Techniques for evaluating dynamically modified plans are provided. A selection of a treatment plan template is received, where the treatment plan template specifies a plurality of treatment stages, where each treatment stage defines a plurality of treatment options. A plurality of modifications to the treatment plan template is generated. It is determined, for each respective modification of the plurality of modifications, whether the respective modification is permissible, based on one or more predefined institutional criteria. Upon determining that a first modification of the plurality of modifications is permissible, a first treatment plan is generated based on the first modification to the treatment plan template. Further, a first predicted efficacy measure is generated for the first treatment plan based on analyzing a knowledge graph. Finally, the first treatment plan is provided, along with at least an indication of the first predicted efficacy measure.

Methods and systems for processing records include extracting feature vectors from words in an unstructured portion of a record. The feature vectors are weighted based similarity to a topic vector from a structured portion of the record associated with the unstructured portion. The weighted feature vectors are classified using a machine learning model to determine respective probability vectors that assign a probability to each of a set of possible relations for each feature vector. Relations between entities are determined within the record based on the probability vectors. An action is performed responsive to the determined relations.

Methods and systems for processing records include extracting feature vectors from words in an unstructured portion of a record. The feature vectors are weighted based similarity to a topic vector from a structured portion of the record associated with the unstructured portion. The weighted feature vectors are classified using a machine learning model to determine respective probability vectors that assign a probability to each of a set of possible relations for each feature vector. Relations between entities are determined within the record based on the probability vectors. An action is performed responsive to the determined relations.

Machine-learning based recommendation engines are configured to execute machine-learning models to generate recommendations as output for a user based at least in part on functional data received at the recommendation engine. The recommendation engine is further configured to automatically determine the relative importance of one or more functional data entries in generating the recommendation. Moreover, the recommendation engine executes additional machine-learning models, including a machine-learning model trained to avoid negative outcomes, and an opportunity-based machine-learning model to identify alternative recommendation options based on alternative training logic.

Machine-learning based recommendation engines are configured to execute machine-learning models to generate recommendations as output for a user based at least in part on functional data received at the recommendation engine. The recommendation engine is further configured to automatically determine the relative importance of one or more functional data entries in generating the recommendation. Moreover, the recommendation engine executes additional machine-learning models, including a machine-learning model trained to avoid negative outcomes, and an opportunity-based machine-learning model to identify alternative recommendation options based on alternative training logic.

Exemplary embodiments described in this disclosure are generally directed to systems and methods for detecting alertness of a driver of a vehicle. In one exemplary method, a driver alertness detection system determines whether a driver of a vehicle is susceptible to lagophthalmos. If the driver is susceptible to lagophthalmos, the driver alertness detection system may evaluate an alertness state of the driver by disregarding an eyelid status of the driver and monitoring biometrics of the driver such as, a heart rate and/or a breathing pattern. Alternatively, the driver alertness detection system may evaluate an alertness state of the driver by placing a higher priority on the biometrics of the driver than on the eyelid status. However, if the driver is not susceptible to lagophthalmos, the driver alertness detection system evaluates the alertness state by placing a higher priority on the eyelid status than on the biometrics of the driver.

In accordance with various embodiments, provided is a scalp management service provision server for providing a hair loss prevention service and scalp care service for a user, including: a DB management unit interlocked with the scalp management service provision server and configured to obtain a scalp image of the user from a scalp care device including a camera; a scalp condition diagnosis unit configured to determine a scalp condition of the user based on the obtained scalp image; a hair condition diagnosis unit configured to determine a hair condition of the user based on the obtained scalp image; a hair loss diagnosis unit configured to provide a current hair loss progress degree of the user and a hair loss prediction simulation of the user based on the scalp condition and the hair condition; a scalp care solution provision unit configured to provide information about a scalp analysis result and hair analysis result of the user through a user terminal of the user and to determine a scalp care product for the user from among a number of scalp care products included in a scalp care product DB; and a remote care device control unit configured to remotely control the scalp care device with a control value determined according to the scalp analysis result and hair analysis result of the user.

In accordance with various embodiments, provided is a scalp management service provision server for providing a hair loss prevention service and scalp care service for a user, including: a DB management unit interlocked with the scalp management service provision server and configured to obtain a scalp image of the user from a scalp care device including a camera; a scalp condition diagnosis unit configured to determine a scalp condition of the user based on the obtained scalp image; a hair condition diagnosis unit configured to determine a hair condition of the user based on the obtained scalp image; a hair loss diagnosis unit configured to provide a current hair loss progress degree of the user and a hair loss prediction simulation of the user based on the scalp condition and the hair condition; a scalp care solution provision unit configured to provide information about a scalp analysis result and hair analysis result of the user through a user terminal of the user and to determine a scalp care product for the user from among a number of scalp care products included in a scalp care product DB; and a remote care device control unit configured to remotely control the scalp care device with a control value determined according to the scalp analysis result and hair analysis result of the user.

A medical treatment device is configured to be used during a treatment session at a first location and includes a medical treatment component configured to perform at least one of hemodialysis, hemofiltration, and peritoneal dialysis on a patient during the treatment session at the first location. The device also includes a monitoring system configured to receive data from one or more sensors connected to the monitoring system, and to confirm a presence of an authorized helper at the first location. A user interface permits an operator to control functions of the medical treatment component and the monitoring system is configured to perform the presence confirmation automatically and at the predefined time intervals during the treatment session. The monitoring system is also configured to generate an alarm and to cause the medical treatment component to go into a failsafe operational mode.

Artificial intelligence based systems and methods for analyzing user-specific data to predict user-specific skin or hair conditions. User-specific data of a user is received at a scalp and hair analysis application and defines a scalp or hair region of the user including last wash data of the user and at least one other factor of the user. An artificial intelligence based learning model, trained with training data regarding scalp and hair regions of respective individuals, analyzes the user-specific data to generate a scalp or hair prediction value corresponding to the scalp or hair region of the user. The application generates, based on the scalp or hair prediction value, a user-specific treatment designed to address at least one feature based on the scalp or hair prediction value of the user's scalp or hair region.