An opponent model for agent-based shared decision-making via a genetic algorithm

Introduction

Shared decision-making (SDM) has received a great deal of attention as an effective way to achieve patient-centered medical care. SDM aims to bring doctors and patients together to develop treatment plans through negotiation. However, time pressure and subjective factors such as medical illiteracy and inadequate communication skills prevent doctors and patients from accurately expressing and obtaining their opponent's preferences. This problem leads to SDM being in an incomplete information environment, which significantly reduces the efficiency of the negotiation and even leads to failure.

Methods

In this study, we integrated a negotiation strategy that predicts opponent preference using a genetic algorithm with an SDM auto-negotiation model constructed based on fuzzy constraints, thereby enhancing the effectiveness of SDM by addressing the problems posed by incomplete information environments and rapidly generating treatment plans with high mutual satisfaction.

Results

A variety of negotiation scenarios are simulated in experiments and the proposed model is compared with other excellent negotiation models. The results indicated that the proposed model better adapts to multivariate scenarios and maintains higher mutual satisfaction.

Discussion

The agent negotiation framework supports SDM participants in accessing treatment plans that fit individual preferences, thereby increasing treatment satisfaction. Adding GA opponent preference prediction to the SDM negotiation framework can effectively improve negotiation performance in incomplete information environments.

Patient and Clinician Perspectives on Shared Decision Making in Vascular Access Selection: A Qualitative Study

RATIONALE & OBJECTIVE

Collaborative approaches to vascular access selection are being increasingly encouraged to elicit patients' preferences and priorities where no unequivocally superior choice exists. We explored how patients, their caregivers, and clinicians integrate principles of shared decision making when engaging in vascular access discussions.

STUDY DESIGN

Qualitative description.

SETTING & PARTICIPANTS

Semistructured interviews with a purposive sample of patients, their caregivers, and clinicians from outpatient hemodialysis programs in Alberta, Canada.

ANALYTICAL APPROACH

We used a thematic analysis approach to inductively code transcripts and generate themes to capture key concepts related to vascular access shared decision making across participant roles.

RESULTS

42 individuals (19 patients, 2 caregivers, 21 clinicians) participated in this study. Participants identified how access-related decisions follow a series of major decisions about kidney replacement therapy and care goals that influence vascular access preferences and choice. Vascular access shared decision making was strengthened through integration of vascular access selection with dialysis-related decisions and timely, tailored, and balanced exchange of information between patients and their care team. Participants described how opportunities to revisit the vascular access decision before and after dialysis initiation helped prepare patients for their access and encouraged ongoing alignment between patients' care priorities and treatment plans. Where shared decision making was undermined, hemodialysis via a catheter ensued as the most readily available vascular access option.

LIMITATIONS

Our study was limited to patients and clinicians from hemodialysis care settings and included few caregiver participants.

CONCLUSIONS

Findings suggest that earlier, or upstream, decisions about kidney replacement therapies influence how and when vascular access decisions are made. Repeated vascular access discussions that are integrated with other higher-level decisions are needed to promote vascular access shared decision making and preparedness.

Improving Initial Medication Adherence to cardiovascular disease and diabetes treatments in primary care: Pilot trial of a complex intervention

Introduction

The Initial Medication Adherence (IMA) intervention is a multidisciplinary and shared decision-making intervention to improve initial medication adherence addressed to patients in need of new treatments for cardiovascular diseases and diabetes in primary care (PC). This pilot study aims to evaluate the feasibility and acceptability of the IMA intervention and the feasibility of a cluster-RCT to assess the effectiveness and cost-effectiveness of the intervention.

Methods

A 3-month pilot trial with an embedded process evaluation was conducted in five PC centers in Catalonia (Spain). Electronic health data were descriptively analyzed to test the availability and quality of records of the trial outcomes (initiation, implementation, clinical parameters and use of services). Recruitment and retention rates of professionals were analyzed. Twenty-nine semi-structured interviews with professionals (general practitioners, nurses, and community pharmacists) and patients were conducted to assess the feasibility and acceptability of the intervention. Three discussion groups with a total of fifteen patients were performed to review and redesign the intervention decision aids. Qualitative data were thematically analyzed.

Results

A total of 901 new treatments were prescribed to 604 patients. The proportion of missing data in the electronic health records was up to 30% for use of services and around 70% for clinical parameters 5 months before and after a new prescription. Primary and secondary outcomes were within plausible ranges and outliers were barely detected. The IMA intervention and its implementation strategy were considered feasible and acceptable by pilot-study participants. Low recruitment and retention rates, understanding of shared decision-making by professionals, and format and content of decision aids were the main barriers to the feasibility of the IMA intervention.

Discussion

Involving patients in the decision-making process is crucial to achieving better clinical outcomes. The IMA intervention is feasible and showed good acceptability among professionals and patients. However, we identified barriers and facilitators to implementing the intervention and adapting it to a context affected by the COVID-19 pandemic that should be considered before launching a cluster-RCT. This pilot study identified opportunities for refining the intervention and improving the design of the definitive cluster-RCT to evaluate its effectiveness and cost-effectiveness.

Clinical trial registration

ClinicalTrials.gov, identifier NCT05094986.

Shared decision-making conversations and smoking cessation interventions: critical components of low-dose CT lung cancer screening programs

Lung cancer remains the world's deadliest cancer despite efforts to decrease smoking rates. Lung cancer screening (LCS) with low-dose computed tomography (LDCT) was shown to reduce lung cancer deaths by 20%. Screening with LDCT comes with potential harms including a high rate of false-positive test results, subsequent follow-up procedures, and radiation exposure. For some patients, the potential benefits associated with screening may be outweighed by the harms. The decision to screen must therefore take into consideration patients' risk of developing lung cancer, comorbidities that may prevent diagnostic procedures or curative surgery, and their values and preferences regarding the benefits and harms of screening. A process called shared decision-making (SDM) is recognized as a crucial feature of LCS. SDM is a patient-centered approach where healthcare providers provide best clinical evidence and then work together with patients to discern if the screening process aligns with the patient's values and preferences. Unfortunately, clinician SDM skills are often of poor quality which can lead to patients making uninformed decisions. Decision support tools that help patients make informed decisions and increase SDM on LCS are available. In 2015, the Centers for Medicare & Medicaid Services issued a coverage memo for LCS that contained an unprecedented requirement: an initial patient counseling and SDM visit with the use of at least one decision aid must occur for screening services to be reimbursed. This review focuses on SDM and suggests ways to increase the prevalence and effectiveness of SDM in LCS programs. Stopping smoking greatly reduces a person's risk for developing lung cancer, and smoking cessation messages in LCS guidelines from major medical organizations and interventions in LCS programs are explored. LCS has come of age; so too has SDM as it is an integral part of LCS programs.