Dataset Information

Personalization of Medical Treatment Decisions: Simplifying Complex Models while Maintaining Patient Health Outcomes.

ABSTRACT:

Background

Personalizing medical treatments based on patient-specific risks and preferences can improve patient health. However, models to support personalized treatment decisions are often complex and difficult to interpret, limiting their clinical application.

Methods

We present a new method, using machine learning to create meta-models, for simplifying complex models for personalizing medical treatment decisions. We consider simple interpretable models, interpretable ensemble models, and noninterpretable ensemble models. We use variable selection with a penalty for patient-specific risks and/or preferences that are difficult, risky, or costly to obtain. We interpret the meta-models to the extent permitted by their model architectures. We illustrate our method by applying it to simplify a previously developed model for personalized selection of antipsychotic drugs for patients with schizophrenia.

Results

The best simplified interpretable, interpretable ensemble, and noninterpretable ensemble models contained at most half the number of patient-specific risks and preferences compared with the original model. The simplified models achieved 60.5% (95% credible interval [crI]: 55.2-65.4), 60.8% (95% crI: 55.5-65.7), and 83.8% (95% crI: 80.8-86.6), respectively, of the net health benefit of the original model (quality-adjusted life-years gained). Important variables in all models were similar and made intuitive sense. Computation time for the meta-models was orders of magnitude less than for the original model.

Limitations

The simplified models share the limitations of the original model (e.g., potential biases).

Conclusions

Our meta-modeling method is disease- and model- agnostic and can be used to simplify complex models for personalization, allowing for variable selection in addition to improved model interpretability and computational performance. Simplified models may be more likely to be adopted in clinical settings and can help improve equity in patient outcomes.

SUBMITTER: Weyant C

PROVIDER: S-EPMC8858337 | biostudies-literature | 2022 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Personalization of Medical Treatment Decisions: Simplifying Complex Models while Maintaining Patient Health Outcomes.

Weyant Christopher C Brandeau Margaret L ML

Medical decision making : an international journal of the Society for Medical Decision Making 20210820 4

<h4>Background</h4>Personalizing medical treatments based on patient-specific risks and preferences can improve patient health. However, models to support personalized treatment decisions are often complex and difficult to interpret, limiting their clinical application.<h4>Methods</h4>We present a new method, using machine learning to create meta-models, for simplifying complex models for personalizing medical treatment decisions. We consider simple interpretable models, interpretable ensemble m ...[more]

PMID: 34416832

Similar Datasets

Project description:BackgroundPersonalizing medical treatment decisions based on patient-specific risks and/or preferences can improve health outcomes. Decision makers frequently select treatments based on partial personalization (e.g., personalization based on risks but not preferences or vice versa) due to a lack of data about patient-specific risks and preferences. However, partially personalizing treatment decisions based on a subset of patient risks and/or preferences can result in worse population-level health outcomes than no personalization and can increase the variance of population-level health outcomes.MethodsWe develop a new method for partially personalizing treatment decisions that avoids these problems. Using a case study of antipsychotic treatment for schizophrenia, as well as 4 additional illustrative examples, we demonstrate the adverse effects and our method for avoiding them.ResultsFor the schizophrenia treatment case study, using a previously proposed modeling approach for personalizing treatment decisions and using only a subset of patient preferences regarding treatment efficacy and side effects, mean population-level health outcomes decreased by 0.04 quality-adjusted life-years (QALYs; 95% credible interval [crI]: 0.02-0.06) per patient compared with no personalization. Using our new method and considering the same subset of patient preferences, mean population-level health outcomes increased by 0.01 QALYs (95% crI: 0.00-0.03) per patient as compared with no personalization, and the variance decreased.LimitationsWe assumed a linear and additive utility function.ConclusionsSelecting personalized treatments for patients should be done in a way that does not decrease expected population-level health outcomes and does not increase their variance, thereby resulting in worse risk-adjusted, population-level health outcomes compared with treatment selection with no personalization. Our method can be used to ensure this, thereby helping patients realize the benefits of treatment personalization without the potential harms.

Project description:AimsThe effective refractory period (ERP) is one of the main electrophysiological properties governing arrhythmia, yet ERP personalization is rarely performed when creating patient-specific computer models of the atria to inform clinical decision-making. This study evaluates the impact of integrating clinical ERP measurements into personalized in silico models on arrhythmia vulnerability.Methods and resultsClinical ERP measurements were obtained in seven patients from multiple locations in the atria. Atrial geometries from the electroanatomical mapping system were used to generate personalized anatomical atrial models. The Courtemanche M. et al. cellular model was adjusted to reproduce patient-specific ERP. Four modeling approaches were compared: homogeneous (A), heterogeneous (B), regional (C), and continuous (D) ERP distributions. Non-personalized approaches (A and B) were based on literature data, while personalized approaches (C and D) were based on patient measurements. Modeling effects were assessed on arrhythmia vulnerability and tachycardia cycle length, with sensitivity analysis on ERP measurement uncertainty. Mean vulnerability was 3.4 ± 4.0%, 7.7 ± 3.4%, 9.0 ± 5.1%, and 7.0 ± 3.6% for scenarios A-D, respectively. Mean tachycardia cycle length was 167.1 ± 12.6 ms, 158.4 ± 27.5 ms, 265.2 ± 39.9 ms, and 285.9 ± 77.3 ms for scenarios A-D, respectively. Incorporating perturbations to the measured ERP in the range of 2, 5, 10, 20, and 50 ms changed the vulnerability of the model to 5.8 ± 2.7%, 6.1 ± 3.5%, 6.9 ± 3.7%, 5.2 ± 3.5%, and 9.7 ± 10.0%, respectively.ConclusionIncreased ERP dispersion had a greater effect on re-entry dynamics than on vulnerability. Inducibility was higher in personalized scenarios compared with scenarios with uniformly reduced ERP; however, this effect was reversed when incorporating fibrosis informed by low-voltage areas. Effective refractory period measurement uncertainty up to 20 ms slightly influenced vulnerability. Electrophysiological personalization of atrial in silico models appears essential and requires confirmation in larger cohorts.

Project description:ImportancePatients increasingly demand transparency in and control of how their medical records and biospecimens are shared for research. How much they are willing to share and what factors influence their sharing preferences remain understudied in real settings.ObjectivesTo examine whether and how various presentations of consent forms are associated with differences in electronic health record and biospecimen sharing rates and whether these rates vary according to user interface design, data recipients, data and biospecimen items, and patient characteristics.Design, setting, and participantsFor this survey study, a data and biospecimen sharing preference survey was conducted at 2 academic hospitals from May 1, 2017, to September 31, 2018, after simple randomization of patients to 1 of 4 options with different layout and formats of indicating sharing preferences: opt-in simple, opt-in detailed, opt-out simple, and opt-out detailed.InterventionsAll participants were presented with a list of data and biospecimen items that could be shared for research within the same health care organization or with other nonprofit or for-profit institutions. Participating patients were randomly asked to select the items that they would share (opt-in) or were asked to select items they would not share (opt-out). Patients in these 2 groups were further randomized to select only among 18 categories vs 59 detailed items (simple vs detailed form layout).Main outcomes and measuresThe primary end points were the percentages of patients willing to share data and biospecimen categories or items.ResultsAmong 1800 eligible participants, 1246 (69.2%) who completed their data sharing survey were included in the analysis, and 850 of these patients (mean [SD] age, 51.1 [16.7] years; 507 [59.6%] female; 677 [79.6%] white) responded to the satisfaction survey. A total of 46 participants (3.7%) declined sharing with the home institution, 352 (28.3%) with nonprofit institutions, and 590 (47.4%) with for-profit institutions. A total of 836 (67.1%) indicated that they would share all items with researchers from the home institution. When comparing opt-out with opt-in interfaces, all 59 sharing choice variables (100%) were associated with the sharing decision. When comparing simple with detailed forms, only 14 variables (23.7%) were associated with the sharing decision.Conclusions and relevanceThe findings suggest that most patients are willing to share their data and biospecimens for research. Allowing patients to decide with whom they want to share certain types of data may affect research that involves secondary use of electronic health records and/or biosamples for research.

Dataset Information

Personalization of Medical Treatment Decisions: Simplifying Complex Models while Maintaining Patient Health Outcomes.

Background

Methods

Results

Limitations

Conclusions

Publications

Personalization of Medical Treatment Decisions: Simplifying Complex Models while Maintaining Patient Health Outcomes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets