Construction of a Non-Mutually Exclusive Decision Tree for Medication Recommendation of Chronic Heart Failure

Abstract

Objective: Although guidelines have recommended standardized drug treatment for heart failure (HF), there are still many challenges in making the correct clinical decisions due to the complicated clinical situations of HF patients. Each patient would satisfy several recommendations, meaning the decision tree of HF treatment should be nonmutually exclusive, and the same patient would be allocated to several leaf nodes in the decision tree. In the current study, we aim to propose a way to ensemble a nonmutually exclusive decision tree for recommendation system for complicated diseases, such as HF. Methods: The nonmutually exclusive decision tree was constructed via knowledge rules summarized from the HF clinical guidelines. Then similar patients were defined as those who followed the same pattern of leaf node allocation according to the decision tree. The frequent medication patterns for each similar patient were mined using the Apriori algorithms, and we also carried out the outcome prognosis analyses to show the capability for the evidence-based medication recommendations of our nonmutually exclusive decision tree. Results: Based on a large database that included 29,689 patients with 84,705 admissions, we tested the framework for HF treatment recommendation. In the constructed decision tree, the HF treatment recommendations were grouped into two independent parts. The first part was recommendations for new cases, and the second part was recommendations when patients had different historical medication. There are 14 leaf nodes in our decision tree, and most of the leaf nodes had a guideline adherence of around 90%. We reported the top 10 popular similar patients, which accounted for 32.84% of the whole population. In addition, the multiple outcome prognosis analyses were carried out to assess the medications for one of the subgroups of similar patients. Our results showed even for the subgroup of the same similar patients that no one medication pattern would benefit all outcomes. Conclusion: In the present study, the methodology to construct a nonmutually exclusive decision tree for medication recommendations for HF and its application in CDSS was proposed. Our framework is universal for most diseases and could be generally applied in developing the CDSS for treatment.

Keywords: chronic heart failure; clinical decision support system (CDSS); decision tree; machine learning; medication recommendation; treatment.

FIGURE 1

The workflow to construct and apply nonmutually exclusive decision tree. The workflow included two parts. The first part is the procedure of the construction of nonmutually exclusive decision tree, denoted as “knowledge model.” The second part is the application of the nonmutually exclusive decision tree, which included tree components: the fine group of the patients, the frequent medication patterns mining for each patients group, and the multiple outcomes prognoses analyses.

FIGURE 2

The schematic diagram of an n-day electronic health record (EHR) for inpatient. The data would be segmented into n fragments as indicated by the vertical dash lines, and the colorful boxes represent the different categories of information: d for the prescript medications, c for the results of the laboratory tests, n for the nursing records, and r for the records of the ward rounds.

FIGURE 3

The integrated knowledge-based decision trees for heart failure (HF) with reduced ejection fraction (HFrEF): (A) the decision tree for new cases; (B) the decision tree for cases with initial treatment of HFrEF. The nonmutually exclusive branches were labeled with the red *. For (B), the medications were grouped into two independent parts as indicated by the dashed boxes. The leaf nodes were colored in green, indicating the medications for each branch. The details for decision condition 1 was the existence of congestion symptom; for decision condition 2, the existence of hyponatremia or the tendency of renal function impairment; for decision condition 3, the whether the congestion symptoms got improved; for decision condition 4, whether the heart failure symptoms got improved; for decision condition 5, whether the LVEF ≤40% and no symptom improvement with a combination of multiple medications; for decision condition 6, whether the eGFR ≥30 ml min⁻¹,·1.73 m⁻², and the blood potassium <5.0 mmol/L; for decision condition 7, whether the NYHA was between II and III and the tolerance of ACEI/ARB (the systolic blood pressure ≥95 mmHg); for decision condition 8, whether the LVEF ≤35%, the sinus heart rate ≥70 beats/min, and β-receptor blocker reached the target dose (or the maximum tolerated dose). Abbreviations: eGFR, estimated glomerular filtration rate; NYHA, the New York Heart Association Functional Classification; LVEF, left ventricular ejection fraction.

FIGURE 4

Distribution of the mined frequent historical medications for all HFrEF clinical records (132,158 in total). The top 10 medications were listed with the name and the proportions. Please see Table 1 for the abbreviations of the medicines. The medicines labeled in red were not considered as historical medication strategies in the decision trees for HFrEF.

FIGURE 5

The expansion of the knowledge-based decision tree for cases with initial treatment of HFrEF. The nonmutually exclusive branches were labeled with red *. The leaf nodes were colored in green, indicating the medications for each branch. The decision condition 9 was whether the systolic blood pressure >90 mmHg or the heart rate >60 beats/min. The decision condition 10 was whether the systolic blood pressure >90 mmHg or the heart rate >60 beats/min.

FIGURE 6

The prognosis’s analyses for the subgroup (allocated to leaf nodes 5, 7, 10, 12, and 14): (A,C) showed the occurrence ratios of each outcome for different medications, where the x-axis indicted the different outcomes, the y-axis indicated the occurrence ratio, and the color denoted different medications. (B,D) were 2D heatmaps indicating the calibrated coefficients of each medication for different outcomes, where the x-axis showed the medications, the y-axis indicated the outcomes, and the color was in proportion to the coefficients. Red colors denote the risk factors for the outcomes, and the blue ones denote the protective factors. The coefficients with p-value <0.05 were labeled with red *.