Leave No Patient Behind: Enhancing Medication Recommendation for Rare Disease Patients
- URL: http://arxiv.org/abs/2403.17745v2
- Date: Sun, 11 Aug 2024 07:32:14 GMT
- Title: Leave No Patient Behind: Enhancing Medication Recommendation for Rare Disease Patients
- Authors: Zihao Zhao, Yi Jing, Fuli Feng, Jiancan Wu, Chongming Gao, Xiangnan He,
- Abstract summary: We propose a novel model called Robust and Accurate REcommendations for Medication (RAREMed) to enhance accuracy for rare diseases.
It employs a transformer encoder with a unified input sequence approach to capture complex relationships among disease and procedure codes.
It provides accurate drug sets for both rare and common disease patients, thereby mitigating unfairness in medication recommendation systems.
- Score: 47.68396964741116
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Medication recommendation systems have gained significant attention in healthcare as a means of providing tailored and effective drug combinations based on patients' clinical information. However, existing approaches often suffer from fairness issues, as recommendations tend to be more accurate for patients with common diseases compared to those with rare conditions. In this paper, we propose a novel model called Robust and Accurate REcommendations for Medication (RAREMed), which leverages the pretrain-finetune learning paradigm to enhance accuracy for rare diseases. RAREMed employs a transformer encoder with a unified input sequence approach to capture complex relationships among disease and procedure codes. Additionally, it introduces two self-supervised pre-training tasks, namely Sequence Matching Prediction (SMP) and Self Reconstruction (SR), to learn specialized medication needs and interrelations among clinical codes. Experimental results on two real-world datasets demonstrate that RAREMed provides accurate drug sets for both rare and common disease patients, thereby mitigating unfairness in medication recommendation systems.
Related papers
- Contrastive Learning on Medical Intents for Sequential Prescription Recommendation [7.780844394603662]
Attentive Recommendation with Contrasted Intents (ARCI) is designed to capture the different but coexisting temporal paths across a shared sequence of visits.
We conducted experiments on two real-world datasets for the prescription recommendation task using both ranking and classification metrics.
arXiv Detail & Related papers (2024-08-13T20:10:28Z) - CIDGMed: Causal Inference-Driven Medication Recommendation with Enhanced Dual-Granularity Learning [10.60553153370577]
Medication recommendation aims to integrate patients' long-term health records to provide accurate and safe medication combinations.
Existing methods often fail to deeply explore the true causal relationships between diseases/procedures and medications.
We propose the Causal Inference-driven Dual-Granularity Medication Recommendation method (CIDGMed)
arXiv Detail & Related papers (2024-03-01T08:50:27Z) - Automatic diagnosis of knee osteoarthritis severity using Swin
transformer [55.01037422579516]
Knee osteoarthritis (KOA) is a widespread condition that can cause chronic pain and stiffness in the knee joint.
We propose an automated approach that employs the Swin Transformer to predict the severity of KOA.
arXiv Detail & Related papers (2023-07-10T09:49:30Z) - Knowledge-Driven New Drug Recommendation [88.35607943144261]
We develop a drug-dependent multi-phenotype few-shot learner to bridge the gap between existing and new drugs.
EDGE eliminates the false-negative supervision signal using an external drug-disease knowledge base.
Results show that EDGE achieves 7.3% improvement on the ROC-AUC score over the best baseline.
arXiv Detail & Related papers (2022-10-11T16:07:52Z) - Conditional Generation Net for Medication Recommendation [73.09366442098339]
Medication recommendation targets to provide a proper set of medicines according to patients' diagnoses, which is a critical task in clinics.
We propose Conditional Generation Net (COGNet) which introduces a novel copy-or-predict mechanism to generate the set of medicines.
We validate the proposed model on the public MIMIC data set, and the experimental results show that the proposed model can outperform state-of-the-art approaches.
arXiv Detail & Related papers (2022-02-14T10:16:41Z) - Clinical Outcome Prediction from Admission Notes using Self-Supervised
Knowledge Integration [55.88616573143478]
Outcome prediction from clinical text can prevent doctors from overlooking possible risks.
Diagnoses at discharge, procedures performed, in-hospital mortality and length-of-stay prediction are four common outcome prediction targets.
We propose clinical outcome pre-training to integrate knowledge about patient outcomes from multiple public sources.
arXiv Detail & Related papers (2021-02-08T10:26:44Z) - PREMIER: Personalized REcommendation for Medical prescrIptions from
Electronic Records [8.365167718547296]
We design a two-stage attention-based personalized medication recommender system called PREMIER.
Our system takes into account the interactions among drugs in order to minimize the adverse effects for the patient.
Experiment results on MIMIC-III and a proprietary outpatient dataset show that PREMIER outperforms state-of-the-art medication recommendation systems.
arXiv Detail & Related papers (2020-08-28T04:48:32Z) - Learning-based Computer-aided Prescription Model for Parkinson's
Disease: A Data-driven Perspective [61.70045118068213]
We build a dataset by collecting symptoms of PD patients, and their prescription drug provided by neurologists.
Then, we build a novel computer-aided prescription model by learning the relation between observed symptoms and prescription drug.
For the new coming patients, we could recommend (predict) suitable prescription drug on their observed symptoms by our prescription model.
arXiv Detail & Related papers (2020-07-31T14:34:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.