Virtual Assistant / Chatbot to Improve Clinical Workflow for Home Renal Replacement Therapy

Abstract

A virtual assistant / chatbot for improving clinical workflow in home renal replacement therapy is disclosed herein. The virtual assistant / chatbot includes a patient-facing user interface configured to allow a patient to engage in a virtual chat session by typing, speaking, or otherwise providing information regarding a patient's request or problem related to renal replacement therapy. The virtual assistant / chatbot also includes a back-end server-based system configured to provide logic for responding to the patient's request. The logic defines a sequence of questions and answers for resolving the patient's inquiry. The sequence of assistant / chatbot questions and patient answers can be configured in a node arrangement such that a particular patient answer / request results in a further question for further information from the patient.

Description

[Background technology]

[0001] Some dialysis therapies (e.g., renal replacement therapy) can be self-administered by patients at home. Dialysis therapies can include automated peritoneal dialysis ("APD"), continuous ambulatory peritoneal dialysis ("CAPD"), and hemodialysis ("HD"). For these self-administered therapies, a visiting nurse typically trains the patient to administer the therapy themselves. The visiting nurse is also responsible for responding to patient inquiries and other unscheduled interactions that fall outside of regularly scheduled clinic visits. For example, a new patient may call the nurse if they have questions about administering the therapy, such as how to order a particular component (such as a dialysis fluid bag or disposable cassette and transfer set) or how to respond to a particular alarm on the dialysis machine. In addition to these non-urgent inquiries, in some cases, patients may call the nurse with more urgent issues, such as when they are experiencing complications or symptoms of peritonitis. Although certain tools exist to answer many inquiries, such as searchable online databases, the most comfortable way for patients, many of whom are elderly, is to interact with a nurse using the telephone. Because dialysis therapy is performed daily, visiting nurses must respond promptly to even non-urgent requests to ensure that these issues and inquiries do not delay the patient's dialysis therapy.

[0002] There are two extremes of dialysis patients' behavior when it comes to interacting with visiting nurses. At one extreme, patients do not want to bother nurses even regarding relatively serious conditions. These types of patients may neglect urgent issues such as peritonitis for a long time before escalating the issue with a nurse. This can lead to rare but serious complications if the problem is not self-identified early. At the other extreme, certain patients call their nurses excessively, multiple times a week. In these cases, patients may not have the confidence to perform the therapy and sometimes simply want more psychosocial support.

[0003] Typically, during the day, nurses are tasked with training new patients and interacting with patients at the clinic. In some cases, unscheduled calls from home dialysis patients may interrupt the nurse's workflow or scheduled tasks. In other cases, visiting nurses may not be able to answer patient calls directly when home patients call. Some clinics have administrative assistants to answer patient inquiry calls, but these assistants are not medically trained and are not always available. In smaller dialysis clinics, a nurse may work in other care areas, which means it may take hours or days before they are available to respond to patient calls and requests. Most clinics have a nurse's phone line connected directly to voicemail, whereby the nurse answers these voicemails after "normal" business hours.

[0004] Unfortunately for schedulers, nurses spend a significant amount of time responding to unscheduled patient interactions. First, unscheduled interactions require time for the nurse to determine the urgency of the interaction. The nurse must then spend time to follow up, even for a brief answer to a question, or to inform the patient that their request has been received. The total time responding to unscheduled patient interactions can be up to 10 hours / week.

[0005] Therefore, there is a need for a system that offloads at least a portion of the unscheduled interactions with home dialysis patients. Summary of the Invention [Means for solving the problem]

[0006] A virtual assistant / chatbot for improving clinical workflow in home renal replacement therapy is disclosed herein. The virtual assistant / chatbot includes a patient-facing user interface that may be provided by a dialysis machine or an application (e.g., an app) on a smartphone or tablet. The patient-facing user interface is configured to allow a patient to engage in a virtual chat session by typing, speaking, or otherwise providing information about a patient request or problem related to renal replacement therapy or dialysis therapy. The virtual assistant / chatbot also includes a back-end server-based system configured to provide logic for responding to a patient request. The logic may be defined by instructions stored in a memory device or data structure that defines a logical sequence of questions and answers to resolve a patient inquiry. The sequence of assistant / chatbot questions and patient answers may be configured in a node arrangement such that a particular patient answer / request results in a further assistant / chatbot question for further information from the patient. However, rather than relying on answers from the patient for all Assistant / Chatbot questions, at least some of the Assistant / Chatbot questions may be determined automatically (or at least partially automatically) using medical device data from a medical device (e.g., a dialysis machine) or contained within the patient's electronic medical record.

[0007] The logic described herein is configured to categorize, prioritize, and / or escalate patient requests to better manage the workload of nurses and other dialysis clinicians. For example, the virtual assistant / chatbot logic described herein is configured to automatically respond to a patient inquiry or to determine whether the patient inquiry should be routed to a primary clinician for more detailed medical follow-up. The virtual assistant / chatbot logic described herein is also configured to determine whether the patient inquiry should be routed to a voice mailbox, virtual message box, email inbox, and / or nurse answering service (e.g., visiting nurse) for low priority issues, or instead connected directly to a nurse for more urgent medical emergencies. The virtual assistant / chatbot logic described herein is also configured to determine whether the patient inquiry should be routed to the manufacturer of the dialysis machine (or other medical device) to resolve technical issues, re-raise an alarm, or re-order dialysis consumables such as dialysis fluid bags.

[0008] The exemplary virtual assistant / chatbot logic is configured to reduce direct interactions between patients and nurses regarding relatively simple issues. Additionally, the virtual assistant / chatbot logic is configured to triage incoming patient interactions to appropriate communication paths to ensure that only critical emergencies are immediately brought to the attention of clinicians and nurses. Thus, the exemplary virtual assistant / chatbot logic provides an automated system that increases patient engagement with dialysis treatments, thereby providing better clinical outcomes.

[0009] Patients who do not want to bother nurses may use the virtual assistant / chatbot more than previous interactions, knowing that they are not being disruptive. Nurses or clinicians may interact with these patients periodically as needed, but the virtual assistant / chatbot logic identifies more urgent requests and allows nurses to schedule less urgent discussions at times that fit within their schedule and are convenient for the patient. Thus, the virtual assistant / chatbot logic helps improve patient adherence to dialysis treatments while improving the chances that more severe medical conditions, such as peritonitis or catheter displacement, will be resolved sooner.

[0010] Additionally, for patients who initiate more request interactions, the virtual assistant / chatbot logic provides screens to ensure that a particular patient inquiry is routed to the most appropriate source or communication medium. This configuration ensures that a single patient does not routinely disrupt a nurse's schedule, instead only calling the nurse's attention for more serious issues. Additionally, because these patients may expect more direct interaction, the virtual assistant / chatbot captures enough information during the initial patient communication to allow the nurse or other clinician to appropriately respond with the needed information.

[0011] Overall, the virtual assistant / chatbot logic described herein can reduce clinician confusion by as much as 80%. Although clinicians may still have to respond to 50%-75% of patient inquiries, these inquiries are queued in a communication system that allows clinicians to respond as their schedule or workflow permits. Over the course of a year, the exemplary virtual assistant / chatbot logic can save over 200 hours of clinician time in dealing with non-critical disruptions.

[0012] The exemplary virtual assistant / chatbot logic and methodology of the present disclosure are applicable to fluid delivery for, for example, plasma ferris, hemodialysis ("HD"), hemofiltration ("HF") hemodiafiltration ("HDF") and continuous renal replacement therapy ("CRRT") therapies. The medical fluid data transfer system described herein is also applicable to peritoneal dialysis ("PD"), intravenous drug delivery, and nutritional fluid delivery. These modalities may be referred to herein collectively or generally individually as medical fluid delivery or therapy.

[0013] The above modalities may be provided by a medical fluid delivery machine that houses the necessary components to deliver medical fluids, such as one or more pumps, valves, heaters (if required), on-line medical fluid generating equipment (if required), sensors such as any one or more or all of pressure sensors, conductivity sensors, temperature sensors, air detectors, blood leak detectors, etc., a user interface, and a control unit that may control the above equipment using one or more processors and memories. The medical fluid delivery machine may also include one or more filters, such as a dialyzer or hemofilter for cleaning blood and / or an ultrafilter for purifying water, dialysis fluid, or other fluids.

[0014] The medical fluid delivery machine and medical fluid data transfer system and methodology described herein may be used with home machines. For example, the system may be used with a home HD, HF, or HDF machine operated at the patient's convenience. One such home system is described in commonly assigned U.S. Patent No. 8,029,454, issued October 4, 2011, entitled "High Convection Home Hemodialysis / Hemofiltration And Sorbent System" (the "'454 Patent"), filed November 4, 2004. Another such home system is described in commonly assigned U.S. Patent No. 8,393,690, issued March 12, 2013, entitled "Enclosure for a Portable Hemodialysis System" (the "'690 Patent"), filed August 27, 2008. The entire contents of each of the above references are incorporated herein by reference.

[0015] As described in more detail below, the exemplary virtual assistant / chatbot logic and methodology of the present disclosure may operate within a comprehensive platform or system that may include many different types of devices, patients, clinicians, physicians, service personnel, electronic medical record ("EMR") databases, websites, resource planning systems that process data generated through patient and clinician communications, and many machines equipped with business intelligence. The exemplary virtual assistant / chatbot logic and methodology of the present disclosure operates seamlessly within the entire system without violating its rules and protocols.

[0016] In a first aspect of the present disclosure, which does not limit the present disclosure in any way in light of the disclosure herein, but may be combined with any other aspect enumerated herein unless otherwise specified, a virtual assistant / chatbot system for improving clinical workflow in home renal replacement therapy includes an interface communicatively coupled to a network. The interface is configured to communicate with an interface for an application or medical device on a user device. The system also includes a memory device storing a patient inquiry triage data structure for the virtual assistant or chatbot. The data structure includes a plurality of potential problems related to the operation of the dialysis or medical device, each problem including a hierarchy of questions and possible answers that lead to a response action. The response action includes a direct communication connection with a clinician, and a communication connection with a voicemail system, a person-to-person chat system, or an email system. The system further includes a processor communicatively coupled to the interface and the memory device. The processor is configured to receive a query message from an application on the user device or an interface of the medical device, and provide an interactive session using the virtual assistant or chatbot to progress through the hierarchy of questions with one or more prompts to receive further information until a response action is identified. If the response action is related to direct communication, the processor is configured to determine an address or number of the clinician device and to initiate a communication session between the application on the user device or the interface of the medical device and the clinician device. If the response action is related to a voicemail system, a person-to-person chat system, or the email system, the processor is configured to determine an account for the clinician and to enable the patient to send a request message for the clinician using the application on the user device or the interface of the medical device.

[0017] According to a second aspect of the present disclosure, which may be used in combination with any other aspect recited herein unless otherwise specified, the processor is further configured to combine at least a portion of the further information from the interactive session with a request message for the clinician.

[0018] According to a third aspect of the present disclosure, which may be used in combination with any other aspect recited herein unless otherwise specified, the processor, the memory device, and the interface are located in a cloud computing environment.

[0019] According to a fourth aspect of the present disclosure, which may be used in combination with any other aspect recited in this specification unless otherwise specified, the query message and the further information are received as an utterance, and the processor is configured to convert the utterance into text.

[0020] According to a fifth aspect of the present disclosure, which may be used in combination with any other aspect described herein unless otherwise specified, the processor is further configured to receive a clinician response message from the clinician's account for a voicemail system, a person-to-person chat system, or an email system, and send the clinician response message to an application on the user device or an interface of the medical device.

[0021] According to a sixth aspect of the present disclosure, which may be used in combination with any other aspect enumerated herein unless otherwise specified, the response action further includes an automatic response action, and if the response action is associated with an automatic response action, the processor is configured to send information indicating the automatic response action to an application on the user device or an interface of the medical device.

[0022] According to a seventh aspect of the present disclosure, which may be used in combination with any other aspects enumerated herein unless otherwise specified, the automated response actions include at least one of answers from a patient guide, answers regarding orders for medical device consumables, answers regarding the operation of the medical device, or pre-programmed answers regarding general patient health or medical conditions.

[0023] According to an eighth aspect of the present disclosure, which may be used in combination with any other aspect enumerated herein unless otherwise specified, the response action further includes a medical device manufacturer response action, and if the response action is associated with a medical device manufacturer response action, the processor is configured to determine an address or number of the manufacturer device and cause a communication session to be initiated between an application on the user device or an interface of the medical device and the manufacturer device.

[0024] According to a ninth aspect of the present disclosure, which may be used in combination with any other aspects recited herein unless otherwise specified, the medical device manufacturer response action is related to at least one of reordering consumables for the medical device, a technical issue with the medical device, or an operational issue with the medical device.

[0025] According to a tenth aspect of the present disclosure, which may be used in combination with any other aspect recited herein unless otherwise specified, the medical device includes at least one of a peritoneal dialysis machine, a hemodialysis machine, a continuous renal replacement therapy ("CRRT") machine, an infusion pump, or a patient-controlled analgesia ("PCA") machine.

[0026] According to an eleventh aspect of the present disclosure, which may be used in combination with any other aspects enumerated herein unless otherwise specified, the processor is further configured, after receiving the query message, to access at least one of treatment data from the medical device or patient data associated with the patient from the electronic medical record, and use at least a portion of the treatment data or patient data as an answer to progress through a hierarchy of questions as part of the interactive session.

[0027] According to a twelfth aspect of the present disclosure, which may be used in combination with any other aspect described herein unless otherwise specified, the processor is further configured to, after receiving the query message, access at least one of treatment data from the medical device or patient data associated with the patient from the electronic medical record, and include at least a portion of the treatment data or patient data together with a request message for the clinician.

[0028] According to a thirteenth aspect of the present disclosure, which may be used in combination with any other aspect described herein unless otherwise specified, the treatment data includes at least one of (i) treatment parameters for a dialysis prescription, (ii) results from performing one or more dialysis treatments, (iii) diagnostic information related to a medical device, or (iv) a current status of a medical device, and the patient data includes at least one of electronic medical record information, laboratory results, electronic clinician notes, previous medical diagnoses, patient physiological data, or patient demographic data.

[0029] According to a fourteenth aspect of the present disclosure, which may be used in combination with any other aspect recited herein unless otherwise specified, the hierarchy of the patient inquiry triage data structure is configured to be modified based on the protocols of a hospital system or clinic.

[0030] According to a fifteenth aspect of the present disclosure, which may be used in combination with any other aspect enumerated herein unless otherwise specified, a virtual assistant / chatbot method for improving clinical workflow in home renal replacement therapy includes, in a processor, receiving an inquiry message from an application or an interface of a medical device on a user device, and, via the processor, providing an interactive session using the virtual assistant or chatbot to progress through a hierarchy of questions with one or more prompts to receive further information until a response action is identified, where instructions for the virtual assistant or chatbot are stored in a memory device that also stores a patient inquiry triage data structure for the virtual assistant or chatbot. The data structure includes a plurality of potential problems related to dialysis or medical device operation, each problem including a hierarchy of questions and possible answers that lead to a response action. The response action includes a direct communication connection with a clinician, and a communication connection with a voicemail system, a person-to-person chat system, or an email system. The method also includes, if the response action is related to direct communication, determining, via the processor, an address or number of the clinician device and causing a communication session to be initiated between the application or interface of the medical device on the user device and the clinician device. The method further includes determining a clinician account if the response action is associated with a voicemail system, a person-to-person chat system, or an email system, and enabling the patient to enter a request message for the clinician using an application on the user device or an interface of the medical device.

[0031] According to a sixteenth aspect of the present disclosure, which may be used in combination with any other aspect enumerated herein unless otherwise specified, the method further includes combining, via the processor, at least a portion of the further information from the interactive session with a request message for the clinician.

[0032] According to a seventeenth aspect of the present disclosure, which may be used in combination with any other aspect recited in this specification unless otherwise specified, the query message and further information are received as an utterance, and the method includes converting the utterance to text.

[0033] According to an eighteenth aspect of the present disclosure, which may be used in combination with any other aspect described herein unless otherwise specified, the method further includes receiving, in the processor, a clinician response message from a clinician's account for a voicemail system, a person-to-person chat system, or an email system, and sending, via the processor, the clinician response message to an application on the user device or an interface of the medical device.

[0034] According to a nineteenth aspect of the present disclosure, which may be used in combination with any other aspect enumerated herein unless otherwise specified, the response action further includes an automatic response action, and if the response action is associated with an automatic response action, the method further includes sending information indicating the automatic response action to an application on the user device or an interface of the medical device.

[0035] According to a twentieth aspect of the present disclosure, which may be used in combination with any other aspects enumerated herein unless otherwise specified, the automated response actions include at least one of answers from a patient guide, answers regarding orders for medical device consumables, answers regarding the operation of the medical device, or pre-programmed answers regarding general patient health or medical conditions.

[0036] According to a twenty-first aspect of the present disclosure, which may be used in combination with any other aspect described herein unless otherwise specified, the method further includes, after receiving the query message via the processor, accessing at least one of treatment data from the medical device, a prescribed therapy or program, or patient data related to the patient from an electronic medical record, and including, via the processor, at least a portion of the medical device data, the prescribed therapy or program, or medical information together with a request message for a clinician, wherein the prescribed therapy or program includes treatment parameters for a dialysis prescription, the treatment data includes at least one of (i) results from performing one or more dialysis treatments, (ii) diagnostic information related to the medical device, or (iii) a current status of the medical device, and the patient data includes at least one of electronic medical record information, test results, electronic clinician notes, previous medical diagnoses, patient physiological data, or patient demographic data.

[0037] In a twenty-second aspect of the present disclosure, any of the structures, functions, and alternatives disclosed in association with any one or more of Figures 1-6 may be combined with any other of the structures, functions, and alternatives disclosed in association with any other one or more of Figures 1-6.

[0038] Therefore, in light of the present disclosure and the above aspects, an advantage of the present disclosure is a system for automatically triaging patient healthcare related requests using virtual assistant / chatbot logic.

[0039] Another advantage of the present disclosure is that it uses information provided by the patient during an interactive session with the virtual assistant / chatbot logic to determine whether their inquiry is less urgent, semi-urgent, or critically urgent and provides appropriate response actions based on the urgency.

[0040] A further advantage of the present disclosure is the use of patient and / or treatment data to more quickly converge response actions to patient queries.

[0041] A further advantage of the present disclosure is the use of patient and / or treatment data as part of the content for response actions to patient queries.

[0042] Further features and advantages are described in and will be apparent from the following detailed description and figures. The features and advantages described herein are not all-inclusive, and many further features and advantages will be apparent to those skilled in the art in view of the drawings and description. Also, it is not necessary for any particular embodiment to have all the advantages described herein, and it is expressly contemplated that each advantageous embodiment may be separately claimed. Furthermore, it should be noted that the language used in this specification has been selected primarily for ease of reading and description purposes, and is not intended to limit the scope of the subject matter of the present invention. [Brief description of the drawings]

[0043] [Figure 1] FIG. 1 is a schematic diagram illustrating a medical system including at least one medical fluid delivery machine according to an embodiment of the present disclosure.

[0044] [Diagram 2] FIG. 2 is a schematic diagram of the medical system of FIG. 1 including a clinician server according to one embodiment of the present disclosure.

[0045] [Diagram 3] FIG. 2 is a diagram of a clinician server according to an example embodiment of the present disclosure.

[0046] [Figure 4] FIG. 1 is a diagram of a process performed by a virtual assistant / chatbot logic to triage a patient inquiry according to an example embodiment of the present disclosure.

[0047] [Diagram 5] FIG. 2 illustrates an interface of an application provided on a personal mobile communication device according to an example embodiment of the present disclosure.

[0048] [Figure 6] FIG. 13 is a diagram of a dashboard provided by a clinician application for responding to responsive actions according to an example embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0049] A virtual assistant / chatbot for improving clinical workflow in home renal replacement therapy is disclosed herein. The virtual assistant / chatbot is configured to provide automated triage of incoming patient requests to determine when a response can be provided in an automated manner and when a response from a clinician or medical device manufacturer is required. The virtual assistant / chatbot ensures that patient requests are addressed promptly while reducing the direct burden on clinical staff. The virtual assistant / chatbot is configured to accordingly improve patient engagement and treatment compliance by ensuring that patient requests are handled in the most efficient and timely manner possible.

[0050] As described herein, the virtual assistant / chatbot includes a patient-facing user interface that may be provided by a dialysis machine or an application (e.g., an app) on a smartphone or tablet. The patient-facing user interface is configured to allow a patient to engage in a virtual chat session by typing, speaking, or otherwise providing information regarding questions or issues related to renal replacement or dialysis therapy. The virtual assistant / chatbot also includes a back-end server-based system configured to provide logic for responding to patient requests. The logic may be defined by instructions stored in a memory device or a data structure that defines a logical sequence of questions and answers to resolve a patient inquiry.

[0051] Reference is made herein to a prescribed therapy or program and a corresponding therapy. A prescribed therapy or program corresponds to one or more parameters that define how the medical fluid delivery machine operates to administer a therapy to a patient. For peritoneal dialysis therapy, the parameters may specify the amount (or rate) of fresh dialysis fluid to be pumped into the patient's peritoneal cavity, the time the fluid should remain in the patient's peritoneal cavity (i.e., dwell time), and the amount (or rate) of spent dialysis fluid and ultrafiltration ("UF") to be pumped or drained from the patient after the dwell period ends. For multiple cycle therapy, the parameters may specify the fill, dwell, and drain volumes for each cycle, and the total number of cycles to be performed during the course of a therapy (one therapy provided per day, or separate therapy provided during the day and night). Additionally, the parameters (or device program) may specify the date / time / day (e.g., schedule) on which the therapy should be administered by the medical fluid delivery machine. Additionally, the parameters of the prescribed therapy may specify the total amount of dialysis fluid to be administered for each treatment, as well as the concentration level of the dialysis fluid, such as the dextrose concentration.

[0052] The prescribed therapy may specify parameters for each therapy provided by the medical fluid delivery machine, but the therapy data reported by the machine may differ. As discussed herein, therapy data refers to data generated by the medical fluid delivery machine indicative of measured, detected, or determined parameter values. For example, the prescribed therapy may specify that the therapy should comprise five separate cycles, each with a 45 minute dwell time, but the medical fluid delivery machine may administer the therapy in which fewer cycles are provided, each with a 30 minute dwell time. Differences from the prescribed parameters may be due to the patient ignoring the therapy program or prematurely stopping the therapy. The medical fluid delivery machine monitors how the therapy is being administered and provides parameters indicative of operation accordingly. Parameters for therapy data may include, for example, the total amount of dialysis fluid administered to the patient, the number of cycles administered, the fill volume per cycle, the dwell time per cycle, the drain time / volume per cycle, the estimated amount of UF removed, the therapy start time / date, and / or the therapy end time / date. Therapy data may also include calculated parameters such as fill and drain rates (which are determined by dividing the volume of fluid pumped by the time spent pumping). Therapy data may further include an identification of any alarms that occurred during treatment, the duration of the alarm, the time of the alarm, the event associated with the alarm, and / or an indication of whether the problem that caused the alarm was resolved or whether the alarm was silenced. Therapy data may also include event data such as the time / duration when the medical fluid delivery machine was stopped / paused or the time when treatment was terminated.

[0053] In addition to treatment data, the medical fluid delivery system may use patient data. As disclosed herein, patient data corresponds to medical data that may be included in an electronic medical record ("EMR"), such as medical history, prescription history, current / past treatments, test results, etc. Additionally or alternatively, patient data may include demographic data that may be provided by a clinician / patient, demographic data that may be specified within a prescribed therapy or program, and / or demographic data that may be provided via a patient registration. Demographic data may include patient age, gender, patient activity level, patient renal status, prescription history, etc. In some embodiments, patient data may include an identifier that enables the medical fluid delivery system to store the received data in an appropriate patient record located in a database. The identifier may include a patient identifier, a patient name, and / or a medical fluid delivery system identifier.

[0054] As discussed herein, the medical fluid delivery machine is located at the patient's residence. However, in some embodiments, the medical fluid delivery machine may be located at a full-service medical facility and / or a self-service medical facility. In some embodiments, a patient may use a first medical fluid delivery machine located at his or her residence and a second medical fluid delivery machine located at the self-service medical facility. In these embodiments, the medical fluid delivery system is configured to combine treatment data from the first and second medical fluid delivery machines.

[0055] As disclosed herein, the virtual assistant / chatbot logic is configured to use one or more computational structures, which are specified in a data structure that defines a patient interaction based on one or more patient answers. It should be understood that virtually any data structure may be used. For example, the questions, answers, and results may be stored as nodes and links in a graph database structure. In another example, the questions, answers, and results may be stored in a relational, sequential, or hierarchical data structure. The links between the answers and the questions are configured to guide the virtual assistant / chatbot logic to select the next action to be performed.

[0056] The use of readily available prescribed therapy, treatment data, and / or patient data allows the virtual assistant / chatbot logic disclosed herein to more accurately and quickly identify response actions while reducing the answers required from the patient. In some cases, a patient request or question that initially appears low context or unclear becomes more readily apparent by the virtual assistant / chatbot logic analyzing the prescribed therapy, treatment data, and / or patient data in conjunction with the request. In one example, a patient may initiate an interaction with the virtual assistant / chatbot logic disclosed herein by stating, "I'm tired of this alarm." By itself, this statement is unclear and could refer to a pressure alarm, an obstruction alarm, a low flow alarm, a low battery alarm, etc. However, when the virtual assistant / chatbot logic receives such a statement in conjunction with treatment data from a medical fluid delivery machine that identifies which alarms have been recently triggered, it is likely that the patient is referring to these recently triggered alarms. Thus, the exemplary virtual assistant / chatbot logic quickly converges on the appropriate response action using available data without burdening the patient with excessive questions and without burdening clinical staff by having to respond to every patient inquiry.

[0057] I. Medical Fluid Delivery System Embodiments Exemplary medical fluid delivery systems disclosed herein include one or more medical fluid delivery machines. One example of a medical fluid delivery machine is a renal failure therapy machine. With respect to a renal failure therapy machine, a patient's renal system may fail due to various causes. Renal failure results in several physiological disorders. For example, a patient experiencing renal failure can no longer balance water and minerals or excrete the daily metabolic load. Toxic end products of nitrogen metabolism (urea, creatinine, uric acid, etc.) may accumulate in the patient's blood and tissues.

[0058] Kidney failure and reduced kidney function are treated with dialysis. Dialysis removes waste, toxins and excess water from the body that normally functioning kidneys would otherwise remove. Dialysis treatment for replacement of kidney function is important for many people because the treatment is life-saving.

[0059] One type of renal failure therapy is hemodialysis ("HD"), which generally uses diffusion to remove waste products from a patient's blood. A diffusion gradient is created across a semi-permeable dialyzer between the patient's blood and an electrolyte solution, called the dialysate or dialysis fluid, to drive diffusion.

[0060] Hemofiltration ("HF") is another renal replacement therapy that relies on convective transport of toxins from the patient's blood. HF is achieved by adding substitution or replacement fluid to the extracorporeal circuit during treatment (typically 10 to 90 liters of such fluid). Substitution fluid and fluid accumulated by the patient between treatments are ultrafiltered over the course of HF treatment, providing a convective transport mechanism that is particularly beneficial in removing middle and large molecules (in hemodialysis, only a small amount of waste is removed with the fluid gained between dialysis sessions, but the solute drag from the removal of that ultrafiltrate is not sufficient to provide convective clearance).

[0061] Hemodiafiltration ("HDF") is a treatment modality that combines convective and diffusive clearance. HDF uses dialysis fluid flowing through a dialyzer, similar to standard hemodialysis, to provide diffusive clearance. In addition, substitution solution is delivered directly to the extracorporeal circuit to provide convective clearance.

[0062] Most HD (HF, HDF) treatments are performed in centers. There is a trend toward home hemodialysis ("HHD") today, in part because HHD can be performed daily, providing therapeutic benefits over in-center hemodialysis treatments, which are typically performed two or three times a week. Studies have shown that frequent treatments remove more toxins and waste products than patients undergoing less frequent, but perhaps longer, treatments. Patients undergoing treatments do not experience as many down cycles compared to in-center patients who build up two or three days' worth of toxins prior to treatment. In certain regions, the nearest dialysis center may be many miles away from the patient's home, causing door-to-door treatment times to consume a large portion of the day. In contrast, HHD can occur overnight or during the day while the patient is relaxing, working, or otherwise productive.

[0063] Another type of renal failure therapy is peritoneal dialysis, which infuses a dialysis solution, also called dialysis fluid, into the patient's peritoneal cavity via a catheter. The dialysis fluid contacts the peritoneal membrane of the peritoneal cavity. Waste, toxins and excess water pass from the patient's bloodstream through the peritoneal membrane into the dialysis fluid by diffusion and osmosis, i.e., an osmotic gradient occurs across the membrane. An osmotic agent in dialysis creates an osmotic pressure gradient. Spent or spent dialysis fluid is pumped out of the patient, removing waste, toxins and excess water from the patient. This cycle is repeated, for example, multiple times.

[0064] There are various types of peritoneal dialysis therapies, including continuous ambulatory peritoneal dialysis ("CAPD"), automated peritoneal dialysis ("APD"), as well as tidal flow dialysis and continuous flow peritoneal dialysis ("CFPD"). CAPD is a manual dialysis treatment. Here, the patient manually connects an implanted catheter to a drain, allowing used or spent dialysis fluid to drain from the patient's peritoneal cavity. The patient then connects the catheter to a bag of fresh dialysis fluid and infuses the fresh dialysis fluid through the catheter and into the patient. The patient disconnects the catheter from the fresh dialysis fluid bag, allowing the dialysis fluid to dwell in the peritoneal cavity, and transfer of waste, toxins, and excess water takes place. After a dwell period, the patient repeats the manual dialysis procedure, for example, four times a day, with each treatment lasting from one to six hours. Manual peritoneal dialysis requires significant time and effort from the patient, leaving significant room for improvement.

[0065] Automated peritoneal dialysis ("APD") is similar to CAPD in that the dialysis treatment includes drain, fill and dwell cycles. However, APD machines perform the cycles automatically, usually while the patient sleeps. APD machines do not require the patient to manually perform the treatment cycles and do not require transporting supplies during the day. APD machines fluidly connect to an implanted catheter, a source or bag of fresh dialysis fluid, and a fluid drain. The APD machine pumps fresh dialysis fluid from the dialysis fluid source through the catheter and into the patient's peritoneal cavity. APD machines also allow the dialysis fluid to dwell within the cavity, allowing transfer of waste, toxins, and excess water to occur. The source may include multiple sterile dialysis fluid bags.

[0066] APD machines pump used or spent dialysate from the patient's peritoneal cavity through a catheter to a drain. As with the manual process, several drain, fill and dwell cycles occur during dialysis. A "last fill" occurs at the end of APD and remains in the patient's peritoneal cavity until the next treatment.

[0067] Any of the above modalities performed by the machine may run on a scheduled basis and may require a start-up procedure. For example, dialysis patients typically perform treatments based on a schedule specified by a prescribed therapy or program, such as every other day, daily, etc. Blood processing machines typically require a certain amount of time before processing for setup, for example to perform a disinfection procedure. Patients of the above modalities lead busy lives and may have projects to complete or errands to run on the day scheduled for treatment.

[0068] Much of the appeal of home therapy for patients centers around the lifestyle flexibility it offers by allowing patients to perform therapy at home primarily on their own schedule. However, home medical fluid delivery machines may include software timers that prompt and restrain the patient. Home hemodialysis systems may require the patient to be in close proximity to the home hemodialysis machine to initiate pre-treatment, mid-treatment, and post-treatment sequences, for example.

[0069] In one particular example, the therapy machine may reuse certain components by sanitizing them between treatments. The machine may use one or more sanitization timers that require the patient or caregiver to use the machine to begin treatment before the sanitization timer expires. Otherwise, the patient must wait until another sanitization procedure is completed before beginning treatment. The therapy machine in one embodiment communicates a treatment start time deadline via the machine's graphical user interface.

[0070] The software of the disclosed systems and methodologies contemplates disabling communication between the patient and / or caregiver and the machine whenever the machine is in the "patient connected" software state. For example, if a clinician attempts to send a command to a machine that is currently treating a patient, the command will be intercepted by the middleware software application, so that the command is not forwarded to the machine. The middleware software application can then reply to the clinician to inform them that the machine is busy and not accepting communications.

[0071] The examples described herein are applicable to any medical fluid delivery system that delivers medical fluids, such as blood, dialysis fluids, substitution fluids, or intravenous medications ("IV"). The examples are particularly well suited for renal failure therapies, such as hemodialysis ("HD"), hemofiltration ("HF"), hemodiafiltration ("HDF"), continuous renal replacement therapy ("CRRT"), and peritoneal dialysis ("PD"), all forms of which are referred to herein collectively or generally as individually prescribed therapies or programs. Alternatively, the medical fluid delivery machine may be a drug delivery or nutritional fluid delivery device, such as a large volume peristaltic pump or syringe pump. The machines described herein may be used in a home environment. For example, the machines operating with the data transfer components may be used with a home HD machine, which may be run, for example, overnight while the patient is asleep. Alternatively, the medical fluid data transfer system and methodology of the present disclosure may be used to assist clinicians or nurses in hospitals and / or clinics.

[0072] Referring now to the drawings, and in particular to Figure 1, there is shown a medical system 10. The exemplary system 10 includes a number of medical fluid delivery machines 90, one type of which is described in detail below. The machines 90 of the medical system 10 may be of the same type (e.g., all PD machines) or may be of different types (e.g., a mixture of HD, PD, CRRT, and medical or nutritional fluid delivery).

[0073] Although a single medical fluid delivery unit 90 is shown in communication with the connection server 118, the system 10 manages the operation of multiple medical fluid delivery systems and machines of the same or different types listed above. For example, there may be M hemodialysis machines 90, N hemofiltration machines 90, O CRRT machines 90, P peritoneal dialysis machines 90, Q home drug delivery machines 90, and R nutrition or drug delivery machines 90 connected to the server 118 and operating with the system 10. The numbers M through R may be the same or different and may be 0, 1, 2 or more. In FIG. 1, the medical fluid delivery machine 90 is shown as a therapy machine 90 (home is shown in dashed line).

[0074] The therapy machine 90 may receive purified water at its front end from the water treatment device 60. The water treatment device 60, in one embodiment, connects to the therapy machine 90 via an Ethernet cable. The therapy machine 90 in the illustrated embodiment operates with other devices besides the water treatment device 60, such as a blood pressure monitor 104, a weighing scale, e.g., a wireless weighing scale 106, and a user interface, such as a wireless tablet user interface 122. The therapy machine 90, in one embodiment, connects wirelessly to a server 118 via a modem 102. Each of these components may (but need not) be located within the patient's home, as defined by the dashed lines in FIG. 1. Any, more than one, or all of the components 60, 104, 106, and 122 may communicate with the therapy machine 90 wired or wirelessly. Wireless communication may be via Bluetooth, WiFi, or other suitable wireless communication technologies. TM , Zigbee, Z-Wave, wireless universal serial bus ("USB"), infrared, or any other suitable wireless communication technology. Alternatively, any, more than one, or all of components 60, 104, 106, and 122 may communicate with therapy machine 90 via wired communication.

[0075] The exemplary connectivity server 118 communicates with the medical fluid delivery machines 90 via a medical device system hub 120. The exemplary system hub 120 allows data and information regarding each therapy machine 90 and its peripherals to move back and forth between the machine 90 and other devices connected to the server 118 via the connectivity server 118. In the illustrated embodiment, the system hub 120 is connected to a service portal 130, an enterprise resource planning system 140, a web portal 150, a business intelligence portal 160, a HIPAA-compliant database 124, a product development team 128, and an electronic medical record database maintained, for example, at a clinic or hospital 126a-126n. The connectivity server 118 and / or the portals 130, 150, 160 may include gateway devices.

[0076] The illustrated electronic medical record ("EMR") databases are located at the clinics or hospitals 126a-126n and may store electronic information regarding patients. The system hub 120 may transmit data collected from the machine 90 log files (e.g., treatment data) to the hospital or clinic databases 126a-126n to merge or supplement the patient's medical record. The clinic or hospital databases 126a-126n may include patient-specific treatment and prescription data (e.g., prescribed therapies or programs), and access to such databases may be highly restricted. The exemplary enterprise resource planning system 140 is configured to obtain and compile data generated via patient and clinician website access, such as complaints, billing information, and lifecycle management information. A web portal 150 allows patients and clinics 152a-152n that treat them to access the publicly available website. Business Intelligence Portal 160 collects data from System Hub 120 and provides the data to Marketing 162, Research and Development 164, and Quality / Pharmacovigilance 166.

[0077] It should be understood that the systems, methods, and procedures described herein may be implemented using one or more computer programs or components. The component programs may be provided as a series of computer instructions on any computer-readable medium, including random access memory ("RAM"), read-only memory ("ROM"), flash memory, magnetic or optical disks, optical memory, or other storage media. The instructions may be configured to be executed by a processor, which, upon executing the series of computer instructions, performs or facilitates the execution of all or a portion of the disclosed methods and procedures described herein.

[0078] In one embodiment, the therapy machine 90 performs a home therapy, such as home peritoneal dialysis, on a patient in the patient's home and then reports the results of that therapy (as therapy data) to the system hub 120, which may communicate with one or more servers. As described in more detail below, the one or more servers analyze the therapy data for reporting to clinicians, doctors, and / or nurses responsible for managing the health and well-being of that patient.

[0079] The therapy machine 90 in one embodiment writes log files using, for example, a Linux operating system. The log files document associated therapy machine 90 data, including peripheral device data. The log files may include any one or more of Extensible Markup Language ("XML"), Comma Separated Values ​​("CSV"), or text files. The log files are located in a file server repository managed by the therapy machine 90 software. It is also contemplated that data may be stored on a peripheral device, such as the water treatment device 60, and the data is not sent to the machine 90. Such data may otherwise be obtained via a wired or wireless connection to the peripheral device or downloaded via other data connection or storage medium.

[0080] In one embodiment, the therapy machine 90 uses a connectivity service to transfer therapy data between the modem 102 and the system hub 120, for example, via the Internet. Here, a dedicated line may be provided at each patient's home to connect the therapy machine 90 to the connectivity server 118 via the modem 102. The therapy machine 90, in one embodiment, accesses the Internet using a separate, for example, 3G, 4G, or 5G, modem 102. The modem 102 may use an Internet Service Provider ("ISP") such as Vodafone™. In one implementation aspect, a connectivity agent 114 developed by a connectivity service provider (e.g., provider of the connectivity server 118) is installed on the therapy machine 90 and runs on the machine's primary control processor ("ACPU") 50. A suitable connectivity service is provided by Axeda™, which provides a secure managed connection 116 between the medical device and the connectivity server 118.

[0081] 1 is configured to enable therapy machines 90 to connect to and transfer therapy data to and from the connectivity server 118. The connectivity services operating through the agent 114 and server 118 ensure that connections with machines 90 are secure, ensure that data passes correctly through the firewall of the machine 90, detect if there has been a data or system crash, and ensure that the connectivity server 118 communicates with the correct therapy machine 90.

[0082] In one embodiment, the therapy machine 90 may only connect to the connectivity server 118 when the connectivity agent 114 is turned on or activated. During treatment and post-treatment disinfection, while the machine 90 and its peripherals are functioning, in one embodiment, the connectivity agent 114 is automatically turned off, which prevents the therapy machine 90 from communicating with, sending or receiving data from any entity during treatment and disinfection, or while the machine 90 is running or in operation. In one embodiment, the ACPU 50 turns on the connectivity agent 114 when the therapy machine 90 is idle, e.g., after treatment and post-disinfection are completed. In one embodiment, the connectivity agent 114 is off during therapy (and possibly pre-therapy). After treatment, the connectivity agent 114 retrieves log files from the therapy machine 90 and transfers the therapy data to the connectivity server 118 using a connectivity service. The connectivity service routes data packets to their appropriate destination, but in one embodiment does not modify, access, or encrypt the data.

[0083] In the medical system 10 system of FIG. 1, connectivity services via the connection server 118 may communicate data via the system hub 120 to various locations such as the service portal 130, clinics or hospitals 126a-126n, and web portal 150. The connection server 118 allows service personnel 132a-132n and / or clinicians to track and locate various assets on the network, such as the appropriate therapy machine 90 and 3G, 4G, or 5G modem 102, and their associated information, including the machine or modem serial number. The connection server 118 may also be used to receive firmware updates approved by the service personnel director 134 and obtained remotely via the service portal 130, and provide the firmware updates to authorized therapy machines 90 and associated peripherals, such as water treatment devices 60.

[0084] A. Exemplary Medical Fluid Delivery System Connectivity Embodiments Figure 2 shows a diagram of the medical system 10 of Figure 1 according to an exemplary embodiment of the present disclosure. The exemplary medical system 10 includes a personal mobile communication device 122 (e.g., a user device) operated by, for example, a patient, and a clinician device 152 operated by a clinician. The medical system 10 also includes a therapy machine 90 (e.g., a medical fluid delivery machine) similar to the respective devices described above in connection with Figure 1. The personal mobile communication device 122 and therapy machine 90 may be located, for example, in the patient's home, a self-service clinic, and / or a serviced clinic.

[0085] Therapy machine 90 may include any type of hemodialysis machine, peritoneal dialysis machine, CRRT machine, drug and / or nutritional fluid delivery machine, and combinations thereof. Therapy machine 90 may provide, for example, continuous cyclic peritoneal dialysis ("CCPD"), tidal automated peritoneal dialysis ("APD"), and continuous flow peritoneal dialysis ("CFPD"). Therapy machine 90 may automatically perform drain, fill, and dwell cycles, typically while the patient sleeps.

[0086] The exemplary therapy machine 90 may also include one or more control interfaces 201 for displaying instructions and receiving control inputs from a user. The control interface 201 may include buttons, a control panel, and / or a touch screen. The control interface 201 may also be configured to allow a user to navigate to particular windows or user interfaces on the screen of the therapy machine 90. The control interface 201 may further provide instructions for operating or controlling the therapy machine 90.

[0087] The exemplary therapy machine 90 may receive one or more prescribed therapies or programs 202 remotely from the clinician server 204 and / or clinician database 206. Additionally or alternatively, the therapy machine 90 may be locally programmed with the prescribed therapies or programs 202 via the control interface 201. As discussed herein, the prescribed therapies 202 include parameters that specify how the therapy machine 90 administers one or more scheduled therapies to a patient (e.g., patient 12 of FIG. 1). The therapy parameters 202 may include a number of fill-dwell-drain cycles for a peritoneal dialysis therapy, in addition to the duration of each step. The therapy parameters may also include a total amount of dialysis fluid to be administered (and / or the amount of fluid to be administered per cycle), a dextrose concentration, and / or a target UF removal level. The therapy parameters 202 may also include a treatment day schedule and a total treatment duration. In some embodiments, the clinician server 204 may remotely update any of the prescribed therapy parameters.

[0088] It should be understood that the medical system 10 may include additional medical devices, such as a weight scale, a blood pressure monitor, an infusion pump (e.g., a syringe pump, a linear peristaltic pump, a large volume pump ("LVP"), an ambulatory pump, a multi-channel pump), an oxygen sensor, a respiratory monitor, a glucometer, a blood pressure monitor, an electrocardiogram ("ECG") monitor, and / or a heart rate monitor. In other examples, the medical fluid data transfer system 90 may include fewer medical devices and / or medical devices integrated with the therapy machine 90.

[0089] As shown in Figure 2, the therapy machine 90 is communicatively coupled to the connectivity server 118 via a network 210. As previously described in connection with Figure 1, the connectivity server 118 provides bidirectional communication between the therapy machine 90 and the system hub 120. The network 210 may include any wired or wireless network, including the Internet, a cellular network, or a combination thereof.

[0090] The example system hub 120 is also communicatively coupled to a clinician server 204 and a clinician database 206. As described in more detail below, the clinician server 204 is configured to execute one or more instructions, routines, algorithms, applications, or programs (e.g., virtual assistants / chatbots) 212 to determine how a patient request should be processed. The clinician database 204 is configured to store a prescribed therapy or program 202 for each patient associated with the system 10. The clinician database 206 is also configured to store one or more records for each patient including treatment data 213 from respective therapy machines 90 and / or patient data 214 (e.g., the patient's EMR).

[0091] In the illustrated example, the clinician server 204 is communicatively coupled to a memory device 220 that stores one or more instructions, routines, algorithms, applications, or programs for executing the virtual assistant / chatbot logic 212. The memory device 220 may also store one or more data structures and / or instructions 222 that define an automated interaction with a patient to determine a response action 238. The one or more instructions, routines, algorithms, applications, or programs for executing the virtual assistant / chatbot logic 212 and / or the one or more data structures and / or instructions 222 may include machine-readable instructions that, when executed by one or more processors of the clinician server 204, cause the clinician server 204 to perform the operations described herein.

[0092] As described herein, response actions 238 are operations performed by the clinician server 204 based on the level of response required for a patient inquiry or request. Response actions 238 may include determining that an automatic response is appropriate and sending one or more messages (as response actions 238) to the patient with technical / medical information to address a low or non-urgent patient inquiry. Response actions 238 may also include determining that a patient inquiry has a medium level of urgency and that the inquiry should be sent in one or more messages (as response actions 238) to a voicemail system, a person-to-person chat system, or the clinician's email system. In some embodiments, the clinician server 204 determines which clinician should receive the message based on a name provided by the patient, a documented past relationship with the patient (provided in the patient data 214), or based on a role or responsibility associated with the request. After identifying the clinician, the clinician server 204 determines the corresponding account and sends the response action 238 to the account. In some embodiments, the clinician server 204 prompts the patient to enter the inquiry. Additionally or alternatively, the clinician server 204 uses information from the patient's interaction with the virtual assistant / chatbot 212 to automatically generate content for the response actions 238. In this manner, the data 202, 213, 214 can be used not only to navigate the interaction with the patient, but also in conjunction with the patient responses to convey specific request information to the clinician.

[0093] In one example, the patient may initiate an inquiry by initiating an inability to resolve the alert via the application 140 on their personal mobile communication device 122. In response, the clinician server 204 uses the virtual assistant / chatbot 212 to determine from the patient what actions the patient has already attempted to resolve the alert. Additionally, the clinician server 204 locates the associated treatment data 213 to determine the type of alert and / or the most recent date / time the alert was activated. Based on this collection of data, the clinician server 204 may determine that the patient's inquiry is at a medium level (as intermittent alerts are bothersome but not critical) and prompt the patient accordingly to enter information for a response action 238, and / or the clinician server 204 may use at least a portion of the patient's responses to the virtual assistant / chatbot 212 and / or treatment data 213 / patient data 214 to generate content for the response action 238, which is provided to the appropriate clinician account associated with the resolved alert as a text message, multimedia message, email message, etc. In one example, the response action 238 includes a recorded direct inquiry from the patient (possibly including a video or image of the display interface 201 of the therapy machine 90 showing the alarm) in addition to the alarm-based treatment data 213 and / or patient data 214 for further context.

[0094] If the clinician server 204 determines that the patient request is critical or urgent, the clinician server 204 identifies the clinician and establishes a direct communication link between the identified clinician's clinician device 152 and the patient's personal mobile communication device 122. The communication may include a voice call, a video call, and / or an active chat session.

[0095] 2, the exemplary medical system 10 includes a web portal 150 to facilitate transmission of data to clinician devices 152 and / or personal mobile communication devices 122 via a network 230. The exemplary network 230 may include any wired and / or wireless network, such as the Internet, a cellular network, or a combination thereof. The networks 210 and 230 may include the same network.

[0096] The web portal 150 may include one or more application programming interfaces ("APIs") or other network interfaces that provide for communication of treatment data 213, patient data 214, and / or response actions 238. The web portal 150 may also establish communication sessions between the clinician device 152 and the personal mobile communication device 122. In some cases, the web portal 150 may be configured as a gateway device and / or firewall so that only authorized users and / or devices can communicate with the clinician server 204 and / or clinician database 206. Additionally, the web portal 150 may create a separate session for each connected device 122 and 152.

[0097] The clinician device 152 and / or the personal mobile communication device 122 may include respective applications 240 and 242 configured to interface with the web portal 150 to communicate with the clinician server 204 and / or the clinician database 206. For example, the application 240 may include one or more user interfaces having data fields configured to receive a patient's request or question. The application 240 is also configured to operate with the telephone capabilities of the personal mobile communication device 122 to allow a voice or video call to be routed to the clinician server 204 to interact with the virtual assistant / chatbot 212. The application 242 may also include (or provide) access to email, text, or multimedia messaging services to allow the patient to enter information to interact with the virtual assistant / chatbot 212 and / or the clinician device 152.

[0098] The applications 242 of the clinician device 152 are configured with one or more interfaces for receiving response actions 238 from the clinician server 204. The interfaces allow the clinician to provide responses to requests or queries from the personal mobile communication device 122. The applications 242 are also configured to operate with the telephony capabilities of the clinician device 152 to allow the clinician to receive voice or video calls from the personal mobile communication device 122. The applications 242 may include (or provide) access to email, text, or multimedia messaging services for viewing and responding to patient queries (provided by the response actions 238 via the clinician server 204).

[0099] In other examples, the applications 240 and 242 are web browsers configured to access one or more web pages via a web portal 150 hosted or managed by the clinician server 204. In these other examples, the clinician server 204 provides a user interface and corresponding data fields to the one or more web pages. A user may interact with the web browser to view or enter desired data. The applications 240 and 242 may also include native controls or other installed applications on the devices 122 and 152.

[0100] In some cases, the web portal 150 is configured to convert the prescribed therapy or program 202, treatment data 213, and / or patient data 214 from a text-based or Health-Level-7 ("HL7") standard (e.g., a medical standard) to a web-based message (e.g., an HTTP message, a HyperText Markup Language ("HTML") message, an Extensible Markup Language ("XML") message, a Java Script Object Notation ("JSON") payload, etc.). In other embodiments, the connection server 118 is configured to convert the HL7 prescribed therapy or program 202, treatment data 213, and / or patient data 214 from the therapy machine 90 to a text-based or web-based format (e.g., JSON format) for processing by the clinician server 204 and storage by the clinician database 206.

[0101] In the example shown in FIG. 2, the exemplary personal mobile communication device 122 and clinician device 152 include a processor 250 in communication with a memory 252 that stores instructions. At least a portion of the instructions define or specify respective applications 240 and 242 that, when executed by the processor 250, cause the processor 250 to provide an interface for processing patient inquiries using the virtual assistant / chatbot 212. The processor 250 may include digital and / or analog circuitry structured as a microprocessor, an application specific integrated circuit ("ASIC"), a controller, or the like. The memory 252 includes a volatile or non-volatile storage medium. Additionally, the memory 252 may include any solid state or disk storage medium.

[0102] 2 may also include a third-party server 260 associated with the manufacturer of the therapy machine 90. In some cases, the clinician server 204 determines that the patient's inquiry is related to an operational or technical problem with the therapy machine 90. In these cases, instead of sending a message to the clinician, the clinician server 204 sends a message to the third-party server 260 that includes a response action 238. The response action 238 may include opening a live communication session or providing a text message, multimedia message, email, etc. to a call center or other diagnostic center associated with the third-party server 260.

[0103] II. Clinician Server - Virtual Assistant / Chatbot Embodiments As previously discussed, the example clinician server 204 of FIG. 2 is configured to provide interactive sessions with patients to triage their requests. FIG. 3 illustrates a diagram of the clinician server 204 according to an example embodiment of the present disclosure. In the illustrated example, the clinician server 204 includes instructions or software modules 302-320 that specify how the clinician server 204 performs certain operations. The instructions 302-320 are used by the clinician server 204 to perform the operations of the virtual assistant / chatbot logic 212. The blocks illustrated in FIG. 3 represent the specific operations defined by the instructions 302-320. In other embodiments, some of the blocks may be combined, further divided, or may include additional blocks. Additionally, although the clinician server 204 is shown as being centrally located, in other embodiments, the clinician server 204 and / or the clinician database 206 may be deployed within a cloud computing environment.

[0104] The example instructions 302-320 include a speech-to-text module 302 that receives audio or voice commands from the personal mobile communication device 122. The speech-to-text module 302 receives digital data and / or analog signals that include recorded human speech. The speech-to-text module 302 is configured to convert the digital data and / or analog signals to text using one or more speech-to-text algorithms.

[0105] The speech-to-text module 302 sends the converted text to the language processing module 304, which is configured to use one or more algorithms to modify the received text based on the user's known or learned accent, speech, or slang. The language processing module 304 may include a library of known accents, speech, and / or slang for various types of users. The language processing module 304 selects an appropriate text modifier based on how well the patient matches a particular accent, speech, and / or slang. In some cases, the language processing module 304 may use one or more machine learning algorithms to identify and / or modify the text based on the user's identified accent, speech, or slang. The language processing module 304 outputs modified text that takes into account the user's accent, speech, or slang. For example, the language processing module 304 may receive a text input from the speech-to-text module 302 that includes a combination of vowels, constants, and pauses. After filtering through the language processing module 304 , the strings of vowels, constants, and pauses are refined into text words and / or phrases, which are input to the speech recognition module 306 .

[0106] The speech recognition module 306 is configured to run one or more natural language processing algorithms to determine the meaning of the received word or phrase. In some embodiments, the speech recognition module 306 identifies the meaning of a string of words or phrases, and the identified meaning is stored as metadata in a separate data field or is attached to the word and / or phrase. The speech recognition module 306 may analyze the word or phrase and identify that a question is being asked and the subject of the question. In this example, the speech recognition module 306 adds that the word or phrase corresponds to the question and keywords associated with the question. The processing performed by the speech recognition module 306 adds formatted information that allows for subsequent analysis based on more defined linguistic parameters.

[0107] In some embodiments, the speech recognition module 306 is configured to search for a specific keyword to start a virtual session with the patient. If a virtual session is not already in progress, the speech recognition module 306 listens or processes text and phrases for a specific keyword or phrase indicating to start a session. For example, the virtual assistant / chatbot may be called "Claria". Thus, the speech recognition module 306 searches for the term "Claria" or a similar spelling. If there is a match, the speech recognition module 306 starts a virtual session with the patient and processes the phrase containing the term "Claria". At this point, the speech recognition module 306 processes the subsequent words and / or phrases as part of the virtual conversation. However, if no match is made, the speech recognition module 306 truncates the text from further processing and refrains from recording other patient conversations or surrounding room sounds. It should also be understood that the virtual assistant / chatbot 212 may be activated by the patient by selecting a corresponding icon displayed by the user interface 201 of the therapy machine 90 or the application 240 of the personal mobile communication device 122.

[0108] The exemplary clinician server 204 also includes a response engine 308 configured to apply text from the speech recognition module 306 and / or data 202, 213, and / or 214 to the virtual assistant / chatbot logic 212. Thus, potential inputs to the response engine 308 include text from the speech recognition module 306 and / or text from a chatbot program provided by the user interface 201 of the therapy machine 90 or the application 240 of the personal mobile communication device 122. The inputs also include the prescribed therapy or program 202, treatment data 213, and / or patient data 214.

[0109] The exemplary adaptive interface 308 includes an input interface 310 configured to receive text and / or other input entered into the user interface 201 of the therapy machine 90 or the application 240 of the personal mobile communication device 122. The input may include a selection of an icon that causes the adaptive interface 308 to initiate a virtual interactive session with the patient. The input may also include text entered into a chat session via the user interface 201 of the therapy machine 90 or the application 240 of the personal mobile communication device 122. In some cases, the response engine 308 launches a virtual chat session by opening a virtual chat or text messaging session on the user interface 201 of the therapy machine 90 or the application 240 of the personal mobile communication device 122. Text entered by the user into a field or text box is sent by the user interface 201 of the therapy machine 90 or the application 240 of the personal mobile communication device 122 to the response engine 308 via the input interface 310. In some cases, the input interface 310 may include one or more application programming interfaces ("APIs") that connect to a text messaging application that enables routing of entered text to the response engine 308. In addition to text, the input interface 308 can accept images, videos, emojis, or indications of selection of displayed options.

[0110] To receive the therapy data 213 from the therapy machine 90, the server 204 includes a machine interface 312. An exemplary memory interface 312 is configured to request or receive the therapy data 213 from the therapy machine 90. In some embodiments, the adaptive interface 308 is configured to request the therapy data 213 using the machine interface 312 after detecting that the patient has initiated a virtual interactive session. In another embodiment, the adaptive interface 302 may use the machine interface 312 to search the clinician database 206 for relevant therapy data 213 and / or patient data 214 (and prescribed therapy or program) when the virtual assistant / chatbot logic 212 is configured to use certain medical information to answer questions, determine response actions 238, or create content for the response actions 238.

[0111] FIG. 4 is a diagram of a process 400 performed by the virtual assistant / chatbot logic 212 to triage a patient's inquiry according to an exemplary embodiment of the present disclosure. The exemplary process 400 begins when a patient initiates an inquiry using an application 240 on the personal mobile communication device 122 and / or the display interface 201 of the therapy machine 90. The virtual assistant / chatbot logic 212 uses logic to select one or more follow-up questions. In other words, the virtual assistant / chatbot logic 212 provides an interactive session to proceed through a hierarchy of questions with one or more prompts to receive further information until a response action 238 is identified. In some embodiments, the request / answer / question hierarchy of the virtual assistant / chatbot logic 212 may be modified based on the protocol of the hospital system or clinic.

[0112] FIG. 5 illustrates an interface of an application 240 provided on a personal mobile communication device 122 according to an exemplary embodiment of the present disclosure. In event A, the application 240 displays at least some therapy data 213, including ultrafiltration trends. The interface includes an icon 500 that allows the patient to initiate the virtual assistant / chatbot logic 212. Event B shows the application displaying an interactive interface 502 for the virtual assistant / chatbot logic 212. The interactive interface 502 includes automated text from the virtual assistant / chatbot logic 212 asking the patient about a problem or question. As shown, the patient types or speaks that they are running out of mini-caps (i.e., PD disposables). The interactive interface 502 may also display a picture of a generic virtual assistant or a picture of the patient's clinician. The text or utterance provided by the patient is processed by the clinician server and / or the virtual assistant / chatbot logic 212 as previously described.

[0113] The virtual assistant / chatbot logic 212 includes a list of possible problems and keywords associated with the problems. The response engine 308, in conjunction with the virtual assistant / chatbot logic 212, performs keyword matching to determine which problem the patient is likely referring to. In the above example, the patient indicates that he or she needs help with an alarm, but is unable to identify the type of alarm (e.g., occlusion alarm, dialysis fluid leak alarm, low container alarm, pumping alarm, overfill alarm, etc.). In this case, the virtual assistant / chatbot logic 212 identifies keywords associated with each alarm type. Instead of asking the patient further questions, the response engine 308 uses the treatment data 213 to determine that an occlusion alarm is active. This further information allows the response engine 308 and / or the virtual assistant / chatbot logic 212 to determine that the problem is related to the occlusion alarm.

[0114] The virtual assistant / chatbot logic 212 includes a data structure of possible problems. Each problem has one or more keywords associated with the problem. The keywords are preselected based on an analysis of the data 202, 213 and / or 214 and patient responses from a patient population relevant to the problem. For example, an occlusion alarm problem includes keywords such as "alarm, warning, noise, blinking, beep, and alert." The keywords may also include a diagnostic identifier generated by the therapy machine 90 (included in the therapy data 213) associated with the occlusion detection. These keywords may include a diagnostic trouble code, a field identifier for the occlusion detection, or an event identifier.

[0115] The virtual assistant / chatbot logic 212 is configured to compare the received text and data 202, 213, and / or 214 to each of the high-level questions. The virtual assistant / chatbot logic 212 selects the question with the highest match score or probability based on the comparison to the keywords. The virtual assistant / chatbot logic 212 can prevent selection if the match does not exceed a match threshold, such as 60% or 75%. In this example, the virtual assistant / chatbot logic 212 includes a follow-up question to ask the patient based on which question has the highest match score.

[0116] The virtual assistant / chatbot logic 212 may include a hierarchy of questions and answers for at least some of the possible problems. These further questions and answers may further refine the problem into a more precise problem and provide a better solution. For example, a higher level problem may simply refer to an alarm. The lower level questions and answers provide keywords and criteria for different types of alarms. In some cases, such as the occlusion alarm example above, the answer may be determined directly from the data 202, 213 and / or 214 without further input from the patient. However, if any of the lower level answers cannot be determined, the virtual assistant / chatbot logic 212 uses the listed questions associated with each possible answer of the higher level problem to select which question will be provided to the patient for follow-up. The hierarchy of the virtual assistant / chatbot logic 212 provides problem / sub-problem crossing that allows the response engine 308 to quickly converge on the problem likely to be experienced by the patient to determine the response action 238.

[0117] At some point in the hierarchy, an answer for a sub-problem is associated with a response action 238. The virtual assistant / chatbot logic 212 determines when there is a match or near match over a threshold for the response action 238. Based on this match, the response engine 308 sends the response action 238 to the patient and / or the identified clinician. In some cases, the response action 238 may be provided for a higher level problem without having to go through the hierarchy of sub-problems. Thus, the virtual assistant / chatbot logic 212 defines how the response engine 308 interacts with the patient to identify which problem is being experienced by the patient.

[0118] As shown in FIG. 4, there are several different possible response actions 238 based on the determined criticality level. In some embodiments, the virtual assistant / chatbot logic 212 may have three levels. In other embodiments, there may be fewer or more levels. In the three-level configuration, the lowest level corresponds to basic patient questions or requests that may be answered automatically without human intervention. These include questions / requests regarding patient guidance, reordering supplies, and / or general information regarding the therapy machine 90. The medium level corresponds to requests / patient questions for the clinician to address when time permits, thereby not interrupting the clinician's workflow. These questions or requests may relate to minor or moderate medical issues and / or rare problems with the therapy machine 90. The critical level corresponds to questions / requests that need to be answered by the clinician immediately. These response actions 238 are flagged, prioritized, and escalated by the clinician server 204. These questions / requests or patient inquiries may relate to peritonitis, fluid status, and frequent or ongoing issues with the therapy machine 90.

[0119] FIG. 4 also illustrates at least a portion of the prescribed therapy or program 202, treatment data 213, and / or patient data 214, which may be used by the virtual assistant / chatbot logic 212 to converge on the responsive action 238 more quickly or to create the content of the responsive action 238. The prescribed therapy or program 202 includes treatment parameters defined in one or more dialysis prescriptions or programs. For PD, the prescribed therapy or program 202 may include one or more of a total fill volume, number of cycles, fill rate, fill volume per cycle, dwell time, drain rate, expected ultrafiltration ("UF") removed per cycle or treatment, dialysis fluid concentration (e.g., dextrose concentration), or treatment schedule. For HD, the prescribed therapy or program 202 may specify treatment time, blood circulation rate, dialysis fluid circulation rate, dialysis fluid volume, treatment schedule, or dialysis fluid concentration. With respect to infusion therapy, the prescribed therapy or program 202 may include the infusion rate, the volume of fluid to be infused, the type / volume of fluid, the drug or ingredient concentration of the fluid, and the total infusion time. The prescribed therapy or program 202 may be received from the therapy machine 90 and / or a clinician database 206 (stored in the patient's EMR).

[0120] The therapy data 213 describes how the dialysis treatment was performed. As shown in FIG. 4, for PD treatment, the therapy data 213 may include at least one of the date / time the treatment was performed, the number of cycles per treatment, the fill volume, the drain volume, the estimated or measured amount of UF removed, and any events that occurred during the treatment. Events may include alarms, warnings, patient inputs that contradict limits or thresholds, line occlusions, line leaks / breaks, treatment pauses, etc. In some cases, the therapy data 213 may also include physiological data if the therapy machine 90 is connected to (or includes) one or more sensors (blood pressure sensor or cuff, weight scale, heart rate sensor, ECG sensor, etc.). Overall, the therapy data 213 provides a summary of how the dialysis treatment was performed.

[0121] The therapy data 213 may further include device information. For example, device information 508 may include the correct state of the therapy machine 90, such as whether the machine is in a priming sequence, in a cleaning / disinfecting sequence, about to start a cycle of PD therapy, progressing through a fill phase, progressing through a dwell phase, progressing through a drain phase, or ending a cycle or therapy. Device information may also include diagnostic information, such as faults detected in one or more pumps, valves, or other dialysis components.

[0122] The patient data 214 relates to information specific to the patient that cannot be readily determined through monitoring of the therapy machine 90. The patient data 214 may include patient activity information, patient demographic information, and patient medical information. The patient activity information is determined through one or more question and answer sessions with the patient. Additionally or alternatively, the patient activity information may be determined from the patient's EMR.

[0123] In one example, a PD treatment may take three or four hours to complete. During this time, the patient is fluidly connected to the therapy machine 90 at least during the dialysis fluid fill and drain phases of the cycle, which may be tedious for the patient. To help fill the time, the clinician server 204 may be configured to determine from the treatment data 213 that the fill phase will occur for the next 30 minutes. The clinician server 204 may also be configured to determine from the speech recognition module 306 that the ambient environment is quiet. Based on these conditions, the clinician server 204 may be configured to initiate a virtual session with the patient to fill the time to obtain some patient data 214, which may include diet information, fluid intake, medications, activity levels, mental state, and sleep patterns. The clinician server 204 may prompt the patient with simple questions such as "What did you eat today?", "What medications are you taking?", "What did you do today?", and "How are you feeling?" and "How did you sleep?". Patient responses are recorded by the clinician server 204 as patient data 214. The clinician server 204 may timestamp the patient data 214 to allow trends to be determined. In some cases, the clinician server 204 may use virtual assistant / chatbot logic 212 to ask questions and determine if follow-up questions are necessary. In addition to asking questions during treatment, the clinician server 204 may ask questions after or before treatment at times less likely to interrupt the patient.

[0124] In addition to prompting the patient for patient activity information, the clinician server 204 may prompt the patient for patient demographic information. Alternatively, the clinician server 204 may obtain patient demographic information from one or more EMRs stored in the clinician database 206. As shown in FIG. 4, the patient demographic information may include gender, age, weight, race, ethnicity, and geographic location. The clinician server 204 may use the virtual assistant / chatbot logic 212 to obtain the patient demographic information from the patient before, during, or after treatment.

[0125] The clinician server 204 may use the same virtual session to prompt the patient for patient medical information. Alternatively, the clinician server 204 may use the therapy machine 90 to obtain at least a portion of the patient's medical information using connected physiological sensors. In yet another example, the clinician server 204 obtains the patient medical information in the patient data 214 from one or more EMRs. Collectively, the patient data 214 provides a summary of the patient's health, which may include at least some of the subject information obtained via the virtual session.

[0126] As shown in FIG. 4, the process 400 includes triaging the patient request to an appropriate response action 238. The first response action 238a corresponds to providing an automatic response to the patient. The first response action 238a is selected for a specified low-level inquiry. The response references a particular section of medical and / or product documentation and / or a section of the patient data 214 (e.g., the patient's EMR). The clinician server 204 copies the information and includes the information in one or more response messages as response actions 238a. The messages may be conveyed as text or multimedia messages, audio messages, and / or audiovisual messages. The following questions and responses may be provided via the response actions 238a: Example 1: Questions can be answered by a chatbot and / or a patient guide. "How do I connect the new solution bag?" Answered using information on page 93 of the Patient Guide The chatbot answers and closes the call Example 2: Routine but patient-specific questions "We're running low on minicaps, when is the next delivery?" One with a clear yes / no that can be easily answered. Chatbots provide direct answers – to simple questions that should be answered by a database.

[0127] Response actions 238b, 238e, and 238f in FIG. 4 correspond to critical level responses. Here, the clinician server 204 determines that the patient needs to be put in contact with a clinician, nurse, or doctor. The clinician server 204 uses the virtual assistant / chatbot logic 212 along with the patient's response and data 202, 213, and / or 214 to determine which practitioner is best to handle the response, in addition to determining the criticality of the response. After identifying the individuals, the clinician server 204 determines their phone numbers or virtual identifiers in an electronic address book to establish a communication session. The clinician server 204 may include a communication interface 314 to establish a voice call, a video call, a conference call, and / or a live text session. The communication interface 314 may send one or more messages to the identified clinician device 152 and the personal mobile communication device 122 to establish a session via the respective response action 238b, 238e, or 238f. In some embodiments, the communication interface 314 adds content for the response action 238 for viewing on the application 242 of the clinician device 152. The content may include information provided by the patient during the virtual session and / or relevant portions of the data 202, 213, and / or 214. The following is an example of an interaction: Example 3: Urgent question, sent immediately and directly to the nurse "My stomach hurts and my runoff is cloudy. What should I do?" Contact the nurse with urgent note / message escalation; and tell the patient to come in

[0128] In some embodiments, the clinician server 204 selects a response action 238c for the message to the manufacturer of the therapy machine 90. The response action 238c may include a text message, voicemail, email, etc. that can be addressed in a timely manner by the manufacturer's call center. In case of an emergency, the clinician server 204 establishes a live session as described above. The following is an example of a dialogue: Example 4: A question can be answered by a chatbot. "There is something floating in my new solution bag, what should I do?" Answer with "Don't use it; connect to product monitoring" The chatbot answers and closes the call

[0129] 4 also illustrates a response action 238d in which a message is provided to the clinician. In these cases, the clinician server 204 constructs an email, text message, voice message, etc. that includes some information determined from the virtual interaction with the patient and / or data 202, 213, and / or 214. Additionally, the clinician server 204 may prompt the patient to leave a voicemail or other text for the clinician. In these examples, the clinician server 204 uses the communications interface 316 to send the response action 238d to the appropriate communications account of the clinician. Below is an example interaction: Example 5: Questions that are difficult to answer leave a voicemail for the clinic that are given a prioritization score, cannot be answered in the patient guide, but are not urgent. "I'm about to do a 24 hour collection but I forgot how to do it; can you help?" The nurse can receive the message and call back later with instructions.

[0130] 6 is an illustration of a dashboard 600 provided by the clinician application 242 to respond to the response actions 238d according to an exemplary embodiment of the present disclosure. The dashboard 600 displays a list of patients by day and the response actions 238d associated with each patient. The dashboard 600 is configured to allow the clinician to select a response action 238d. In response to a selection, the dashboard 600 of the application 242 provides an interface for the clinician to enter or record a response, which is then transmitted to the application 240 of the personal mobile communication device 122 via the clinician server 204.

[0131] The dashboard 600 also provides an indication as to which response actions 238d have been addressed. In some embodiments, the dashboard 600 changes the color of the icon or otherwise prompts the response action 238d to draw the clinician's attention if a response is not provided within a threshold time, such as 2 hours, 4 hours, 6 hours, 12 hours, 24 hours, 48 ​​hours, etc. Additionally, if the response action 238d has not been addressed within the threshold, the clinician server 204 may provide the response action 238d to other clinician's dashboards. The dashboard 600 may also allow a clinician to route the response action 238a to another clinician.

[0132] (III. Conclusion) It should be understood that various changes and modifications to the presently preferred embodiments described herein will be apparent to those skilled in the art. Such changes and modifications can be made without departing from the spirit and scope of the present subject matter and without diminishing its intended advantages. Accordingly, such changes and modifications are intended to be covered by the appended claims.

Claims

1. 1. A virtual assistant / chatbot system for improving clinical workflow for home renal replacement therapy, the system comprising: an interface communicatively coupled to a network, the interface configured to communicate with an application on a user device or an interface for a medical device; a memory device storing a patient inquiry triage data structure for a virtual assistant or chatbot, the data structure including a plurality of potential problems related to dialysis or medical device operation, each problem including a hierarchy of questions and possible answers leading to response actions, the response actions including a direct communication connection with a clinician and a communication connection with a voicemail system, a person-to-person chat system, or an email system; a processor communicatively coupled to the interface and the memory device; Equipped with The processor: receiving a query message from the application on the user device or the interface of the medical device; accessing treatment data from the medical device after receiving the query message; providing an interactive session using the virtual assistant or chatbot, the interactive session progressing through the hierarchy of questions with one or more prompts to receive further information until a responsive action is identified, and at least a portion of the treatment data is used as answers to progress through the hierarchy of questions as part of the interactive session; If the response action relates to direct communication, determining an address or number of a clinician device and causing a communication session to be initiated between the application on the user device or the interface of the medical device and the clinician device; If the response action is related to the voice mail system, the person-to-person chat system, or the email system, determining a clinician account and enabling the patient to send a request message for the clinician using the application on the user device or the interface of the medical device; A system that is configured to:

2. The system of claim 1 , wherein the processor is further configured to incorporate at least a portion of the further information from the interactive session with the request message for the clinician.

3. The system of claim 1 , wherein the processor, the memory device, and the interface are located in a cloud computing environment.

4. The system of claim 1 , wherein the query message and the further information are received as speech, and the processor is configured to convert the speech to text.

5. The processor: receiving a clinician response message from the clinician's account for the voice mail system, the person-to-person chat system, or the email system; transmitting the clinician response message to the application on the user device or the interface of the medical device; The system of claim 1 , further configured to:

6. The response actions further include automatic response actions; 2. The system of claim 1, wherein if the response action is associated with the automatic response action, the processor is configured to transmit information indicating the automatic response action to the application on the user device or the interface of the medical device.

7. 7. The system of claim 6, wherein the automated response actions include at least one of answers from a patient guide, answers regarding ordering for medical device consumables, answers regarding the operation of the medical device, or pre-programmed answers regarding general patient health or medical conditions.

8. the response actions further include medical device manufacturer response actions; 2. The system of claim 1, wherein if the response action is associated with the medical device manufacturer response action, the processor is configured to determine an address or number of a manufacturer device and cause a communication session to be initiated between the application on the user device or the interface of the medical device and the manufacturer device.

9. 10. The system of claim 8, wherein the medical device manufacturer response action relates to at least one of a reordering of consumables for the medical device, a technical problem with the medical device, or an operational problem with the medical device.

10. 10. The system of claim 1, wherein the medical device comprises at least one of a peritoneal dialysis machine, a hemodialysis machine, a continuous renal replacement therapy ("CRRT") machine, an infusion pump, or a patient-controlled analgesia ("PCA") machine.

11. The processor: accessing patient data associated with the patient from an electronic medical record after receiving the query message; additionally using at least a portion of the patient data as answers to progress through the hierarchy of questions as part of the interactive session; The system of claim 1 , further configured to:

12. The processor: accessing patient data associated with the patient from an electronic medical record after receiving the query message; including at least a portion of the treatment data or the patient data with the request message for the clinician; The system of claim 1 , further configured to:

13. the treatment data includes at least one of (i) treatment parameters for a dialysis prescription, (ii) results from administering one or more dialysis treatments, (iii) diagnostic information associated with the medical device, or (iv) a current status of the medical device; The system of claim 1 , wherein the patient data includes at least one of electronic medical record information, test results, electronic clinician notes, previous medical diagnoses, patient physiological data, or patient demographic data.

14. The system of claim 1 , wherein the patient inquiry triage data structure hierarchy is configured to be modified based on hospital system or clinic protocols.

15. 1. A virtual assistant / chatbot method for improving clinical workflow for home renal replacement therapy, the method comprising: receiving, at a processor, a query message from an application on a user device or an interface of a medical device; accessing, via the processor, treatment data from the medical device after receiving the query message; Providing an interactive session using a virtual assistant or chatbot via the processor, the interactive session progressing through a hierarchy of questions with one or more prompts to receive further information until a response action is identified, instructions for the virtual assistant or chatbot are stored in a memory device that also stores a patient inquiry triage data structure for the virtual assistant or chatbot, the data structure including a plurality of potential problems related to dialysis or medical device operation, each problem including the questions and a hierarchy of possible answers leading to a response action, the response action including a direct communication connection with a clinician and a communication connection with a voicemail system, a person-to-person chat system, or an email system, and at least a portion of the treatment data is used as an answer to progress through the hierarchy of questions as part of the interactive session; If the response action relates to direct communication, determining, via the processor, an address or number of a clinician device and causing a communication session to be initiated between the application on the user device or the interface of the medical device and the clinician device; If the response action is related to the voice mail system, the person-to-person chat system, or the email system, determining a clinician account and enabling the patient to send a request message for the clinician using the application on the user device or the interface of the medical device; A method comprising:

16. The method of claim 15 , further comprising: via the processor, combining at least a portion of the additional information from the interactive session with the request message for the clinician.

17. The method of claim 15 , wherein the query message and the further information are received as speech, and the method includes converting the speech to text.

18. receiving, at the processor, a clinician response message from the clinician's account for the voice mail system, the person-to-person chat system, or the email system; transmitting the clinician response message via the processor to the application on the user device or the interface of the medical device; 16. The method of claim 15, further comprising:

19. The response actions further include automatic response actions; 16. The method of claim 15, wherein if the response action is associated with the automatic response action, the method further comprises transmitting information indicating the automatic response action to the application on the user device or the interface of the medical device.

20. 20. The method of claim 19, wherein the automated response actions include at least one of a response from a patient guide, a response regarding ordering for medical device consumables, a response regarding the operation of the medical device, or a pre-programmed response regarding general patient health or medical conditions.

21. After receiving the inquiry message, accessing via the processor at least one of a prescribed therapy or program or patient data associated with the patient from an electronic medical record; including, via the processor, at least a portion of the treatment data, the prescribed therapy or program, or the patient data with the request message for the clinician; further comprising the prescribed therapy or program includes treatment parameters for a dialysis prescription, and the treatment data includes at least one of (i) results from administering one or more dialysis treatments, (ii) diagnostic information associated with the medical device, or (iii) a current status of the medical device; 16. The method of claim 15, wherein the patient data includes at least one of electronic medical record information, test results, electronic clinician notes, previous medical diagnoses, patient physiological data, or patient demographic data.

Images