Abstract: Techniques for patient population flow modeling are disclosed, where such modeling can provide insights for future trends among a patient population, e.g., to facilitate allocation of resources for the patient population or to inform treatment recommendations for patients. A flow model can be used on dialysis patient populations where the patients are grouped into a compartment according to a certain criterion (or given criteria), where each compartment corresponds to the number of patients in each group, and where the number of compartments can vary depending on the given criteria. A model can then be used to describe the transition rates between the different compartments, as well as influx and efflux within each compartment. Such a model can be used, by way of example, to investigate the impact of sodium-glucose co-transporter 2 (SGLT2) inhibitors on the population dynamics of end-stage renal disease patients.

Abstract: A method for mitigating the spread of infectious diseases among dialysis patients is provided. The method comprises: receiving, by a prediction system and from a medical facility, individual treatment data indicating dialysis treatment information associated with a patient undergoing dialysis treatment; receiving, by the prediction system and from a blood testing laboratory, individual lab data indicating blood analysis information associated with the patient; determining, by the prediction system, disease analysis results for the patient based on inputting the individual treatment data and the individual lab data into a disease prediction machine learning (ML) model, wherein the disease analysis results indicate a likelihood of the patient being infected with a contagious disease; and providing, by the prediction system and to the medical facility, instructions indicating one or more responsive actions based on the disease analysis results.

Abstract: An apparatus used in analyzing spent dialysate includes at least a first surface configured to accommodate a dialysate drain bag in a first predetermined position, and at least a second surface configured to accommodate a dialysate analysis device in a second predetermined position, such that when the dialysate drain bag is in the first predetermined position and the dialysate analysis device is in the second predetermined position, a light sensor of the dialysate analysis device is positioned to sense light passing through the dialysate drain bag.

Abstract: Techniques for vascular access identification and validation are disclosed. The techniques include: directly or indirectly acquiring an acquired value for a parameter that is a function of oxygen saturation (SO2) of a sample of blood in or obtained from a vascular access device (VAD) disposed in a subject; performing an evaluation of the acquired value at least by comparing the acquired value with one or more reference values; and responsive to the evaluation of the acquired value, assigning an identity classification to the VAD, wherein the identity classification is one of a central venous catheter (CVC), an arteriovenous access device (AVA), or another class of VAD.

Abstract: The described technology may include processes to model acid-base homeostasis in normal patients and under acid-base disorder conditions. In one embodiment, a method may include an acid-base homeostasis analysis. The method may include, via a processor of a computing device: providing a physiological acid-base model configured to model acid-base homeostasis of a virtual patient, the physiological acid-base model to: determine a plurality of operating parameters for an HCO3/CO2 buffering system having renal and pulmonary regulatory mechanisms, determine acid-base information comprising a bicarbonate concentration, a carbon dioxide concentration, and a free hydrogen ions concentration via simulating the HCO3/CO2 buffering system, and determine predicted patient information based on the acid-base information. Other embodiments are described.

Abstract: This disclosure teaches the generation of multiple recipes for patients with chronic kidney disease. The recipes are generated by application of a large language model to patient data, including both medical and preference data. The recipes are verified by a dietician and may be used to generate shopping lists and instructions for an automated food preparation device.

Abstract: Techniques and apparatus for generating, performing, and evaluating virtual clinical trials that include clinic modules to represent real-world operational aspects of trial entities are described. In one embodiment, for example, an apparatus may include at least one memory, and logic coupled to the at least one memory. The logic may be configured to generate a plurality of avatars configured to model a health condition associated with a population of patients, and to perform a virtual clinical trial to simulate a course of treatment for the plurality of avatars, the virtual clinical trial to include at least one clinic module associated with at least one event and a probability for the at least one event, the at least one event to model an operational aspect of an entity of the virtual clinical trial. Other embodiments are described.

Abstract: The present teachings generally include devices, systems, methods, and computer-program products for determining a fluid status of patients using bioimpedance measurements and the like. In general, aspects of the present teachings may include one or more of: an eight-point electrode bioimpedance device including two (wired or wireless) handles with integrated sensors to measure distance, e.g., so that body height and segmental length can be measured; techniques to determine the fluid status of a patient from bioimpedance measurements of the patient's legs; improved techniques for determining fluid overload (or otherwise determining fluid status) using a ratio of extracellular volume (ECV) to total body water (TBW); and using body segmental resistances to determine fluid status and/or fluid volume.

Abstract: Techniques for real-time intradialytic hypotension (IDH) prediction are disclosed. A system obtains historical hemodialysis treatment data that is segmented into sets of machine learning training data based on temporal proximities to IDH events and trains a machine learning model to predict IDH events based on the sets of machine learning training data.

Abstract: Techniques and apparatus for generating, performing, and evaluating virtual clinical trials that include clinic modules to represent real-world operational aspects of trial entities are described. In one embodiment, for example, an apparatus may include at least one memory, and logic coupled to the at least one memory. The logic may be configured to generate a plurality of avatars configured to model a health condition associated with a population of patients, and to perform a virtual clinical trial to simulate a course of treatment for the plurality of avatars, the virtual clinical trial to include at least one clinic module associated with at least one event and a probability for the at least one event, the at least one event to model an operational aspect of an entity of the virtual clinical trial. Other embodiments are described.

Abstract: Techniques for monitoring fluid volumes during peritoneal analysis include: computing lower abdominal fluid volumes, continuously during a dwell time of a peritoneal dialysis treatment, based at least on bioimpedance data from electrodes positioned on a patient's upper thighs; and computing intraperitoneal volumes, continuously during the dwell time of the peritoneal dialysis treatment, based at least on bioimpedance data from the electrodes positioned on the patient's upper thighs and electrodes positioned on the patient's torso.

Abstract: An apparatus used in analyzing spent dialysate includes: at least one surface configured to accommodate a dialysate drain bag or drain line in a predetermined position; a light source positioned to emit light through the dialysate drain bag or drain line; and a light sensor positioned to sense light emitted by the light source through the dialysate drain bag or drain line.

Abstract: A method for detecting occult hemorrhages is provided. The method includes obtaining a first hematocrit concentration prior to infusing a saline solution into a bloodstream of a patient. The method further includes infusing the saline solution into the bloodstream of the patient and obtaining a second hematocrit concentration after infusing the saline solution into the bloodstream. The method also includes determining a first absolute blood volume based on the first hematocrit concentration and the second hematocrit concentration. In addition, the method includes generating a notification indicating a potential occult hemorrhage based on the first absolute blood volume and a pre-defined absolute blood volume threshold, and providing the notification indicating the potential occult hemorrhage.

Abstract: Techniques for monitoring fluid volumes during peritoneal analysis include: computing lower abdominal fluid volumes, continuously during a dwell time of a peritoneal dialysis treatment, based at least on bioimpedance data from electrodes positioned on a patient's upper thighs; and computing intraperitoneal volumes, continuously during the dwell time of the peritoneal dialysis treatment, based at least on bioimpedance data from the electrodes positioned on the patient's upper thighs and electrodes positioned on the patient's torso.

Abstract: A computing system for determining a systematic training strategy for the user is provided. The computing system includes a user device that uses one or more sensors to obtain partial pressure of oxygen (PO2) levels of a user over a period of time. The user device provides previous PO2 levels to a personalized erythropoiesis model generation computing platform. The computing platform obtains individualized user data for the user indicating or more previous hematocrit and/or hemoglobin measurements for the user. The computing platform determines an individualized erythropoiesis model for the user based on the one or more previous hematocrit and/or hemoglobin measurements and the previous PO2 information, and employs the individualized erythropoiesis model to determine predicted hematocrit and/or hemoglobin measurements. The computing platform performs one or more actions based on the one or more predicted hematocrit and/or hemoglobin measurements.

Abstract: An apparatus used in analyzing spent dialysate includes: at least one surface configured to accommodate a dialysate drain bag or drain line in a predetermined position; a light source positioned to emit light through the dialysate drain bag or drain line; and a light sensor positioned to sense light emitted by the light source through the dialysate drain bag or drain line.

Abstract: Techniques for real-time intradialytic hypotension (IDH) prediction are disclosed. A system obtains historical hemodialysis treatment data that is segmented into sets of machine learning training data based on temporal proximities to IDH events and trains a machine learning model to predict IDH events based on the sets of machine learning training data.

Abstract: The present disclosure relates to a medical functional device or arrangement of components having a first blood circuit for extracorporally withdrawing and reintroducing blood from and to a patient (P), and a second blood circuit for extracorporally withdrawing and reintroducing blood from and to a person (D), wherein both the first blood circuit and the second blood circuit each comprise an arterial line and a venous line. In this, the medical functional device, or the arrangement, comprises at least one connecting device for establishing a fluid communication between the arterial line of the first blood circuit for the patient (P) with the venous line (73) of the second blood circuit for the person (D) and for establishing a fluid communication between the arterial line of the second blood circuit for the person (D) with the venous line of the first blood circuit for the patient (P).

Abstract: A method for determining a next hypoxia-inducible factor prolyl hydroxylase inhibitor (HIF-PHI) dosage for a first patient using a patient HIF-PHI model is provided. The method includes obtaining population patient data indicating HIF-PHI dosages and hemoglobin measurements for the patients. Then, virtual patient avatars are generated based on the population patient data. Each of the virtual patient avatars indicates a set of personalized model parameters for a HIF-PHI model. A plurality of HIF-PHI models are determined for the virtual patient avatars. Using the HIF-PHI models, one or more HIF-PHI treatment schemes for administering the HIF-PHI dosages is determined. Subsequently, the HIF-PHI treatment schemes along with a hematocrit and/or hemoglobin concentration for a patient are used to determine a next HIF-PHI dosage for the patient, and the next HIF-PHI dosage is administered for the patient.

Abstract: A computing system for determining a systematic training strategy for the user is provided. The computing system includes a user device that uses one or more sensors to obtain partial pressure of oxygen (PO2) levels of a user over a period of time. The user device provides previous PO2 levels to a personalized erythropoiesis model generation computing platform. The computing platform obtains individualized user data for the user indicating or more previous hematocrit and/or hemoglobin measurements for the user. The computing platform determines an individualized erythropoiesis model for the user based on the one or more previous hematocrit and/or hemoglobin measurements and the previous PO2 information, and employs the individualized erythropoiesis model to determine predicted hematocrit and/or hemoglobin measurements. The computing platform performs one or more actions based on the one or more predicted hematocrit and/or hemoglobin measurements.