Interface’, IN202141038167 titled ‘AI-Based Health Monitoring using Wearables’, and IN201941053715 titled ‘Smart Healthcare System using IoT’. While such technologies add efficiency to data gathering and transmission, they still present critical limitations. These include excessive dependence on symptomatic data, lack of adaptability for low-incidence diseases, insufficient use of geospatial or behavioral information, and delays caused by central data aggregation.
[005] There is thus a need for an improved and advanced computer-implemented system for real-time surveillance and intervention for low-incidence infectious disease outbreaks that can administer the aforementioned limitations in a more efficient manner.
SUMMARY
[006] Embodiments in accordance with the present invention provide a computer-implemented system for real-time surveillance and intervention for low-incidence infectious disease outbreaks. The computer-implemented system comprising heterogeneous data acquisition devices adapted to capture multimodal data selected from physiological signals, environmental parameters, self-reported symptoms, mobility traces, environmental imagery, reportable events, or a combination thereof. The computer-implemented system further comprising a communication layer comprising a low-power wide-area network. The computer-implemented system further comprising edge computing nodes configured to pre-process the multimodal data received from the heterogeneous data acquisition devices using pre-processing techniques. The computer-implemented system further comprising a cloud-based analytics platform comprising a processing unit. The processing unit is configured to acquire multimodal data, via the edge computing nodes, from the heterogeneous data acquisition devices; detect spatiotemporal anomalies indicative of early outbreak signals using a spatiotemporal anomaly detection model trained for rare-event detection; correlate the detected spatiotemporal anomalies with geo-behavioural and environmental drivers; estimate, based on the correlated detected spatiotemporal anomalies, an outbreak likelihood, an extent of the outbreak, or a combination thereof; and generate intervention recommendations using a decision-support engine.
[007] Embodiments in accordance with the present invention further provide a processor-implemented method for real-time management of low-incidence infectious disease outbreaks. The method comprising steps of acquiring multimodal data, via edge computing nodes, from heterogeneous data acquisition devices; detecting spatiotemporal anomalies indicative of early outbreak signals using a spatiotemporal anomaly detection model trained for rare-event detection; correlating the detected spatiotemporal anomalies with geo-behavioral and environmental drivers; estimating, based on the correlated detected spatiotemporal anomalies, an outbreak likelihood, an extent of the outbreak, or a combination thereof; and generating intervention recommendations using a decision-support engine.
[008] Embodiments of the present invention may provide a number of advantages depending on their particular configuration. First, embodiments of the present application may provide a computer-implemented system for real-time surveillance and intervention for low-incidence infectious disease outbreaks.
[009] Next, embodiments of the present application may provide a computer-implemented system that enables identification of low-incidence and unusual infectious diseases at an early stage.
[0010] Next, embodiments of the present application may provide a computer-implemented system that reduces a risk of widespread transmission.
[0011] Next, embodiments of the present application may provide a computer-implemented system that provides immediate policy recommendations without dependence on manual reporting or delays.
[0012] Next, embodiments of the present application may provide a computer-implemented system that combines clinical, environmental, epidemiological, mobility, and behavioral datasets.
[0013] Next, embodiments of the present application may provide a computer-implemented system that results in higher accuracy and reliability compared to traditional methods.
[0014] Next, embodiments of the present application may provide a computer-implemented system that supports deployment in both rural and urban environments.
[0015] Next, embodiments of the present application may provide a computer-implemented system that allows nationwide expansion without heavy infrastructure changes.
[0016] Next, embodiments of the present application may provide a computer-implemented system that eliminates a need for human intervention, ensuring rapid responses with low operational delays.
[0017] These and other advantages will be apparent from the present application of the embodiments described herein.
[0018] The preceding is a simplified summary to provide an understanding of some embodiments of the present invention. This summary is neither an extensive nor exhaustive overview of the present invention and its various embodiments. The summary presents selected concepts of the embodiments of the present invention in a simplified form as an introduction to the more detailed description presented below. As will be appreciated, other embodiments of the present invention are possible utilizing, alone or in combination, one or more of the features set forth above or described in detail below.
BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The above and still further features and advantages of embodiments of the present invention will become apparent upon consideration of the following detailed description of embodiments thereof, especially when taken in conjunction with the accompanying drawings, and wherein:
[0020] FIG. 1 illustrates a schematic block diagram of a computer-implemented system for real-time surveillance and intervention for low-incidence infectious disease outbreaks, according to an embodiment of the present invention;
[0021] FIG. 2 illustrates an architectural diagram of the computer-implemented system for real-time surveillance and intervention for low-incidence infectious disease outbreaks, according to an embodiment of the present invention; and
[0022] FIG. 3 depicts a flowchart of a method for real-time management of low-incidence infectious disease outbreaks, according to an embodiment of the present invention.
[0023] The headings used herein are for organizational purposes only and are not meant to be used to limit the scope of the description or the claims. As used throughout this application, the word "may" is used in a permissive sense (i.e., meaning having the potential to), rather than the mandatory sense (i.e., meaning must). Similarly, the words “include”, “including”, and “includes” mean including but not limited to. To facilitate understanding, like reference numerals have been used, where possible, to designate like elements common to the figures. Optional portions of the figures may be illustrated using dashed or dotted lines, unless the context of usage indicates otherwise.
DETAILED DESCRIPTION
[0024] The following description includes the preferred best mode of one embodiment of the present invention. It will be clear from this description of the invention that the invention is not limited to these illustrated embodiments but that the invention also includes a variety of modifications and embodiments thereto. Therefore, the present description should be seen as illustrative and not limiting. While the invention is susceptible to various modifications and alternative constructions, it should be understood, that there is no intention to limit the invention to the specific form disclosed, but, on the contrary, the invention is to cover all modifications, alternative constructions, and equivalents falling within the scope of the invention as defined in the claims.
[0025] In any embodiment described herein, the open-ended terms "comprising", "comprises”, and the like (which are synonymous with "including", "having” and "characterized by") may be replaced by the respective partially closed phrases "consisting essentially of", “consists essentially of", and the like or the respective closed phrases "consisting of", "consists of”, the like.
[0026] As used herein, the singular forms “a”, “an”, and “the” designate both the singular and the plural, unless expressly stated to designate the singular only.
[0027] FIG. 1 illustrates a schematic block diagram of a computer-implemented system 100 for real-time surveillance and intervention for low-incidence infectious disease outbreaks, according to an embodiment of the present invention. In an embodiment of the present invention, the computer-implemented system 100 may provide an artificial intelligence-based surveillance and intervention system that may detect, track, and control low-frequency infectious disease epidemics in real-time. The computer-implemented system 100 may consist of Artificial Intelligence (AI) algorithms, Internet of Things-enabled data collection devices, cloud-based health databases, and decision support tools to combine environmental, epidemiological, and mobility data. The computer-implemented system 100 may facilitate predictive modeling, early outbreak warning, and policy recommendations to prevent epidemic expansion. The computer-implemented system 100 may constantly track anomaly patterns, geotagged health histories, and notify health officials. The solution may be taken into the field to urban and rural locations with modular flexibility. The computer-implemented system 100 may provide a scalable, smart infrastructure to safeguard public health with low latency and high accuracy, particularly where unusual outbreaks seldom occur and legacy systems respond slowly.
[0028] In an embodiment of the present invention, the computer-implemented system 100 may feature a built-in Artificial Intelligence (AI) driven decision-support mechanism specific to low-incidence and rare disease epidemics. The computer-implemented system 100 may use deep learning, federated data analysis, and spatiotemporal anomaly detection to forecast low-frequency outbreak trends. The computer-implemented system 100 may integrate wearable biosensors, satellite images, and hospital reporting in real-time into an early dynamic warning system. The computer-implemented system 100 may feature an intervention logic that may be strengthened with reinforcement learning to develop increasingly better policy suggestions over time. A foresight capability of the computer-implemented system 100 may be enhanced by integrating behavioral and environmental information. The computer-implemented system 100 may support prevention prior to the clinical symptom becoming statistically likely, thereby building a futuristic Artificial Intelligence (AI) first public health action system.
[0029] According to the embodiments of the present invention, the system 100 may incorporate non-limiting hardware components to enhance a processing speed and an efficiency, such as the system 100 may comprise heterogeneous data acquisition devices 102, a communication layer 104, a low-power wide-area network 106, edge computing nodes 108, a cloud-based analytics platform 110, a processing unit 112, and a decision-support engine 114. In an embodiment of the present invention, the hardware components of the system 100 may be integrated with computer-executable instructions for overcoming the challenges and the limitations of the existing systems.
[0030] In an embodiment of the present invention, the heterogeneous data acquisition devices 102 may be adapted to capture multimodal data. The multimodal data may be, but not limited to, physiological signals, environmental parameters, self-reported symptoms, mobility traces, environmental imagery, reportable events, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the multimodal data, including known, related art, and/or later developed technologies.
[0031] The heterogeneous data acquisition devices 102 may include sensors and input devices such as wearable sensors for capturing physiological data such as body temperature, heart rate, blood oxygen saturation, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the physiological data, including known, related art, and/or later developed technologies. Environmental sensors may capture temperature, humidity, air quality, and animal movement data. Mobile devices may provide Global Positioning System (GPS) tracking, symptom self-reporting, and Bluetooth-based tracing. Drone or remote cameras may enable thermal or visible data collection in remote locations.
[0032] In an embodiment of the present invention, the communication layer 104 may comprise the low-power wide-area network 106. The low-power wide-area network 106 may be selected from a Long-Range Wide Area Network (LoRa WAN), a Narrowband Internet of Things (NB-IoT), a Wireless-Fidelity (Wi-Fi), a Sigfox, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the low-power wide-area network 106, including known, related art, and/or later developed technologies. The low-power wide-area network 106 may be adapted to support a Message Queuing Telemetry Transport (MQTT), a Constrained Application Protocol (CoAP), and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the protocol, including known, related art, and/or later developed technologies.
[0033] In an embodiment of the present invention, the edge computing nodes 108 may be configured to pre-process the multimodal data received from the heterogeneous data acquisition devices 102 using pre-processing techniques. The pre-processing techniques performed by the edge computing nodes 108 may be, but not limited to, selected from validation, noise reduction, feature extraction, preliminary anomaly screening, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the pre-processing techniques, including known, related art, and/or later developed technologies.
[0034] In an embodiment of the present invention, the cloud-based analytics platform 110 may comprise the processing unit 112. The cloud-based analytics platform 110 may be configured to perform federated learning across the edge computing nodes 108 to aggregate model updates using secure aggregation. The processing unit 112 may be microcontrollers such as, but not limited to, an Espressif 32 (ESP32) and STMicroelectronics 32 (STM32) for local real-time data collection. Further, the edge computing nodes 108 may comprise processors such as NVIDIA Jetson Nano and Google Coral that may enable local machine learning inference. Additionally, cloud servers may provide central data aggregation, deep model training, and visualization.
[0035] The processing unit 112 may be configured to acquire multimodal data, via the edge computing nodes 108, from the heterogeneous data acquisition devices 102. The processing unit 112 may be configured to detect spatiotemporal anomalies indicative of early outbreak signals using a spatiotemporal anomaly detection model trained for rare-event detection. The spatiotemporal anomaly detection model may be a rare-event trained model selected from a deep neural network with spatiotemporal convolutions, a graph neural network, a Bayesian hierarchical model, a Gaussian process model adapted for sparse-event detection, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the rare-event trained model, including known, related art, and/or later developed technologies.
[0036] The spatiotemporal anomaly detection model may include anomaly detection models for early indication of abnormal disease activity. The spatiotemporal anomaly detection model may identify potential outbreak hotspots. Reinforcement learning agents may optimize intervention strategies. Federated learning frameworks may support privacy-preserving model training.
[0037] The processing unit 112 may be configured to correlate the detected spatiotemporal anomalies with geo-behavioural and environmental drivers. The detected anomalies may be correlated with the geo-behavioural and the environmental drivers may be performed by utilizing a set of the multimodal data selected from mobility traces, land-use maps, weather data, animal-movement data to compute a likelihood metric for outbreak propagation, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the multimodal data selected, including known, related art, and/or later developed technologies. The processing unit 112 may be configured to estimate, based on the correlated detected spatiotemporal anomalies, an outbreak likelihood, an extent of the outbreak, and so forth.
[0038] The processing unit 112 may be configured to generate intervention recommendations using the decision-support engine 114. The decision-support engine 114 may generate the intervention recommendations selected from targeted testing locations, resource allocation instructions, localized movement advisories, quarantine or isolation recommendations, public-health messaging templates, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the intervention recommendations, including known, related art, and/or later developed technologies. The processing unit 112 may be configured to assign a confidence score to each of the detected spatiotemporal anomalies to determine.
[0039] In an embodiment of the present invention, a power supply may include solar panels to operate the computer-implemented system 100. The power supply may further comprise rechargeable lithium-ion battery packs may be employed for portable power. The power supply may further comprise a grid connection may be utilized where available.
[0040] FIG. 2 illustrates an architectural diagram 200 of the computer-implemented system 100, according to an embodiment of the present invention.
[0041] In an embodiment of the present invention, the computer-implemented system 100 may operate through a structured sequence for epidemic surveillance and control. In an embodiment of the present invention, IoT devices, including wearable sensors, environmental sensors, and mobile devices, may capture real-time data. The collected data may include symptom inputs, physiological parameters, environmental conditions, and geolocation. In an embodiment of the present invention, mobility data such as geospatial movement and transportation records may be acquired. Further, modality data may provide additional context for tracking potential outbreak propagation.
[0042] In an embodiment of the present invention, the data may be transmitted to the cloud-based analytics platform 110. Before transmission, the processing unit 112 may be configured to perform verification and filtering. Noise may be rejected, and abstracted information may be generated. In an embodiment of the present invention, the decision-support engine 114 may process the transmitted data. The decision-support engine 114 may include anomaly detection models and predictive modeling frameworks. The anomaly detection models and the predictive modeling framework may analyze the spatiotemporal anomalies and may generate outbreak alerts when abnormal trends are detected.
[0043] The decision-support engine 114 may further generate intervention recommendations. The intervention recommendations may include targeted testing, movement control, mobilization measures, or public alerts. In an embodiment of the present invention, the intervention recommendations may be delivered to health authorities through dashboards and reports. Such outputs may enable real-time decision-making and immediate local response. In an embodiment of the present invention, the health authorities may provide feedback on the intervention recommendations. The feedback may be received through dashboards or reporting mechanisms. In an embodiment of the present invention, the feedback may be integrated back into the decision-support engine 114 and to the cloud-based analytics platform 110. A reinforcement learning and federated learning may be applied to update and optimize the decision-support engine 114.
[0044] In an embodiment of the present invention, the interaction among IoT devices, mobility data, Artificial Intelligence (AI) engines, cloud-based health databases, decision support engines, and health authorities may establish a closed-loop surveillance framework. The framework may be responsive, anticipatory, and specifically adapted for low-incidence infectious diseases.
[0045] In an embodiment of the present invention, the computer-implemented system 100 may provide a framework for real-time data input into a learning-based platform with capabilities for predictive and prescriptive guidance in controlling low-frequency infectious diseases. In an embodiment of the present invention, the computer-implemented system 100 may be constructed in synchronization with geographic needs and infrastructural availability.
[0046] In an embodiment of the present invention, a mobile-only version may be implemented, wherein mobile devices may act as sensors through symptom checkers, Global Positioning System (GPS) location, and Bluetooth tracking for rural village settings. In yet another embodiment of the present invention, a hospital-based representation may be incorporated into hospital health information systems (HIS) to provide real-time notifications to healthcare workers when anomalies are registered. In a further embodiment of the present invention, a wearable integration version may employ biosensors such as heart rate, body temperature, and oxygen level to detect abnormal patterns in high-risk groups.
[0047] In a further embodiment of the present invention, a drone-based data collection model may utilize drones for gathering environmental or population data in remote locations, that may be processed using Artificial Intelligence (AI) driven predictive analytics. In a further embodiment of the present invention, the edge computing nodes 108 deployment may enable in-sensor processing of data through the edge computing nodes 108 in low-connectivity environments, thereby generating alerts or collecting and forwarding data to central servers. In a further embodiment of the present invention, every occurrence of interoperable standalone hardware or node may be configured within an extensible surveillance network at a national level. Such a configuration may enable geographic and socioeconomic scalability with high intervention planning and outbreak prediction precision.
[0048] FIG. 3 depicts a flowchart of a method 300 for real-time management of the low-incidence infectious disease outbreaks using the computer-implemented system 100, according to an embodiment of the present invention.
[0049] At step 302, the computer-implemented system 100 may acquire the multimodal data, via the edge computing nodes 108, from the heterogeneous data acquisition devices 102.
[0050] At step 304, the computer-implemented system 100 may detect the spatiotemporal anomalies indicative of the early outbreak signals using the spatiotemporal anomaly detection model trained for the rare-event detection.
[0051] At step 306, the computer-implemented system 100 may correlate the detected spatiotemporal anomalies with the geo-behavioural and the environmental drivers.
[0052] At step 308, the computer-implemented system 100 may estimate, based on the correlated detected spatiotemporal anomalies, the outbreak likelihood, the extent of the outbreak, and so forth.
[0053] At step 310, the computer-implemented system 100 may generate the intervention recommendations using the decision-support engine 114.
[0054] While the invention has been described in connection with what is presently considered to be the most practical and various embodiments, it is to be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims.
[0055] This written description uses examples to disclose the invention, including the best mode, and also to enable any person skilled in the art to practice the invention, including making and using any devices or systems and performing any incorporated methods. The patentable scope of the invention is defined in the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements within substantial differences from the literal languages of the claims. , Claims:CLAIMS
I/We Claim:
1. A computer-implemented system (100) for real-time surveillance and intervention for low-incidence infectious disease outbreaks, the computer-implemented system (100) comprising:
heterogeneous data acquisition devices (102) adapted to capture multimodal data selected from physiological signals, environmental parameters, self-reported symptoms, mobility traces, environmental imagery, reportable events, or a combination thereof;
a communication layer (104) comprising a low-power wide-area network (106);
edge computing nodes (108) configured to pre-process the multimodal data received from the heterogeneous data acquisition devices (102) using pre-processing techniques; and
a cloud-based analytics platform (110) comprising a processing unit (112), characterized in that the processing unit (112) is configured to:
acquire multimodal data, via the edge computing nodes (108), from the heterogeneous data acquisition devices (102);
detect spatiotemporal anomalies indicative of early outbreak signals using a spatiotemporal anomaly detection model trained for rare-event detection;
correlate the detected spatiotemporal anomalies with geo-behavioural and environmental drivers;
estimate, based on the correlated detected spatiotemporal anomalies, an outbreak likelihood, an extent of the outbreak, or a combination thereof; and
generate intervention recommendations using a decision-support engine (114).
2. The computer-implemented system (100) as claimed in claim 1, wherein the pre-processing techniques performed by the edge computing nodes (108) are selected from validation, noise reduction, feature extraction, preliminary anomaly screening, or a combination thereof.
3. The computer-implemented system (100) as claimed in claim 1, wherein the cloud-based analytics platform (110) is configured to perform federated learning across the edge computing nodes (108) to aggregate model updates using secure aggregation.
4. The computer-implemented system (100) as claimed in claim 1, wherein the spatiotemporal anomaly detection model is a rare-event trained model selected from a deep neural network with spatiotemporal convolutions, a graph neural network, a Bayesian hierarchical model, a Gaussian process model adapted for sparse-event detection, or a combination thereof.
5. The computer-implemented system (100) as claimed in claim 1, wherein correlating detected anomalies with the geo-behavioural and the environmental drivers is performed by utilizing a set of the multimodal data selected from mobility traces, land-use maps, weather data, animal-movement data to compute a likelihood metric for outbreak propagation, or a combination thereof.
6. The computer-implemented system (100) as claimed in claim 1, wherein the decision-support engine (114) generates the intervention recommendations selected from targeted testing locations, resource allocation instructions, localized movement advisories, quarantine or isolation recommendations, public-health messaging templates, or a combination thereof.
7. The computer-implemented system (100) as claimed in claim 1, wherein the low-power wide-area network (106) is selected from a Long-Range Wide Area Network (LoRa WAN), a Narrowband Internet of Things (NB-IoT), a Sigfox, or a combination thereof.
8. The computer-implemented system (100) as claimed in claim 1, wherein the low-power wide-area network (106) is adapted to support a Message Queuing Telemetry Transport (MQTT), a Constrained Application Protocol (CoAP), or a combination thereof.
9. The computer-implemented system (100) as claimed in claim 1, wherein the processing unit (112) is configured to assign a confidence score to each of the detected spatiotemporal anomalies.
10. A processor-implemented method (300) for real-time management of low-incidence infectious disease outbreaks, the method (300) characterized by steps of:
acquiring multimodal data, via edge computing nodes (108), from heterogeneous data acquisition devices (102);
detecting spatiotemporal anomalies indicative of early outbreak signals using a spatiotemporal anomaly detection model trained for rare-event detection;
correlating the detected spatiotemporal anomalies with geo-behavioral and environmental drivers;
estimating, based on the correlated detected spatiotemporal anomalies, an outbreak likelihood, an extent of the outbreak, or a combination thereof; and
generating intervention recommendations using a decision-support engine (114).

Date: October 03, 2025
Place: Noida

Nainsi Rastogi
Patent Agent (IN/PA-2372)
Agent for the Applicant