scholarly journals Predicting Therapy Success and Costs for Personalized Treatment Recommendations Using Baseline Characteristics: Data-Driven Analysis (Preprint)

2018 ◽  
Author(s):  
Vincent Bremer ◽  
Dennis Becker ◽  
Spyros Kolovos ◽  
Burkhardt Funk ◽  
Ward van Breda ◽  
...  
Keyword(s):  
Decision Making ◽  
Cost Effectiveness ◽  
Incremental Cost ◽  
Treatment Recommendations ◽  
Prediction Performance ◽  
Personalized Treatment ◽  
Machine Learning Techniques ◽  
Treatment Recommendation ◽  
Individual Treatment ◽  
Treatment Type

BACKGROUND Different treatment alternatives exist for psychological disorders. Both clinical and cost effectiveness of treatment are crucial aspects for policy makers, therapists, and patients and thus play major roles for healthcare decision-making. At the start of an intervention, it is often not clear which specific individuals benefit most from a particular intervention alternative or how costs will be distributed on an individual patient level. OBJECTIVE This study aimed at predicting the individual outcome and costs for patients before the start of an internet-based intervention. Based on these predictions, individualized treatment recommendations can be provided. Thus, we expand the discussion of personalized treatment recommendation. METHODS Outcomes and costs were predicted based on baseline data of 350 patients from a two-arm randomized controlled trial that compared treatment as usual and blended therapy for depressive disorders. For this purpose, we evaluated various machine learning techniques, compared the predictive accuracy of these techniques, and revealed features that contributed most to the prediction performance. We then combined these predictions and utilized an incremental cost-effectiveness ratio in order to derive individual treatment recommendations before the start of treatment. RESULTS Predicting clinical outcomes and costs is a challenging task that comes with high uncertainty when only utilizing baseline information. However, we were able to generate predictions that were more accurate than a predefined reference measure in the shape of mean outcome and cost values. Questionnaires that include anxiety or depression items and questions regarding the mobility of individuals and their energy levels contributed to the prediction performance. We then described how patients can be individually allocated to the most appropriate treatment type. For an incremental cost-effectiveness threshold of 25,000 €/quality-adjusted life year, we demonstrated that our recommendations would have led to slightly worse outcomes (1.98%), but with decreased cost (5.42%). CONCLUSIONS Our results indicate that it was feasible to provide personalized treatment recommendations at baseline and thus allocate patients to the most beneficial treatment type. This could potentially lead to improved decision-making, better outcomes for individuals, and reduced health care costs.

Abstract P214: Patient and Physician Factors Influence Decision-Making in Hypercholesterolemia

Circulation ◽  
2015 ◽  
Vol 131 (suppl_1) ◽  
Author(s):  
Michel Krempf ◽  
Ross J Simpson ◽  
Dena R Ramey ◽  
Philippe Brudi ◽  
Hilde Giezek ◽  
...  
Keyword(s):  
Decision Making ◽  
Goal Attainment ◽  
Clinical Decision Making ◽  
Treatment Strategies ◽  
Treatment Decision ◽  
Clinical Decision ◽  
Treatment Recommendations ◽  
Treatment Choice ◽  
Treatment Recommendation ◽  
Double Blind

Objectives: Little is known about how patient factors influence physicians’ treatment decision-making in hypercholesterolemia. We surveyed physicians’ treatment recommendations in high-risk patients with LDL-C not controlled on statin monotherapy. Methods: Physicians completed a questionnaire pre-randomization for each patient in a double-blind trial (NCT01154036) assessing LDL-C goal attainment rates with different treatment strategies. Patients had LDL-C ≥100 mg/dL after 5 weeks’ atorvastatin 10 mg/day and before randomization. Physicians were asked about treatment recommendations for three scenarios: (1) LDL-C near goal (100-105 mg/dL), (2) LDL-C far from goal (120 mg/dL), then (3) known baseline LDL-C of enrolled patients on atorvastatin 10 mg/day. Factors considered in their choice were specified. Physicians had been informed of projected LDL-C reductions for each treatment strategy in the trial. Regression analysis identified prognostic factors associated with each scenario, and projected LDL-C values for physicians’ treatment choices were compared to actual LDL-C values achieved in the trial. Results: Physicians at 296 sites completed questionnaires for 1535 patients. The most common treatment strategies for all three scenarios were: 1) not to change therapy, 2) double atorvastatin dose, 3) add ezetimibe, 4) double atorvastatin dose and add ezetimibe. Doubling atorvastatin dose was the most common treatment recommendation in all scenarios (43-52% of patients). ‘No change in therapy’ was recommended in 6.5% of patients when LDL-C was assumed far from goal. Treatment recommendations were more aggressive if actual LDL-C was known or considered far from goal. When compared with the ‘no change in therapy’ recommendation, CV risk factors and desire to achieve a more aggressive LDL-C goal were generally considered in decision-making for each treatment choice, regardless of LDL-C scenario. Patients randomized to a more aggressive regimen than recommended by physicians had larger reductions in LDL-C: the actual reduction in LDL-C in patients randomized to ‘add ezetimibe’ was -20.8% versus a projected reduction of -10.0% when physicians recommended ‘doubling atorvastatin dose’. Conclusions: This study provides insight into physicians’ perspectives on clinical management of hypercholesterolemia and highlights a gap in knowledge translation from guidelines to clinical practice. Targeting lower LDL-C and CV risk were key drivers in clinical decision-making but, generally, physicians were more conservative in their treatment choice than guidelines recommend, which may result in poorer LDL-C reduction. When compared with actual outcomes, projected LDL-C control was better if physicians used more comprehensive strategies rather than simply doubling the statin dose.

scholarly journals Design and implementation of an intelligent framework for supporting evidence-based treatment recommendations in precision oncology

2020 ◽  
Author(s):  
Frank P.Y. Lin
Keyword(s):  
Decision Making ◽  
Recommendation System ◽  
Unmet Need ◽  
Treatment Recommendations ◽  
Treatment Recommendation ◽  
Evidence Based ◽  
Supporting Evidence ◽  
Precision Oncology ◽  
Sequential Decision ◽  
Evidence Based Treatment

AbstractBACKGROUNDThe advances in genome sequencing technologies have provided new opportunities for delivering targeted therapy to patients with advanced cancer. However, these high-throughput assays have also created a multitude of challenges for oncologists in treatment selection, demanding a new approach to support decision-making in clinics.METHODSTo address this unmet need, this paper describes the design of a symbolic reasoning framework using the method of hierarchical task analysis. Based on this framework, an evidence-based treatment recommendation system was implemented for supporting decision-making based on a patient’s clinicopathologic and biomarker profiles.RESULTSThis intelligent framework captures a six-step sequential decision process: (1) concept expansion by ontology matching, (2) evidence matching, (3) evidence grading and value-based prioritisation, (4) clinical hypothesis generation, (5) recommendation ranking, and (6) recommendation filtering. The importance of balancing evidence-based and hypothesis-driven treatment recommendations is also highlighted. Of note, tracking history of inference has emerged to be a critical step to allow rational prioritisation of recommendations. The concept of inference tracking also enables the derivation of a novel measure — level of matching — that helps to convey whether a treatment recommendation is drawn from incomplete knowledge during the reasoning process.CONCLUSIONSThis framework systematically encapsulates oncologist’s treatment decisionmaking process. Further evaluations in prospective clinical studies are warranted to demonstrate how this computational pipeline can be integrated into oncology practice to improve outcomes.

scholarly journals ICER is good for us—Possibly not for you, he or she

2011 ◽  
Vol 27 (1) ◽  
pp. 98-98
Author(s):  
Markku Pekurinen
Keyword(s):  
Health Care ◽  
Decision Making ◽  
Cost Effectiveness ◽  
Incremental Cost ◽  
Healthcare Systems ◽  
Incremental Cost Effectiveness Ratio ◽  
Decision Makers ◽  
Cost Effectiveness Ratio ◽  
Sufficient Criterion ◽  
Important Ingredient

Cleemput et al. make a point that the incremental cost-effectiveness ratio (ICER) alone is not a sufficient criterion to guide decision making in health care, and needs many other supplementary inputs. This is nothing new, it has been well known for years to researchers and decision makers alike. ICER serves as an important ingredient to guide decision making, at least in some healthcare systems.

scholarly journals Estimating and evaluating personalized treatment recommendations from randomized trials with ptr

2021 ◽  
Vol 21 (2) ◽  
pp. 348-359
Author(s):  
Matthias Pierce ◽  
Richard Emsley
Keyword(s):  
Randomized Trials ◽  
Patient Characteristics ◽  
Treatment Recommendations ◽  
Trial Data ◽  
Personalized Treatment ◽  
Treatment Recommendation ◽  
Bootstrap Resampling ◽  
Recommendation Algorithm ◽  
Continuous Outcome ◽  
Alternative Regime

One of the targets of personalized medicine is to provide treatment recommendations using patient characteristics. We present the command ptr, which both predicts a personalized treatment recommendation algorithm and evaluates its effectiveness versus an alternative regime, using randomized trial data. The command allows for multiple (continuous or categorical) biomarkers and a binary or continuous outcome. Confidence intervals for the evaluation parameter are provided using bootstrap resampling.

Evaluation of a genomic-based prognostic test for metastasis in high-risk post-prostatectomy patients: Does it impact physician decision making?

2013 ◽  
Vol 31 (6_suppl) ◽  
pp. 196-196
Author(s):  
Ketan K. Badani ◽  
Darby J. S. Thompson ◽  
Anirban Pradip Mitra ◽  
Mercedeh Ghadessi ◽  
Christine Buerki ◽  
...  
Keyword(s):  
Decision Making ◽  
High Risk ◽  
Treatment Recommendations ◽  
Additional Treatment ◽  
Treatment Recommendation ◽  
Test Results ◽  
Clinical Implementation ◽  
Clinical Predictors ◽  
Physician Decision Making ◽  
The Impact

196 Background: Currently, identification of individual patients who are truly at risk of developing lethal prostate cancer after radical prostatectomy (RP) is based on clinical nomograms. A prospectively validated genomic classifier (Decipher) has been shown to more accurately predict metastatic disease post RP than established clinical predictors and can identify patients with adverse pathology who may be cured by RP alone and may therefore not require additional treatment. Methods: An IRB-approved study assessed the impact of a genomic classifier (GC) test in 240 pathologically high-risk post RP case reviews. Twenty (20) urologic oncologists from 18 institutions reviewed 12 cases presented in a randomized, de-identified fashion via a secure online platform to provide treatment recommendations pre- and post- patient GC test results. Possible recommendations included referral to radiation oncologist and/or initiation of adjuvant hormones, close observation, or other. The primary endpoint was any change in treatment recommendation after unblinding of GC test results. Confidence in treatment recommendations was assessed using a 5-point Likert scale. Results: Following unblinding of GC test results, treatment recommendations changed in 43% (95% CI: 37-49) of all cases. Specifically, among cases with a pre-GC recommendation involving treatment, 31% (95% CI: 23-41) of respondents changed their recommendation to observation post-GC.Respondents considered the GC result to have influenced their recommendation in 63% (95% CI: 56-68) of cases. The addition of information provided by the GC result increased decision making confidence in 39% (95% CI: 30-49) of cases where a change of treatment recommendation was made. Following unblinding, physicians reported that the GC result was clinically relevant in 84% (95% CI: 79-84) of cases. Conclusions: GC appears to influence treatment recommendations and decision making confidence for high-risk prostatectomy patients. This study suggests that clinical implementation of GC may potentially impact treatment recommendations.

The Interaction between Price Negotiations and Heterogeneity: Implications for Economic Evaluations

2020 ◽  
Vol 40 (2) ◽  
pp. 144-155
Author(s):  
Helen O’Donnell ◽  
Laura McCullagh ◽  
Michael Barry ◽  
Cathal Walsh
Keyword(s):  
Decision Making ◽  
Cost Effectiveness ◽  
Incremental Cost ◽  
Hybrid Approach ◽  
Cost Effective ◽  
Worked Examples ◽  
Population Heterogeneity ◽  
Medical Decision ◽  
Economic Evaluations ◽  
Price Negotiations

Economic evaluation is an important element of the decision making process for the reimbursement of drugs. Heterogeneity can be considered an explained variation in clinical or economic outcomes based on the clinical and sociodemographic characteristics of patients. However, to our knowledge, the relationship between price negotiations and population heterogeneity has not been considered in the literature to date. If a company offers a conditional discount that is dependent on obtaining reimbursement in 2 subgroups or indications, an interaction is generated between groups that should be accounted for in economic evaluations. Critically, where the drug has 2 indications but is only cost-effective in 1 indication at the full price (herein “indication 1”), the cost savings realized from implementation of the discount in indication 1 can be used to offset the incremental cost of extending reimbursement to indication 2 at the discounted price. This reduces the incremental cost-effectiveness ratio and increases the probability of positive reimbursement compared to a stratified approach. Given the additional complexity that this introduces, we introduce a framework deemed the “hybrid approach” to guide the economic assessment. We present 2 worked examples. We show that failure to account for the interaction can lead to inaccurate conclusions regarding a drug’s cost effectiveness and that adoption of strategic behavior could theoretically increase the reimbursement price of drugs. By adopting this framework, cost-effective interventions are identified that may have been previously misclassified as not being cost-effective and vice versa. Recognition of the interaction in the literature by pharmaceutical companies may influence the forms of discounts offered to decision makers. Therefore, we expect this research to have far-reaching effects on medical decision making.

Implementation of a Molecular Tumor Board in Clinical Decision Making at the Medical Center University of Freiburg

Blood ◽  
2016 ◽  
Vol 128 (22) ◽  
pp. 3579-3579
Author(s):  
Rainer Claus ◽  
Lisa Lutz ◽  
Hauke Busch ◽  
Leman Mehmed ◽  
Agnes Csanadi ◽  
...  
Keyword(s):  
Decision Making ◽  
Clinical Decision Making ◽  
Molecular Data ◽  
Treatment Recommendations ◽  
Tumor Board ◽  
Treatment Recommendation ◽  
Off Label ◽  
Organ Specific ◽  
Molecular Tumor Board ◽  
Made In

Abstract Introduction: In-depth knowledge about molecular pathogenesis of malignant diseases and rapidly increasing availability of targeted treatment options enables molecularly guided decision-making. We have established a Molecular Tumor Board (MTB) that focuses on patient management based on specific molecular data at the individual patient level. Methods: The MTB has its main focus on hematologic and solid neoplasias progressing during standard treatment, on rare entities and on patients with treatment resistance. The biweekly MTB supports the work of organ-specific boards and external cooperation partners. The MTB multidisciplinary team consists of expert physicians from Hematology, Medical Oncology, Gynecology, Dermatology, Pediatrics and Radiation Oncology as well as Pathology, Molecular biology, Computational Biology and Genetics. Diagnostic and therapeutic recommendations are based on customized diagnostics and a case-by-case literature review. Recommendations are communicated back to the treating physician. Results: In the first year after implementation of the MTB, a total of 92 pts have been discussed in 155 case discussions during 25 MTB meetings. Referred patient cases covered the entire range of malignancies seen by the organ-specific boards including hematologic malignancies. 132 diagnostic recommendations were made in 80/92 (87%) pts, including IHC, ISH or panel sequencing with diagnostic reporting (n=96/72 pts) and exome, genome, transcriptome and/or methylome analysis (n=24/22 pts.). 43 treatment recommendations were made in 39/92 (42%) pts with an implementation rate of 47% (20/43 recommendations in 19/39 pts). Treatment recommendations mainly comprised off-label antibody and tyrosine kinase inhibitor (TKI) therapy (40%) and trial inclusions (28%). Major reasons for non-adherence to recommendations included patient will, death of pts and medical reasons. Objective responses were observed in 5/19 (26%) pts to TKI in- and off-label and antibody off-label treatments. Disease stabilization was achieved in 3/19 (16%) pts. Specifically, the use of PD-(L)1 inhibiting antibodies was suggested in 13 cases (11 off-label) and implemented in 6 cases. Here, 2/6 pts responded or exhibited stable disease upon PD-(L1) blockage. Conclusion: Implementation of a Molecular Tumor Board serves as an interdisciplinary platform for integrating comprehensive molecular data sets as predictive biomarkers in molecular guided, individualized patient care. Our experience demonstrates that individualized treatment recommendation is feasible and effective for a substantial proportion of patients in challenging clinical situations. Disclosures Claus: Roche: Consultancy, Honoraria; Gilead: Consultancy, Honoraria; Janssen-Cilag: Consultancy, Honoraria, Other: Travel Funding.

Sign in / Sign up

Export Citation Format

Share Document