Smart dosing for cancer therapy
AssigneeOptimDosing, LLC
InventorsDavid Inwald, Kenneth I. Kohn
Life of this patent
Estimating the term…
Abstract
A method of dosing cancer therapies, by collecting patient data including cancer therapies/drugs to be taken, analyzing the data in view of dosing criteria established based on outside data, and determining a dose for each cancer therapy/drug taken. A logic engine for dosing cancer therapies, including an algorithm stored on non-transitory computer readable media for collecting clinical trial data to establish criteria for dosing cancer therapies/drugs to a single patient and patient data and storing the clinical trial data and patient data in a database, analyzing the patient data in view of criteria established from the clinical trial data, and determining a dose for each cancer therapy/drug. A method of adjusting treatment of a cancer patient.
Claims16
A method of dosing cancer therapies, including the steps of:
- a healthcare professional collecting and inputting patient data including cancer therapies and drugs to be taken into a database with a central artificial intelligence (AI) stored on computer readable media;
- the central AI analyzing the data in view of dosing criteria established based on outside data of clinical trial data from outside databases of clinics, electronic medical records, pharmaceutical companies, private databases, and contract research organizations (CROs),
- extracting with the AI all features relating variables that effect drug metabolism and creates a model relating dosing to patient condition and effect of cancer therapies and drugs on the condition that effect efficacy and toxicity of all cancer therapies and drugs taken, wherein the variables are age of patient, weight of patient, known side effects of cancer therapies/drugs alone and in combinations with other cancer therapies/drugs, known toxicity range as related to effective dose (ED 50) and dose response points of interest, efficacy ranges, tumor scans, and chronic treatment effect versus acute treatment,
- identifying with the AI nearest neighbors of persons having similar patient data and/or underwent a treatment plan with similar cancer therapies or drug combinations and identifies related study and trial data with a K-Nearest Neighbor algorithm,
- comparing with the AI patient data to neighboring patient data with weighting schemes;
- and
- calculating with the central AI, for each dosage, classifications with confidence intervals, the generic drug model is ran using the same set of dosages mapped out to the same classifiers used when evaluating context data, the outputs from both models are weighted and combined to determine the optimal dose while simultaneously maximizing therapeutic effect and minimizing adverse effects for the combination of cancer therapies and drugs taken, and displaying the dose in a readable report for a practitioner all in real time.
A logic engine for dosing cancer therapies, comprising an algorithm stored on non-transitory computer readable media for collecting clinical trial data from outside databases of clinics, electronic medical records, pharmaceutical companies, private databases, and contract research organizations (CROs) to establish criteria for dosing cancer therapies/drugs to a single patient and patient data and storing the clinical trial data and patient data in a database, analyzing the patient data in view of criteria established from the clinical trial data with artificial intelligence (AI), extracting with the AI all features relating variables that effect drug metabolism and creates a model relating dosing to patient condition and effect of cancer therapies and drugs on the condition that effect efficacy and toxicity of all cancer therapies and drugs taken, wherein the variables include age of patient, weight of patient, known side effects of cancer therapies/drugs alone and in combinations with other cancer therapies/drugs, known toxicity range as related to effective dose (ED 50) and dose response points of interest, efficacy ranges, and chronic treatment effect versus acute treatment, identifying with the AI nearest neighbors of persons having similar patient data and/or underwent a treatment plan with similar cancer therapies or drug combinations and identifies related study and trial data with a K-Nearest Neighbor algorithm, comparing with the AI patient data to neighboring patient data with weighting schemes, and determining a dose for each cancer therapy/drug, and providing with said algorithm an output in the form of a practitioner readable report all in real time.
A method of adjusting treatment of a cancer patient, including the steps of:
- a patient inputting data about nutrition, medication, lifestyle, symptoms, and user defined metrics in an application stored on non-transitory computer readable media;
- a central artificial intelligence (AI) integrating data from outside wearable medical devices, outside databases of clinical trial data from clinics, electronic medical records, pharmaceutical companies, private databases, and contract research organizations (CROs), and updated patient scans;
- performing with the central AI an analysis on the data by the AI extracting all features relating variables that effect drug metabolism and creating a model relating dosing to patient condition and effect of cancer therapies and drugs on the condition that effect efficacy and toxicity of all cancer therapies and drugs taken, wherein the variables include age of patient, weight of patient, known side effects of cancer therapies/drugs alone and in combinations with other cancer therapies/drugs, known toxicity range as related to effective dose (ED 50) and dose response points of interest, efficacy ranges, and chronic treatment effect versus acute treatment, and by the AI identifying nearest neighbors of persons having similar patient data and/or underwent a treatment plan with similar cancer therapies or drug combinations and identifying related study and trial data with a K-Nearest Neighbor algorithm, comparing with the AI patient data to neighboring patient data with weighting schemes;
- outputting with the AI a result from the data to medical professionals;
- and
- the medical professionals adjusting the treatment of the patient based on the data all in real time.
Dependencies are inferred from the claim text.