Smart dosing for cancer therapy

A computer-implemented method of tracking triggers of symptoms in cancer patients, including the steps of:

• receiving, by a processor on a mobile device chosen from the group consisting of a smart phone and tablet computer, data from a patient about nutrition, medication, lifestyle, symptoms due to cancer therapy and drugs taken, pain, and user defined metrics from a user interface of a symptom tracking application stored on non-transitory computer readable media;
• analyzing the received data with multiple regressions that find patterns between how the patient lives, the cancer therapy they are taking, and how they feel;
• outputting, by the processor, a result from the data identifying daily activities that effect the patient's symptoms due to cancer therapy and displaying the result to the patient on the mobile device;
• the symptom tracking application being in electronic communication with a database having a central artificial intelligence (AI) stored on computer readable media, the database including patient data collected by a healthcare professional including cancer therapies and drugs taken;
• the central AI analyzing the patient data and data from said symptom tracking application 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 central AI 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 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 central AI nearest neighbors of persons having similar patient data, underwent a treatment plan with similar cancer therapies or drug combinations, and used a different dose of cancer therapies or drugs and their symptoms improved, and identifying related study and trial data with a K-Nearest Neighbor algorithm,
• comparing with the central AI patient data to neighboring patient data with a weighting scheme by assigning a weight to each parameter of patient data and neighboring patient data and producing a normalized distance representing a difference metric between the patient and the nearest neighbors;
• calculating with the central AI, for each dosage at all possible dosing ranges, 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;
• and
• adjusting, by medical professionals, the cancer therapy of the patient based on the analysis of the symptom tracking application and central AI in order to reduce symptoms experienced by the patient during cancer therapy.

A computer-implemented method of adjusting treatment of a cancer patient, including the steps of:

• receiving, by a processor on a mobile device chosen from the group consisting of a smart phone and tablet computer, data from a patient about nutrition, medication, lifestyle, symptoms due to cancer therapy and drugs taken, and user defined metrics from a user interface of a symptom tracking application stored on non-transitory computer readable media;
• integrating, by the processor, data from external devices and external databases;
• analyzing, by the processor, the received data with multiple regressions that find patterns between how the patient lives, the cancer therapy they are taking, and how they feel;
• outputting, by the processor, a result from the data identifying daily activities that effect the patient's symptoms due to cancer therapy to medical professionals;
• the symptom tracking application being in electronic communication with a database having a central artificial intelligence (AI) stored on computer readable media, the database including patient data collected by a healthcare professional including cancer therapies and drugs taken;
• the central AI analyzing the patient data and data from said symptom tracking application 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 central AI 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 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 central AI nearest neighbors of persons having similar patient data, underwent a treatment plan with similar cancer therapies or drug combinations, and used a different dose of cancer therapies or drugs and their symptoms improved, and identifying related study and trial data with a K-Nearest Neighbor algorithm,
• comparing with the central AI patient data to neighboring patient data with a weighting scheme by assigning a weight to each parameter of patient data and neighboring patient data and producing a normalized distance representing a difference metric between the patient and the nearest neighbors;
• calculating with the central AI, for each dosage at all possible dosing ranges, 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;
• and
• adjusting, by medical professionals, the cancer therapy of the patient based on the analysis of the symptom tracking application and central AI in order to reduce symptoms experienced by the patient during cancer therapy.