Techniques for providing interactive clinical decision support for drug dosage reduction
Examples described herein generally relate to recommending drug dosage reductions for a patient. A computer system may generate an initial non-linear glide path of recommended dosages starting at an initial dosage of a drug for a patient and ending at a goal dosage at an estimated time of arrival. The system may receive periodic patient monitoring including at least one drug withdrawal scale score, anxiety scale score, and indicated side effect. The system may determine, using one or more machine learning algorithms, a revised glide path based on a data record for the patient, the at least the drug withdrawal scale score and the at least one anxiety scale score for the patient. The system may recommend at least one medication or therapy for the indicated side effect. The system may determine a prescription adjustment based on the revised glide path.
1 . A method of treating withdrawal symptoms associated with reduced dosage of a drug, comprising:
providing a patient, with access to a prescription support application configured to:
generate, an initial non-linear glide path of recommended dosages starting at an initial dosage of the drug associated with the withdrawal symptoms of the patient and ending at a goal dosage at an estimated time of arrival based on a guideline for the drug;
receive, from a patient interface, periodic patient monitoring including at least one drug withdrawal scale score, at least one anxiety scale score, and at least one indicated side effect;
determine, using one or more machine learning algorithms, a revised glide path starting at a current dosage of the drug associated with the withdrawal symptoms and ending at the goal dosage at a new estimated time of arrival based on a data record for the patient, the at least one drug withdrawal scale score and the at least one anxiety scale score for the patient, wherein determining the revised glide path comprises:
estimating a success probability of the initial non-linear glide path for the patient by applying a machine-learning model trained on labeled past outcomes of glide paths for other patients with withdrawal symptoms for the drug to the data record for the patient, the at least one drug withdrawal scale score, and the at least one anxiety scale score for the patient; and
determining that the estimated success probability of the initial non-linear glide path is less than a threshold probability;
recommending at least one medication or therapy for the indicated side effect;
determining a prescription adjustment of the drug for the patient based on the revised glide path; and
administering doses of the drug to the patient according to the adjusted prescription based on the revised glide path until reaching the goal dosage,
wherein the withdrawal symptoms are associated with a diagnosed Opioid Use Disorder, wherein the Opioid Use Disorder is specified for an opioid pain medication previously prescribed to the patient, wherein the drug is the opioid pain medication previously prescribed to the patient, and wherein the drug comprises a synthetic opioid other than methadone.
2 . The method of claim 1 , wherein generating the initial non-linear glide path of recommended dosages comprises:
adjusting the initial non-linear glide path using a second machine-learning model trained to select adjustments that improve the success probability.
3 . The method of claim 1 , wherein determining the revised glide path, using one or more machine learning algorithms, comprises adjusting the initial glide path using a second machine-learning model trained to select adjustments that improve the estimated success probability.
4 . The method of claim 1 , wherein determining, using one or more machine learning algorithms, the revised glide path comprises adjusting the estimated time of arrival.
5 . The method of claim 1 , wherein determining the prescription adjustment based on the revised glide path comprises:
determining a current supply of prescribed medication that can satisfy doses to the revised glide path; and
recommending prescribing additional doses for unsatisfied doses of the revised glide path.
6 . The method of claim 1 , wherein recommending the at least one medication or therapy for the indicated side effect comprises using an artificial neural network trained to select from a set of treatments based on the indicated side effect, the drug, and the patient record.
7 . The method of claim 1 , wherein the initial non-linear glide path includes an initial linear phase, a gradual adjustment phase, and a soft landing phase.
8 . The method of claim 1 , wherein the drug is one of: an opioid, a benzodiazepine, a non-benzodiazepine sleep medication, an antidepressant, or a proton pump inhibitor.
9 . A system for treating withdrawal symptoms associated with a reduced dosage of a drug, comprising:
a memory storing computer-executable instructions; and
a processor configured to execute the computer-executable instructions to:
generate an initial non-linear glide path of recommended dosages starting at an initial dosage of the drug associated with the withdrawal symptoms of a patient and ending at a goal dosage at an estimated time of arrival based on a guideline for the drug;
receive, from a patient interface, periodic patient monitoring including at least one drug withdrawal scale score, at least one anxiety scale score, and at least one indicated side effect;
determine, using one or more machine learning algorithms, a revised glide path starting at a current dosage of the drug associated with the withdrawal symptoms and ending at the goal dosage at a new estimated time of arrival based on a data record for the patient, the at least one drug withdrawal scale score and the at least one anxiety scale score for the patient, wherein to determine the revised glide path, the processor is configured to:
estimate a success probability of the initial non-linear glide path for the patient by applying a machine-learning model trained on labeled past outcomes of glide paths for other patients with withdrawal symptoms for the drug to the data record for the patient, the at least one drug withdrawal scale score, and the at least one anxiety scale score for the patient; and
determine that the estimated success probability of the initial non-linear glide path is less than a threshold probability;
recommend at least one medication or therapy for the indicated side effect; and
determine a prescription adjustment of the drug for the patient based on the revised glide path,
wherein the drug is a drug being used by the patient based on a previous prescription, wherein the prescription adjustment for the patient is a number of doses of the drug for administration to the patient until reaching the goal dosage, wherein the withdrawal symptoms are associated with a diagnosed Opioid Use Disorder, wherein the Opioid Use Disorder is specified for an opioid pain medication previously prescribed to the patient, wherein the drug is the opioid pain medication previously prescribed to the patient, and wherein the drug comprises a synthetic opioid other than methadone.
10 . The system of claim 9 , wherein the processor is configured to execute the instructions to:
adjust the initial glide path using a second machine-learning model trained to select adjustments that improve the success probability.
11 . The system of claim 9 , wherein the processor is configured to execute the instructions to adjust the initial glide path using a second machine-learning model trained to select adjustments that improve the estimated success probability.
12 . The system of claim 9 , wherein the processor is configured to execute the instructions to adjust the estimated time of arrival.
13 . The system of claim 9 , wherein the processor is configured to execute the instructions to:
determine a current supply of prescribed medication that can satisfy doses according to the revised glide path; and
recommend prescribing additional doses for unsatisfied doses of the revised glide path.
14 . The system of claim 9 , wherein the processor is configured to execute the instructions to use an artificial neural network trained to select from a set of treatments based on the indicated side effect, the drug, and the patient record.
15 . The system of claim 9 , wherein the initial non-linear glide path includes an initial linear phase, a gradual adjustment phase, and a soft landing phase.
16 . The system of claim 9 , wherein the drug is one of: an opioid, a benzodiazepine, a non-benzodiazepine sleep medication, an antidepressant, or a proton pump inhibitor.
17 . A non-transitory computer readable medium storing computer-executable instructions that when executed by a processor cause the processor to:
generate an initial non-linear glide path of recommended dosages for treating withdrawal symptoms of a patient starting at an initial dosage of a drug associated with the withdrawal symptoms of the patient and ending at a goal dosage at an estimated time of arrival based on a guideline for the drug;
receive, from a patient interface, periodic patient monitoring including at least one drug withdrawal scale score, at least one anxiety scale score, and at least one indicated side effect;
determine, using one or more machine learning algorithms, a revised glide path starting at a current dosage of the drug prescribed to the patient and ending at the goal dosage at a new estimated time of arrival based on a data record for the patient, the at least one drug withdrawal scale score and the at least one anxiety scale score for the patient, wherein the instructions to determine the revised glide path comprise instructions to:
estimate a success probability of the initial non-linear glide path for the patient by applying a machine-learning model trained on labeled past outcomes of glide paths for other patients with withdrawal symptoms for the drug to the data record for the patient, the at least one drug withdrawal scale score, and the at least one anxiety scale score for the patient; and
determine that the estimated success probability of the initial non-linear glide path is less than a threshold probability;
recommend at least one medication or therapy of the indicated side effect;
determine a prescription adjustment of the drug for the patient based on the revised glide path; and
issue an updated prescription for administration of doses of the drug to the patient based on the revised glide path until reaching the goal dosage,
wherein the withdrawal symptoms are associated with a diagnosed Opioid Use Disorder, wherein the Opioid Use Disorder is specified for an opioid pain medication previously prescribed to the patient, wherein the drug is the opioid pain medication previously prescribed to the patient, and wherein the drug comprises a synthetic opioid other than methadone.
18 . The system of claim 9 , wherein the number of doses of the drug includes non-standard doses in increments smaller than commercially available units.
19 . The method of claim 1 , wherein the one or more machine learning algorithms comprise a supervised learning model.
20 . The method of claim 1 , wherein the one or more machine learning algorithms comprise an unsupervised learning model.