Multi-modal imaging guided non-contact vital sign monitoring system and method

Abstract

The present disclosure relates to systems and methods for monitoring a patient in a clinical setup environment by using non-contact multi-modal imaging. For example, based on receiving imaging data, a computing device may identify an object and a region of interest formed by the object. The computing device may then cause a sensor to capture first sensor data at a first time instant and capture second sensor data at a second time instant, where the sensor data is associated with the region of interest. Based on determining that a difference between the first sensor data and the second sensor data is greater than or equal to a threshold difference, the computing device may generate an alert indicative of the second sensor data and send the alert indicative of the second sensor data to an additional computing device.

Description

Multimodal imaging-guided non-contact vital sign monitoring system and method

[0001] Related applications

[0002] This application claims priority to U.S. Provisional Application No. 63 / 541,638, filed September 29, 2023, the disclosure of which is incorporated herein by reference and used for all purposes. Technical Field

[0003] This application relates to systems and methods for monitoring patients in a nursing setting. Background Technology

[0004] As technology advances, medical facility equipment offers more functionality. For example, inpatient monitoring utilizes video surveillance to assist in providing patient care. In such cases, patients are typically monitored in medical settings such as intensive care units (ICUs) or surgical wards via fixed or mobile camera devices. The video feeds captured by these cameras can be analyzed to determine a wealth of patient statistics, such as bed ambulation, activity, and medication triage. In other examples, video feedback can be used to determine specific measurements associated with the patient, such as heart rate and respiratory rate. However, the reliability of using video imaging data to derive vital signs is much lower. Most analytical algorithms not only require the patient to remain stationary while the video is being analyzed, but external factors such as lighting and presentation often lead to inaccurate or incomplete results.

[0005] Various exemplary implementations of this disclosure relate to overcoming one or more defects associated with patient management systems. Summary of the Invention

[0006] As described above, video surveillance systems can be beneficial for patient monitoring in healthcare settings. For example, traditional healthcare settings rely on healthcare professionals such as nurses and doctors being physically present with patients to collect information. This information ranges from behavioral patterns (e.g., getting out of bed, falls, sleep, medication triage, activity, etc.) to physical measurements (e.g., heart rate, respiratory rate, blood oxygen saturation, etc.). This physical collection of information is very time-consuming and can be a burden for healthcare staff responsible for a large number of patients. Furthermore, because healthcare staff typically cannot monitor patients around the clock, measurements may sometimes be overlooked or even missed. Video surveillance systems themselves offer a solution.

[0007] Video surveillance systems have become increasingly well-known and commonly used in healthcare settings. Typically, patients are monitored via fixed or mobile cameras that send real-time video feeds to personnel and / or artificial intelligence (AI) systems for review. In the case of AI, the video feeds are typically fed into a classification engine that can alert healthcare staff when certain events are detected in the video feed, such as a patient falling. However, video surveillance systems are not limited to behavioral patterns—they can also be used to detect physical measurements.

[0008] However, current video surveillance systems are not without limitations. For example, existing video surveillance technologies require numerous factors to be in place to obtain accurate results. For instance, to detect physical measurements such as vital signs, the patient must remain stationary and within the full field of view of the camera, forcing the patient to remain confined to the "monitoring area." Furthermore, AI algorithms used to determine vital signs require immutable environmental factors such as lighting and camera angle. However, most clinical settings are dynamic and constantly changing, leading to information obstruction and adverse lighting, posture, orientation, and movement—all of which can prevent the imaging processing system from deriving reliable signals. The system and method described in this paper provide accurate entry and recording of data from a multimodal system when data reliability is determined based on collected multimodal sensor data about the patient. In this way, the system can reliably enter patient data into electronic medical records without human intervention, ensuring the accuracy and quality of the entered data, enabling healthcare professionals to use electronic medical records to determine treatment procedures.

[0009] Therefore, this application relates to systems and methods for monitoring patients in clinical setting environments using non-contact multimodal imaging. For example, care facilities such as clinics or hospital settings may include imaging devices and / or sensors. Imaging devices may include any device with imaging capabilities, such as visible camera devices; infrared camera devices; or red-green-blue (RGB) camera devices, to name just a few non-limiting examples. In some examples, imaging devices may include image-changing features such as translation, tilt, and zoom. Sensors may include any sensing device capable of determining one or more measurements associated with a patient. For example, sensors may be configured to monitor vital signs and may include, for example, millimeter (mm) wave sensors or light detection and ranging (LIDAR) sensors. It should be noted that although this application describes the use of a single imaging device and a single sensor, any number of imaging devices and / or sensors may be used herein.

[0010] In some examples, the imaging device and / or sensor can be coupled to a mobile platform, such as a pan-tilt unit. For example, the pan-tilt unit can be mechanically moved such that the imaging device and / or sensor can be positioned to obtain a complete and accurate image of the environment in which the imaging device and / or sensor are located. For example, the pan-tilt unit can be mechanically tilted vertically or horizontally such that the imaging device and / or sensor can obtain accurate data about all areas of the environment. The mobile platform can be configured to be guided in at least one of the x, y, or z directions within a care facility or other space.

[0011] In some aspects, the technology described herein relates to a method comprising: receiving first data from a first sensor located in a care facility, the first data being associated with the care facility and a patient within the care facility; and determining a region of interest within the care facility based at least in part on the first data and by providing the first data to a machine learning model, the machine learning model being trained using data labeled with location data associated with objects in space. The method further comprises: having a computing device in the care facility cause a second sensor located in the care facility to capture second data associated with the region of interest at a first moment; and determining a physiological parameter associated with the patient based at least in part on either the first or the second data. The method further comprises: determining a confidence score associated with the physiological parameter based at least in part on the second data and the first data; and recording the physiological parameter in association with an electronic medical record associated with the patient based at least in part on the confidence score. Attached Figure Description

[0012] Figure 1 shows a schematic block diagram of an example patient management system environment.

[0013] Figure 2 shows a top view of an example patient management system environment.

[0014] Figure 3 shows a schematic block diagram of an example process for providing alerts to clinician devices based on sensor data, indicating that a patient needs caregiver intervention.

[0015] Figure 4 illustrates an example process for issuing alerts to clinician devices that a patient may have fallen or is at risk of falling.

[0016] Figure 5 illustrates an example process for monitoring patient characteristics using infrared and RGB cameras based on lighting conditions in a patient's room.

[0017] Figure 6 illustrates an example process for monitoring patient characteristics and sending alerts to clinician devices based on sensor data, indicating that the patient requires nursing intervention.

[0018] Figure 7 shows example computing systems and devices that can be used to implement the described technology. Detailed Implementation

[0019] The systems and methods disclosed and envisioned herein relate to the monitoring of patient vital signs using non-contact multimodal imaging. Various embodiments of this disclosure will be described in detail with reference to the accompanying drawings, wherein the same reference numerals denote the same parts and components in several views. Additionally, any examples set forth in this specification are not intended to be limiting, but merely illustrate some of the many possible implementations.

[0020] Figure 1 illustrates a schematic block diagram of an example patient management system environment 100 for monitoring patient characteristics and issuing alerts to clinicians when patient characteristics exceed threshold ranges, indicating that the patient may require assistance or intervention. The example patient management system environment 100 includes an imaging device 102, a sensor 104, a clinician device 106, a patient management system 110, and a patient 108. The imaging device 102, sensor 104, clinician device 106, and / or patient management system 110 may communicate via one or more networks 112.

[0021] In some examples, imaging device 102 may include any device with imaging capabilities that enables imaging device 102 to locate objects in an environment such as a medical setting. For example, imaging device 102 may include a camera device, such as an infrared camera, an RGB camera, a thermal camera, or other such imaging devices, to name just a few non-limiting examples. In some examples, imaging device 102 may include a device capable of capturing still images. Additionally or alternatively, imaging device 102 may include a video camera device that may be capable of capturing a stream of imaging data for continuous monitoring. In some examples, imaging device 102 may be used to determine the location of objects located in a medical setting such as a hospital or clinic. Typically, the object to be located may be a patient, such as patient 108; therefore, imaging device 102 may be configured to determine the location of patient 108. However, in other examples, the object may include one or more items that are not patient 108 but are associated with patient 108 and indicate characteristics of patient 108. For example, this could include wearable devices 124 or medical devices associated with patient 108, such as wristbands, patches, heart rate monitors, blood pressure cuffs, or intravenous fluid (IV) bags.

[0022] In some examples, the example patient management system environment 100 may include at least one or more sensors, such as sensor 104. Sensor 104 may include any device capable of non-contact monitoring of patient 108 to determine one or more characteristics associated with patient 108. In some examples, sensor 104 may be used to determine characteristics associated with patient 108. For example, sensor 104 may be used to monitor one or more vital signs of patient 108, such as patient 108's respiratory rate or patient 108's heart rate. For example, to monitor patient 108's respiratory rate, an RGB camera device may be used. For example, an RGB camera device may detect the rise and fall of patient 108's chest over a period of time by analyzing pixel intensity changes via image processing techniques to generate a sinusoidal waveform indicating patient 108's breathing pattern. However, using an RGB camera device as a sensor is only one example, and any type of sensing device may be used. For example, the sensing device may include an imaging device, such as an IR camera device or an IR sensor. In other examples, the sensor may be a patient sensing device specifically designed to determine patient characteristics, such as a pulse rate sensor, blood oxygen saturation sensor, temperature sensor, or other such sensors, capable of measuring patient parameters and / or data. In some examples, the sensor may be located in the room adjacent to patient 108 and / or worn by patient 108. Various non-limiting examples of sensors are described herein.

[0023] In some examples, imaging device 102 and / or sensor 104 may be coupled to a gimbal or steerable structure, enabling imaging device 102 and / or sensor 104 to mechanically rotate about one or more axes (e.g., x, y, z), providing stability for imaging device 102 and / or sensor 104 while acquiring image and sensor data with fine control over the active area and / or field of view. Furthermore, in some examples, one or more axes of the gimbal may be locked, constraining imaging device 102 and / or sensor 104 to move in the direction of the axis. Thus, imaging device 102 and / or sensor 104 can acquire a 360-degree view of the environment. In some examples, the system's sensors may face the same direction and / or different directions in different embodiments. In some examples, different sensors in the system may each have a corresponding gimbal and / or steerable structure, allowing independent positioning of the sensors (e.g., with different fields of view) according to the control system's decision. In some examples, sensors may be connected to a gimbal and / or steerable structure, such that one sensor can act as a first-level sensor, while one or more other sensors follow its field of view as second-level sensors. For example, a first-level sensor, such as that of a camera device, can be guided to have a specific field of view, while a second-level sensor, such as that of a radar device, can be guided such that the active sensing area of ​​the radar device overlaps or coordinates with the field of view of the camera device. In some examples, the first-level and second-level sensors can overlap and / or be guided to the same area or field of view. In some examples, the first-level and second-level sensors can be guided to different fields of view to provide coverage of a wider area within the care facility, for example, such that the fields of view of the sensors partially overlap or do not overlap but are adjacent to each other.

[0024] In the examples, clinician device 106 may include computing devices such as mobile phones, tablets, laptops, desktop computers, etc., which can provide clinicians (e.g., doctors, nurses, technicians, pharmacists, dentists, etc.) with information about the health of patient 108. In some cases, clinician device 106 may be located within a medical facility, although scenarios where clinician device 106 is present and / or transported outside the medical facility are also considered, such as a doctor's mobile phone or a home desktop computer that the doctor might use when on call. In some examples, clinician device 106 may include processors, microprocessors, and / or other computing device components, as shown and described below.

[0025] Example patient management system environment 100 may include patient management system 110, which may consist of one or more server computing devices and may communicate with imaging device 102 and sensor 104 to respond to queries, receive data, respond to data, etc. Communication between patient management system 110, imaging device 102, sensor 104 and / or clinician device 106 occurs via network 112, wherein the communication may include imaging data, sensor data and / or patient data related to patient health. The server of patient management system 110 may act on these requests from imaging device 102, sensor 104 and / or clinician device 106 and determine one or more responses to these queries, and responses are returned to imaging device 102, sensor 104 and / or clinician device 106. The server of patient management system 110 may also include one or more processors, microprocessors or other computing devices, as discussed in more detail with reference to FIG7.

[0026] The patient management system 110 may include one or more database systems accessible by a server that stores different types of information. For example, the database may store correlations and algorithms for managing imaging data, signal data, and other patient data that will be shared between imaging device 102, sensor 104, and / or clinician device 106. The database may also include clinical data. The database may reside on the server of the patient management system 110 or on a separate computing device accessible by the patient management system 110.

[0027] Network 112 is typically any type of wireless network or other communication network known in the art. Examples of network 112 include the Internet, intranet, wide area network (WAN), local area network (LAN), virtual private network (VPN), cellular network connection, and connections established using protocols such as 802.11a, b, g, n, and / or ac. Alternatively or additionally, network 112 may include nanoscale networks, near field communication networks, body area networks (BAN), personal area networks (PAN), near area networks (NAN), campus-area networks (CAN), and / or inter-area networks (IAN).

[0028] In some examples, the patient management system 110, imaging device 102, sensor 104, and / or clinician device 106 may generate, store, and / or selectively share signals, imaging data, sensor data, and / or other patient data with each other to provide improved outcomes for patients and clinicians treating patients by accurately monitoring patient characteristics and alerting clinicians when changes in patient characteristics may indicate that the patient requires caregiver intervention.

[0029] For example, imaging device 102 may capture image data associated with a patient in a medical facility and send such image data to patient management system 110. In some examples, capturing image data may be in response to a request, such as from a clinician at patient management system 110, to identify and / or monitor characteristics associated with the patient. These characteristics may include any number of measurable indicators associated with the patient, such as vital signs (e.g., patient's body temperature, patient's pulse rate, patient's respiratory rate, patient's blood pressure, etc.), intake and output (e.g., fluid intake and fluid output, medication intake, etc.), or patient movement, to name just a few non-limiting examples. While some characteristics can be measured by directly monitoring the patient (e.g., respiratory rate), others can be measured by monitoring objects associated with the patient, such as catheters or IV bags. Thus, image data can represent objects, where the term "object" can refer not only directly to the patient but also to any object that may be associated with the patient and could indicate characteristics of the patient 108.

[0030] In some examples, the patient management system 110 can process image data to optimize the images. For instance, the patient management system 110 can input image data into its image optimization module 114, which can modify the image data to optimize it to the highest quality. For example, the image optimization module 114 can automatically evaluate and adjust the image data to improve its resolution, reformat it to the correct format, resize it to the correct dimensions, or compress it, to name just a few non-limiting examples. Therefore, by optimizing the image data, the patient management system 110 can obtain more accurate images, thereby more accurately identifying objects in the image data. Image optimization performed by the image optimization module 114 can include preprocessing, segmentation, and correction. During the preprocessing stage, input sensor data can be corrected for defective pixels using an input lookup table, and contrast expansion can be performed on the input sensor data using a dynamic range histogram method. Color correction can also be performed on the input sensor data based on global image data of the environment for white balance and other ambient lighting conditions. During the segmentation phase, image processing techniques and morphological operations are used to process the input image data to locate objects, people, structures, and other such items as regions within the preprocessed image data. During the segmentation phase, specific regions requiring special correction, such as areas illuminated by ultra-bright LEDs, fluorescent lighting, dark corners, and other such regions, can be identified and segmented. During the correction phase, the identified segments can be adjusted by reducing or increasing the dynamic range of the segment and / or by applying a custom color lookup table to refine the image data within that segment.

[0031] In some examples, the patient management system 110 can identify objects. For example, based on captured image data, the imaging device can send the image data to the object recognition component 116 of the patient management system 110. In some examples, the object recognition component 116 may include a machine learning model 118 trained to identify one or more objects in the image data. For example, the machine learning model 118 may include artificial neural networks, decision trees, regression algorithms, or other machine learning algorithms to identify one or more objects in the image data. The machine learning model 118 can be trained using training data that includes other image data containing one or more objects. Using the training data, the machine learning model 118 can be trained to detect and / or recognize objects within the image data. Furthermore, the machine learning model 118 can continue to train the machine learning model using image data previously input into the machine learning model, thereby improving the accuracy of the machine learning model.

[0032] The object recognition component 116 can also interact with the imaging device 102 to modify image data and improve the confidence of object detection. For example, focus and / or lighting settings, zoom, and other imaging features can be adjusted based on object detection. Similarly, if an object is partially visible, the imaging device 102 can be rotated or moved to translate or tilt toward it. If the target object is not visible in the image data, the imaging device 102 can be moved to search for the object within a room. In some examples, additional training data can be provided to the machine learning model 118 to provide labels for image data indicating partial and / or undetected objects. The machine learning model 118 can be used to determine the confidence and / or quality of image data for object detection. For example, the machine learning model 118 can be used to determine image quality and / or features and create additional image data (e.g., by controlling the imaging device 102 to improve image data and / or by detecting partial or missing objects).

[0033] Based on identifying an object within image data, the region of interest identification component 120 of the patient management system 110 can identify a region of interest formed by that object. The region of interest may include a “target” area where sensors can more accurately acquire sensor data associated with the object. For example, the region of interest for a sensor used to determine a patient’s respiratory rate may be the patient’s chest. Alternatively, the region of interest for determining a patient’s fluid output may be the patient’s catheter. In some examples, the region of interest identification component 120 may determine the region of interest in part based on a request to identify and / or monitor features associated with the patient. For example, based on receiving a request, the patient management system 110 may determine a region of interest associated with the object that may be associated with the request. Additionally or alternatively, in some examples, the region of interest identification component 120 may determine the region of interest based on detection by sensor 104. For example, the region of interest identification component 120 may determine the sensor data most likely captured by sensor 104. Based on the determination of the sensor data most likely captured by sensor 104, the patient management system 110 may determine the region of interest (ref focus) most likely associated with the sensor data. Furthermore, in some examples, multiple objects and / or multiple regions of interest may be identified. For example, the area of ​​interest used to determine a patient’s fluid input and output could be both the IV and the catheter associated with the patient.

[0034] Based on the identification of an area of ​​interest, the patient management system 110 can cause the sensor 104 to capture sensor data associated with that area. The sensor data can include any data received by the sensor 104 that is associated with an object. For example, this could include measurements of light, temperature, movement, pressure, speed, proximity, or humidity, to name just a few non-limiting examples. In some examples, the sensor 104 can capture sensor data at different times to determine characteristics associated with the patient. Continuing with the example above where the characteristic is the patient's respiratory rate, sensor data can be determined at different times to accurately determine the patient's respiratory rate. For example, the sensor 104 can capture first sensor data at a first time, where the first sensor data indicates the first rise and fall of the patient's chest. Then the sensor 104 can capture second sensor data at a second time, where the second sensor data may indicate the second rise and fall of the patient's chest. Based on determining the time period from the first time to the second time, the patient management system 110 can determine the patient's respiratory rate.

[0035] In some examples, the sensor 104 used may be determined based on image data. For example, the type of sensor used may be based at least in part on image data captured by imaging device 102 and / or sensor 104. Based on the captured image data, sensor 104 and the associated patient management system 110 may determine one or more environmental attributes associated with the location associated with imaging device 102. This may include factors such as light and temperature, to name just a few. Based on a request to determine characteristics associated with patient 108, patient management system 110 may determine one or more sensors that may be suitable based on environmental factors, such that sensor 104 can be optimized to collect sensor data in the corresponding environment in which sensor 104 is located.

[0036] In some examples, sensor data collected at multiple times can be used to determine whether a patient needs or may require caregiver intervention. For example, based on received first and second sensor data, the alarm component 122 of the patient management system 110 can determine the difference between the first and second sensor data. The alarm component 122 can compare the difference between the first and second sensor data. In some examples, the difference between the first and second sensor data can indicate normal fluctuations associated with a condition. For example, a slight change in a patient's respiratory rate may be normal and may not be a cause for concern. However, a larger change may indicate a change in the patient's condition that may require clinician intervention. For example, the alarm component 122 can determine that the difference between the first and second sensor data is greater than or equal to a threshold difference between the first and second sensor data. The threshold difference can be condition- and / or patient-specific, such that determining that the difference between the first and second sensor data is greater than or equal to the threshold difference can accurately indicate that the patient may need help or intervention. In some examples, the various thresholds described herein can be customizable and / or adjustable based on user input and / or prior patient data.

[0037] In some examples, based on determining that the threshold difference between the first sensor data and the second sensor data is greater than or equal to a threshold difference, the alarm component 122 can generate an alarm indicating the second sensor data. The alarm component 122 can then send the alarm, including the second sensor data, to the clinician device 106, thereby alerting the clinician that the patient may require intervention or assistance. For example, the alarm could automatically appear on the clinician device as a pop-up notification, informing the clinician that the patient may require help or intervention.

[0038] In some examples, first sensor data can be used to determine one or more patient physiological parameters, while second sensor data can be used to determine the confidence level of the first sensor data, such as for determining when to add the determined physiological parameter to the patient's electronic medical record. In an example, imaging device 102 can be used to determine the physiological parameter, and based on image features and / or the confidence level output by machine learning model 118, system 100 can determine to use sensor 104 to collect additional sensor data to determine whether to add the physiological parameter to the patient 108's electronic medical record. In some cases, sensor 104 can be used to determine the patient's location or movement or other data about the patient. In an illustrative example, respiratory rate or pulse rate can be determined based on data from imaging device 102. In this illustrative example, sensor 104 of a radar device can be used to determine the location of patient 108 and / or whether patient 108 is moving during the determination of respiratory rate or pulse rate. In the case of patient movement, the confidence level of the physiological parameter may decrease. When patient 108 remains stationary (and may have remained stationary for a threshold period of time), system 100 can increase the confidence level of the physiological parameter to reflect the patient's true state, and can determine whether to enter or record the physiological parameter into patient 108's electronic medical record based on the confidence score.

[0039] The following examples of the configuration and usage of the imaging device 102, sensor 104, and clinician device 106 are shown and described with reference to at least Figures 2 through 6.

[0040] Figure 2 shows a top view of an environment 200 for a patient management system. For example, environment 200 is shown as a hospital room housing patient 202. However, this application contemplates environment 200 as any medical setting where patients can be observed, such as an operating room, outpatient facility, or clinical laboratory, to name just a few non-limiting examples. Environment 200 may include imaging device 204 and sensor 206, similar to imaging device 102 and sensor 104 described above with reference to Figure 1. Environment 200 may additionally include clinician equipment 208, which may be the same as or similar to clinician equipment 106.

[0041] In some examples, imaging device 204 can acquire image data of environment 200. For example, as shown by dashed lines 210a and 210b, imaging device 204 can scan or capture images of environment 200. The imaging data can then be analyzed to identify one or more objects in the environment. As described above, an object can be one or more items that can be detected and captured by sensors to obtain sensor data indicating a condition associated with the patient. For example, although an object can be the patient, it can additionally or alternatively be an item associated with the patient. In the current illustration, the object includes an IV infusion bag, indicated by object 212.

[0042] Based on object identification, sensor 206 can acquire sensor data associated with object 212. For example, when imaging device 204 can acquire image data of environment 200, sensor 206 can use the imaging data acquired by imaging device 204 to acquire data for a portion of environment 200. By determining specific points for sensor 206 to acquire sensor data, the sensor is more likely to acquire accurate sensor data. For example, as shown by dashed lines 214a and 214b, sensor 206 can scan or capture images of object 212 within environment 200.

[0043] Figure 3 shows a schematic block diagram of a process 300 for providing an alert to a clinician device based on sensor data, indicating that a patient requires caregiver intervention. Process 300 may include the patient 202, imaging device 204, sensor 206, clinician device 208, and object 212 shown in Figure 2.

[0044] For example, at operation 302, imaging device 204 can capture image data. For example, imaging device 204 may be located in a medical facility such as a hospital room and may be configured to capture images of the environment in which imaging device 204 is located. Imaging device 204 may include any device capable of capturing one or more images of the environment in which it is located. For example, as shown in the present embodiment, imaging device 204 may be an RGB camera capable of detecting one or more objects in the environment. For example, imaging device 204 may be located in the room where patient 202 is located and may be configured to capture one or more images of that room. For example, the present embodiment shows imaging device 204 scanning the environment to capture image data via dashed lines 210a and 210b. In some examples, imaging device 204 may send image data to a patient management system (not shown) that may input the image data into a machine learning model trained to identify one or more objects in the image data. In the current illustration, the machine learning model detects patient 202 and an IV bag connected to patient 202 as objects. In some examples, the machine learning model may detect a single object comprising multiple items (e.g., patient and associated device). In other examples, machine learning models can detect multiple objects that may or may not be related to each other.

[0045] At operation 304, the patient management system can determine a region of interest associated with an object. In the current illustration, the patient management system detects object 212 (IV infusion bag) as a region of interest. A region of interest may include a “target” area where sensors can more accurately determine sensor data associated with the object. In some examples, the region of interest may be determined based on a request from a clinician to determine characteristics associated with patient 202. For example, a nurse may wish to monitor fluid input levels associated with patient 202 and may therefore enter a corresponding request into the patient management system. Based at least in part on this request, the patient management system can determine a region of interest associated with that request and / or image data. Continuing with the current illustration, the patient management system can determine that the region of interest is the IV infusion bag, based on image data containing the IV infusion bag connected to patient 202 and a request including monitoring the patient's fluid levels.

[0046] At operation 306, a sensor, such as sensor 206, can acquire sensor data associated with the area of ​​interest. Sensor 206 can be any sensing device that can be used to acquire sensor data associated with a patient. In the current illustration, sensor 206 may include a thermal imaging camera that can detect changes in fluid levels in an IV bag. For example, to monitor fluid input levels, sensor data can be acquired at different times, such as first sensor data at a first time and second sensor data at a second time. The sensor can send the first and second sensor data to a patient management system, which can compare the first and second sensor data to determine one or more changes in the sensor data. In some examples, the patient management system may have a list of pre-programmed threshold levels associated with various patient characteristics. In some examples, the threshold levels may be associated with a period of time. For example, this could include changes in the patient's vital signs over a short period of time (e.g., a rapid increase or decrease in heart rate). In some examples, based on determining that the difference between the first and second sensor data is greater than or equal to a threshold difference, the patient monitoring system can generate an alarm associated with the second sensor data. For example, continuing with the current illustration, the patient management system can determine that the change in the volume of fluid being ingested by patient 202 may be greater than the fluid threshold that patient 202 should ingest, which may be the reason for intervention.

[0047] At operation 308, the patient management system can send an alert to clinician device 208. The alert may include second sensor data, enabling the receiving clinician to understand the condition associated with patient 202. In some examples, the alert may include additional information such as other medical data associated with patient 202, the location of patient 202, the condition of patient 202, or the physician assigned to patient 202, to name just a few new examples. In this way, healthcare staff can easily and effectively monitor patients without being physically present or monitoring patient 202, and receive alerts when a condition may be detected.

[0048] In some examples, at operation 308, the system can decide whether to enroll or record the detected condition, location, physiological parameters, or other such data detected by the sensor. Imaging devices and sensors can be used to determine the data and the confidence level of the data to determine when to record the data in the patient's electronic medical record. This determination can be made by a machine learning model trained using multimodal sensor data labeled with confidence scores (e.g., a dataset including data from multiple types of sensors) and / or the determinations used to enroll or record, or ignore or discard readings.

[0049] Figure 4 illustrates a process 400 for issuing an alert to a clinician's device that a patient may have fallen or is at risk of falling. It should be noted that process 400 is merely an example process illustrating the techniques and methods described herein, which utilize one or more imaging devices and sensors to generate alerts associated with data captured by the sensors being greater than or equal to a threshold, thereby indicating that the patient may require clinical help or intervention. Therefore, while the current illustration describes the RGB imaging device as an imaging device and sensor, such as sensor 104, which may include any device capable of non-contact monitoring of the patient to determine one or more characteristics associated with the patient, any number and type of imaging devices and / or sensors may be used.

[0050] For example, at operation 402, the process includes receiving image data of the hospital room by an RGB camera device. For instance, a clinician or healthcare worker might want to monitor characteristics associated with a patient, such as patient movement. For example, the patient might be at risk of falling and might need to remain in a hospital bed. Instead of requiring the clinician to be physically present in the hospital room continuously monitoring the patient, the RGB camera device can be located in the patient's hospital room and configured to continuously monitor the patient's room by capturing video image data. The video data can be used to determine if the patient has moved, which will be described in detail below.

[0051] At operation 404, process 400 may include identifying a patient in a hospital room. For example, based on captured image data, an RGB camera device may send the image data to a patient monitoring system. The patient monitoring system may include a machine learning model that can be trained and / or configured to accurately identify objects and / or regions of interest associated with the image data.

[0052] At operation 406, process 400 may include identifying the patient's upper body as an area of ​​concern. For example, because the patient's position is being monitored, movement of the patient's upper body may indicate that the patient has moved from a desired position on the hospital bed and may require clinician intervention. Therefore, the patient's upper body can serve as a sufficiently important area of ​​concern for determining whether the patient has moved.

[0053] At operation 408, process 400 may include causing a non-contact patient monitoring sensor to capture sensor data associated with a first position of the patient in the hospital room at a first moment. For example, the first position of the patient at the first moment may serve as a reference position. In other words, the first position of the patient at the first moment may be the position in which the patient is placed in a hospital bed and is expected to remain. Similarly, at operation 410, the process may include causing the sensor to capture second sensor data associated with a second position of the patient in the hospital room at the same moment after the first moment.

[0054] At operation 412, the process may include determining that the difference between the first sensor data and the second sensor data is greater than or equal to a threshold difference. For example, based on the received sensor data, the patient management system may compare a first position and a second position to determine the difference in the patient's position. In some examples, the threshold difference may be associated with a characteristic of the patient being monitored. For example, in the current illustration, since the patient is being monitored to maintain their position in a hospital bed, the threshold difference may be a small distance (e.g., 5 inches, 6 inches, 1 foot, etc.). However, the threshold difference can be any unit of measurement corresponding to the sensor data and can include any range of differences.

[0055] Therefore, at operation 414 (indicated by "No" in operation 412), process 400 may include avoiding generating an alarm indicating a second location for the patient at a second moment, based on determining that the difference between the first sensor data and the second sensor data is less than a threshold difference. In other words, the patient management system can determine that the patient has remained in the same location, or that the patient has moved to a location insufficient to trigger an alarm for the clinician.

[0056] Therefore, at operation 414 (indicated by "No" in operation 412), process 400 may include avoiding generating an alarm indicating a second location for the patient at a second moment, based on determining that the difference between the first sensor data and the second sensor data is less than a threshold difference. In other words, the patient management system can determine that the patient has remained in the same location, or that the patient has moved to a location insufficient to trigger an alarm for the clinician.

[0057] Alternatively, based at least in part on determining that the difference between the first sensor data and the second sensor data is greater than or equal to a threshold difference, process 400 may include at operation 416 an alert generated by the patient management system indicating a second location of the patient at a second moment. For example, the patient may have moved a distance, making the patient now considered to be at risk and potentially requiring clinician intervention to assist the patient back to their hospital bed. Therefore, at operation 418, the process may include providing an alert to a clinician's device, enabling the clinician to check on the patient and provide assistance if necessary.

[0058] In some examples, at operation 412, process 400 may also include determining a confidence level for the first sensor data and / or the second sensor data and / or the difference. In some examples, the confidence level may be based on the patient's physiological parameters or location. If the confidence level is below a threshold, the system may attempt to collect additional sensor data using one or more sensors and / or improve the confidence score based on additional (e.g., second) sensor data. In some examples, instead of generating an alarm, the system may determine when to record and / or enter patient data and / or the difference between patient data, as discussed herein, based on the confidence score.

[0059] Figure 5 illustrates a process 500 for monitoring patient characteristics using infrared and RGB cameras based on the lighting scene within a patient's room. For example, at operation 502, process 500 may at least include receiving the light level of the hospital room via a light level sensor by a computing device (e.g., a patient management system). For example, the patient management system may receive sensor readings of ambient light within the room or absolute luminance read by a room sensor. At operation 504, process 500 may then include the computing device determining the light level of the hospital room. The light level may be determined as a measurement of the ambient lighting level within the room. In some examples, the light level may be on a scale, such as from one to one hundred, where the lower end of the scale is associated with a room without lighting, while the higher end is associated with a room where all light sources (such as bulbs and windows) provide full illumination. The light level may be determined based on detected luminous lumens or other similar measurements for light and / or luminance.

[0060] At operation 506, the computing device can determine whether the light level is greater than a threshold level. The threshold can be a set value, or it can vary based on other sensor data or information, such as being related to other factors that may affect the image acquisition technology.

[0061] At operation 508, if the computing device determines at 506 that the light level is below a threshold level, the computing device can cause the infrared camera to capture sensor data associated with movement of the patient's chest. In other examples, the infrared camera (or other invisible light camera) can be used to capture image data associated with other patient parameters, features, movement, and other such data.

[0062] At operation 510, if the computing device determines that the light level is above a threshold, the computing device can cause an RGB or other visible light imaging device to capture sensor data associated with movement of the patient's chest. In other examples, the visible light imaging device can be used to capture image data associated with other patient parameters, features, movement, and other such data.

[0063] Figure 6 illustrates a process 600 for monitoring patient characteristics to alert clinicians that a patient may require assistance or intervention based on the patient's characteristics exceeding a threshold range. For example, at operation 602, process 600 may at least include receiving image data captured by an imaging device located in the care facility by a computing device (also referred to herein as a "patient management system"). In some examples, the image data may at least partially represent an object. For example, the imaging device may be any device capable of capturing image data, such as an infrared camera, an RGB camera, a thermal camera, or a light-sensing camera, to name just a few non-limiting examples. In some examples, the imaging device may include a device capable of capturing still images. Additionally or alternatively, the imaging device may include a video camera capable of capturing a stream of imaging data for continuous monitoring.

[0064] At operation 604, process 600 may include determining the identification of objects by a computing device and using image data as input to a machine learning model. For example, the machine learning model may include artificial neural networks, decision trees, regression algorithms, or other machine learning algorithms to identify one or more objects in the image data. In some examples, the objects identified by the image data may be medical devices such as wristbands, heart rate monitors, blood pressure cuffs, or intravenous (IV) infusion bags, to name just a few non-limiting examples. Furthermore, the identified objects may represent patients, physiological symptoms (e.g., a patient's body temperature, a patient's pulse rate, a patient's respiratory rate, a patient's blood pressure, etc.) or intake and output (e.g., fluid intake and fluid output, drug intake, etc.), to name just a few non-limiting examples. Thus, image data can represent objects, where the term "object" can refer not only directly to a patient but also to any object that may be associated with a patient and may indicate patient characteristics.

[0065] At operation 606, process 600 may include identifying a region of interest formed by the object using a computing device and based on the identification of the object. The region of interest may include a “target” area where sensors can more accurately acquire sensor data associated with the object. For example, the region of interest for sensors used to determine a patient’s respiratory rate may be the patient’s chest. Alternatively, the region of interest for determining a patient’s fluid output may be the patient’s catheter. In some examples, the region of interest may be determined in part based on a request to determine and / or monitor characteristics associated with the patient. Additionally or alternatively, in some examples, the region of interest may be determined based on sensor detection. For example, the region of interest may determine the sensor data most likely to be captured by the sensor. Based on the determination of the sensor data most likely to be captured by the sensor, the computing device may determine the region of interest most likely associated with the sensor data. Furthermore, in some examples, multiple objects and / or multiple regions of interest may be identified. For example, the region of interest for determining a patient’s fluid input and output may be both an IV and a catheter associated with the patient.

[0066] At operation 608, process 600 may include a computing device causing sensors located in the care facility to capture first sensor data associated with an area of ​​concern at a first moment. Sensor data may include any data received by the sensors and associated with an object. For example, this may include measurements of light, temperature, movement, pressure, speed, proximity, or humidity, to name just a few non-limiting examples. In some examples, sensors may be determined based on image data. Based on captured image data, an imaging device may determine one or more environmental properties associated with the location of the imaging device, such as light and temperature, to name just a few examples. Based on a request to determine characteristics associated with a patient, a patient management system may determine one or more sensors that may be suitable based on environmental factors, such that the sensors can be optimized to collect sensor data from the appropriate environment in which they are located.

[0067] At operation 610, process 600 may include having a computing device cause a sensor to capture second sensor data associated with the region of interest at a second time, different from the first time. In some examples, the sensor may capture sensor data at different times to determine a characteristic associated with the patient. Continuing with the example above where the characteristic is the patient's respiratory rate, sensor data may be determined at different times to accurately determine the patient's respiratory rate. For example, the sensor may capture first sensor data at the first time, where the first sensor data indicates the first rise and fall of the patient's chest. The sensor may then capture second sensor data at the second time, where the second sensor data may indicate the second rise and fall of the patient's chest. Based on determining the time period from the first time to the second time, the patient management system 110 may determine the patient's respiratory rate.

[0068] At operation 612, process 600 may include determining that the difference between the first sensor data and the second sensor data is greater than a threshold difference. For example, based on the received first and second sensor data, an alarm component of the patient management system may determine the difference between the first and second sensor data. In some examples, the difference between the first and second sensor data may indicate normal fluctuations associated with a condition. For example, a slight change in a patient's respiratory rate may be normal and may not be a cause for concern. However, a larger change may indicate a change in the patient's condition that may require clinician intervention. Continuing with the example above where the feature is respiratory rate, the first and second sensor data indicate the first and second rises and falls of the patient's chest. The threshold difference may be condition- and / or patient-specific, such that determining that the difference between the first and second sensor data is greater than or equal to the threshold difference can accurately indicate that the patient may require help or intervention. A computing device may compare the first and second sensor data (i.e., the patient's respiratory rate) and determine that the respiratory rate is greater than the threshold difference / frequency. In some examples, depending on the determination of the computing device, the patient management system may or may not generate an alarm indicating that the difference is greater than a predetermined threshold.

[0069] Based on the determination that the difference between the first sensor data and the second sensor data is less than a threshold difference (e.g., "No" at operation 612), process 600 may include, at operation 614, avoiding the generation of an alarm indicating the second sensor data. Continuing with the example above where the feature is respiratory rate, the computing device may determine that the patient's respiratory rate is below a threshold respiratory rate, and therefore the patient management system will avoid generating an alarm.

[0070] Alternatively, based on determining that the difference between the first sensor data and the second sensor data is greater than or equal to a threshold difference in the sensor data (e.g., "yes" at operation 612), process 600 may include, at operation 616, the generation of an alarm by a computing device indicating the second sensor data. Continuing with the example above where the feature is respiratory rate, the first sensor data and the second sensor data indicate a first rise and a second rise in the patient's chest. The computing device may determine that the patient's respiratory rate is greater than or equal to a threshold difference in respiratory rate and may generate an alarm indicating that difference.

[0071] At operation 618, the process may include providing an alert from a computing device to an additional computing device associated with a caretaker station in the care facility. In some examples, sensor data collected at multiple times may be used to determine if a patient requires caregiver intervention. The threshold difference may be condition- and / or patient-specific, such that determining that the difference between the first and second sensor data is greater than or equal to the threshold difference can accurately indicate that the patient may require help or intervention. Continuing with the example above where the feature is respiratory rate, the patient management system may determine that the patient's respiratory rate is greater than or equal to a threshold difference in respiratory rate, and therefore may send an alert including the second sensor data to a clinician device. For example, the alert may automatically appear as a pop-up notification on the clinician device, informing the clinician that the patient may require help or intervention.

[0072] Example systems and devices

[0073] Figure 7 generally illustrates an example system at 700, which includes a computing device 702, representing one or more computing systems and / or devices that can implement the various technologies described herein. This is illustrated by including a patient management system 110. The computing device 702 can be, for example, a server of a service provider, a device associated with a client (e.g., a client device), a system-on-a-chip, and / or any other suitable computing device or computing system.

[0074] The computing device 702 shown includes a processing system 704, one or more computer-readable media 706, and one or more I / O interfaces 708, which are communicatively coupled to each other. Although not shown, the computing device 702 may also include a system bus or other data and command transmission systems that couple the various components to each other. The system bus may include any one or a combination of different bus architectures, such as a memory bus or memory controller, a peripheral bus, a universal serial bus, and / or a processor or local bus utilizing any of the various bus architectures. Various other examples, such as control and data lines, are also envisioned.

[0075] Processing system 704 represents the functionality of performing one or more operations using hardware. Therefore, processing system 704 is shown as including hardware elements 710, which can be configured as processors, function blocks, etc. This can include application-specific integrated circuits (ASICs) or other logic devices formed using one or more semiconductors. Hardware elements 710 are not limited by the materials forming them or the processing mechanisms employed therein. For example, a processor can consist of semiconductors and / or transistors (e.g., integrated circuits (ICs)). In such a context, processor-executable instructions can be electronically executable instructions.

[0076] Computer-readable medium 706 is shown as including memory / storage component 712. Memory / storage component 712 represents a memory / storage capacity associated with one or more computer-readable media. Memory / storage component 712 may include volatile media (such as random access memory (RAM)) and / or non-volatile media (such as read-only memory (ROM), flash memory, optical disk, magnetic disk, etc.). Memory / storage component 712 may include fixed media (e.g., RAM, ROM, fixed hard disk drive, etc.) and removable media (e.g., flash memory, removable hard disk drive, optical disk, etc.). Computer-readable medium 706 may be configured in various other ways, as further described below.

[0077] I / O interface 708 (input / output interface) represents a function that allows a user to input commands and information into computing device 702 and also allows information to be presented to the user and / or other components or devices using various input / output devices. Examples of input devices include keyboards, cursor control devices (e.g., mice), microphones, scanners, touch functionality (e.g., capacitive or other sensors configured to detect physical touch), camera devices (e.g., which may employ visible or invisible wavelengths, such as infrared frequencies, to recognize non-touch-involved movements as gestures), etc. Examples of output devices include display devices (e.g., monitors or projectors), speakers, printers, network interface cards, haptic-responsive devices, etc. Therefore, computing device 702 can be configured in various ways, as further described below, to support user interaction.

[0078] This document describes various technologies in the general context of software, hardware components, or program modules. Generally, such modules include routines, programs, objects, components, parts, data structures, etc., that perform specific tasks or implement specific abstract data types. The terms “module,” “function,” “logic,” and “part” used herein generally refer to software, firmware, hardware, or a combination thereof. The technologies described herein are characterized by platform independence, meaning that these technologies can be implemented on a wide range of commercial computing platforms with various processors.

[0079] Implementations of the described modules and technologies may be stored and / or transmitted via some form of computer-readable medium. Computer-readable medium may include a variety of media accessible by computing device 702. By way of example and not limitation, computer-readable medium may include "computer-readable storage medium" and "computer-readable transmission medium".

[0080] "Computer-readable storage medium" can refer to a medium and / or device capable of persistently and / or non-transitory storing information, as opposed to mere signal transmission, carrier waves, or signals themselves. Therefore, computer-readable storage medium refers to non-signal-bearing media. Computer-readable storage media include hardware, such as volatile and non-volatile, removable and non-removable media and / or storage devices implemented with methods or techniques suitable for storing information such as computer-readable instructions, data structures, program modules, logic elements / circuits, or other data. Examples of computer-readable storage media may include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical storage, hard disk, magnetic tape cassette, magnetic tape, disk storage or other magnetic storage devices, or other storage devices, tangible media, or articles of art suitable for storing desired information and accessible by a computer.

[0081] "Computer-readable transmission medium" can refer to a medium configured to transmit instructions, such as via a network, to the hardware of computing device 702. Computer-readable transmission media typically transmit computer-readable instructions, data structures, program modules, or other data in modulated data signals, such as carrier waves, data signals, or other transmission mechanisms. Computer-readable transmission media also include any information delivery medium. The term "modulated data signal" refers to a signal having one or more characteristics set or altered in a manner that encodes information in the signal. By way of example and not limitation, computer-readable transmission media include wired media, such as wired networks or direct wired connections, and wireless media, such as acoustic, radio frequency (RF), infrared, and other wireless media.

[0082] As previously described, hardware element 710 and computer-readable medium 706 represent modules, programmable device logic, and / or device logic that can be implemented in hardware form, and can be employed in some embodiments to implement at least some aspects of the techniques described herein, such as executing one or more instructions. The hardware may include components of an integrated circuit or system-on-a-chip, application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), complex programmable logic device (CPLD), and other implementations in silicon or other hardware. In this context, the hardware may operate as a processing device that executes program tasks defined by instructions and / or logic embodied in the hardware, and hardware utilized to store instructions to be executed, such as the computer-readable storage medium previously described.

[0083] The various techniques described herein can also be implemented using combinations of the foregoing. Therefore, software, hardware, or executable modules can be implemented as one or more instructions and / or logic embodied on some form of computer-readable storage medium and / or executed by one or more hardware elements 710. Computing device 702 can be configured to implement specific instructions and / or functions corresponding to the software and / or hardware modules. Therefore, the implementation of a module executable by computing device 702 as software can be at least partially implemented in hardware, for example, by using the computer-readable storage medium and / or hardware elements 710 of processing system 704. Instructions and / or functions can be executed / operated by one or more articles of art (e.g., one or more computing devices 702 and / or processing system 704) to implement the techniques, modules, and examples described herein.

[0084] The techniques described herein can be supported by various configurations of computing device 702, and are not limited to specific examples of the techniques described herein. This functionality can also be implemented, in whole or in part, using a distributed system, such as via platform 716 through a “cloud” 714 as described below.

[0085] Cloud 714 includes and / or represents platform 716 for resource 718. Platform 716 abstracts the underlying functionality of the hardware (e.g., server) and software resources of cloud 714. Resource 718 may include applications and / or data that can be utilized when computer processing is performed on a server remote from computing device 702. Resource 718 may also include services provided via the Internet and / or via subscriber networks such as cellular or Wi-Fi networks.

[0086] Platform 716 can abstract resources and functions to connect computing device 702 to other computing devices. Platform 716 can also be scalable to provide a level of scalability corresponding to the demands encountered by the resources 718 implemented via platform 716. Therefore, in an interconnected device implementation, the implementation of the functions described herein can be distributed across multiple devices of system 700. For example, the function can be implemented partly on computing device 702 and partly via platform 716, which can represent a cloud computing environment.

[0087] The exemplary systems and methods disclosed herein overcome various deficiencies of known prior art devices. Other embodiments of this disclosure will be apparent to those skilled in the art in light of the practice of this specification and the disclosure contained herein. The specification and examples are intended to be considered merely exemplary, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. A method, the method comprising: First data is received from a first sensor located in the care facility, the first data being associated with the care facility and the patients in the care facility; The area of ​​concern within the care facility is determined at least in part based on the first data and by providing the first data to a machine learning model, which is trained using location data labeled with objects in the space; a second sensor located in the care facility is enabled by the computing equipment of the care facility to capture second data associated with the area of ​​concern at a first moment; Physiological parameters associated with the patient are determined at least in part based on the first data or the second data; The confidence score associated with the physiological parameter is determined at least in part based on the second data and the first data; And the physiological parameters are recorded in association with electronic medical records associated with the patient, based at least in part on the confidence score.

2. The method according to claim 1, wherein, The first sensor includes an imaging device, and wherein the first data at least partially represents the object within the region of interest.

3. The method according to claim 1, wherein, The object is positioned at a location within the care facility, and the method further includes: determining environmental attributes of the location by the computing device and based on the first data; and selecting a second sensor from a plurality of sensors operatively connected to the computing device by the computing device and based on the environmental attributes.

4. The method according to claim 1, wherein, The first data and the second data are characterized by one or more metrics, and the method further includes: receiving a request from the computing device to determine the one or more metrics; and selecting the second sensor from a plurality of sensors operatively connected to the computing device based on the request.

5. The method according to claim 1, wherein, The first data includes image data, and the method further includes changing the image data to change at least one of the following: the resolution of the image data; the size of the image data; the brightness of the image data; or the contrast of the image data.

6. The method according to claim 1, wherein, The first sensor or the second sensor includes at least one of the following: an RBG camera device; a thermal imaging camera device; a directional microphone; a LIDAR camera device; a radar sensor; a proximity sensor; a weight sensor; or a physiological parameter sensor.

7. The method according to claim 1, wherein, At least one of the first sensor and the second sensor is coupled to a movable platform capable of orientation in at least one of the x-axis, y-axis, or z-axis.

8. The method according to claim 7, wherein, The first data includes image data of consecutive frames captured over a period of time, and wherein the mobile platform is configured to cause the first sensor to follow the patient within the care facility.

9. The method according to claim 1, wherein, The first sensor includes a first sensor type, and the second sensor includes a second sensor type, which is different from the first sensor type.

10. A system comprising: A first sensor, located in the care facility, comprising a first sensor type; A second sensor, located within the care facility, comprising a second sensor type; and one or more processors communicatively coupled to the first and second sensors. And a non-transitory computer-readable medium storing instructions that, when executed by the one or more processors, cause the one or more processors to perform actions, the actions including: receiving first data associated with the care facility and a patient in the care facility from a first sensor; determining an area of ​​concern within the care facility based at least in part on the first data and by providing the first data to a machine learning model trained using location data labeled with objects in space; causing a second sensor to capture second data associated with the area of ​​concern at a first moment; determining a physiological parameter associated with the patient based at least in part on the first data or the second data; determining a confidence score associated with the physiological parameter based at least in part on the first data and the second data; and recording the physiological parameter in association with an electronic medical record associated with the patient based at least in part on the confidence score.

11. The system according to claim 10, wherein, The object is positioned at a location within the care facility, and the action further includes: determining environmental attributes of the location based on the first data; and selecting a second sensor from a plurality of sensors operatively connected to the one or more processors based on the environmental attributes.

12. The system according to claim 10, wherein, The first data and the second data are characterized by one or more metrics, and the action further includes: receiving a request to determine the one or more metrics; and, based on the request, selecting the second sensor from a plurality of sensors operatively connected to a computing device of the care facility.

13. The system according to claim 10, wherein, The first data includes image data, and the action further includes changing the image data to change at least one of the following: the resolution of the image data; the size of the image data; the brightness of the image data; or the contrast of the image data.

14. The system according to claim 10, wherein, The first sensor includes at least one of the following: an RBG camera device; a thermal imaging camera device; a directional microphone; a LIDAR camera device; or a radar sensor.

15. The system according to claim 10, wherein, The second sensor includes at least one of the following: an RBG camera device; a thermal imaging camera device; a LIDAR camera device; a radar sensor; a proximity sensor; a weight sensor; or a physiological parameter sensor.

16. The system according to claim 10, wherein, At least one of the first sensor and the second sensor is coupled to a movable platform capable of orientation in at least one of the x-axis, y-axis, or z-axis.

17. One or more computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations, the operations including: First data associated with the nursing facility and the patients in the nursing facility is received from a first sensor located in the nursing facility; The area of ​​concern within the care facility is determined at least in part based on the first data and by providing the first data to a machine learning model, which is trained using location data labeled with objects in the space; a second sensor located in the care facility is enabled by the computing equipment of the care facility to capture second data associated with the area of ​​concern at a first moment; Physiological parameters associated with the patient are determined at least in part based on the second data; The confidence score associated with the physiological parameter is determined at least in part based on the second data and the first data; And the physiological parameters are recorded in association with electronic medical records associated with the patient, based at least in part on the confidence score.

18. One or more computer-readable media according to claim 17, wherein, The object is positioned at a location within the care facility, and the operation further includes: determining environmental attributes of the location by the computing device and based on the first data; and selecting a second sensor from a plurality of sensors operatively connected to the computing device by the computing device and based on the environmental attributes.

19. One or more computer-readable media according to claim 17, wherein, The first data and the second data are characterized by one or more metrics, and the operation further includes: receiving a request from the computing device to determine the one or more metrics; and selecting the second sensor from a plurality of sensors operatively connected to the computing device based on the request.

20. One or more computer-readable media according to claim 17, wherein, At least one of the first sensor or the second sensor is coupled to a movable platform capable of orientation in at least one of the x-axis, y-axis, or z-axis, and wherein the first data includes image data of consecutive frames captured over a period of time, and wherein the movable platform is configured to allow the first sensor to follow the patient within the care facility.

Images