Annals Clinical Decision Making: Weighing Evidence to Inform Clinical Decisions

2020 ◽  
Vol 172 (9) ◽  
pp. 599-603 ◽  
Author(s):  
Joshua P. Metlay ◽  
Katrina A. Armstrong
Keyword(s):  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Clinical Decisions

Clinical decision-making and its place in paramedic practice

2019 ◽  
Vol 11 (5) ◽  
pp. 1-5
Author(s):  
Samantha Murdoch
Keyword(s):  
Decision Making ◽  
Clinical Outcome ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Hospital Environment ◽  
Decision Making Process ◽  
Clinical Decisions ◽  
Correct Treatment ◽  
Health And Wellbeing

In the pre-hospital environment, paramedics are required to make clinical decisions, often rapidly to ensure correct treatment and care is provided. Decisions made by paramedics majorly impacts on the life, clinical outcome, safety, health and wellbeing of their patients. With the introduction of the Newly Qualified Paramedic Framework, it potentially has never been more pertinent to examine the decision-making process-an integral part of paramedicine. The implementation of the NQP framework has prompted an exploration into clinical decision making and its place in an ever-evolving profession. Through examination of theories and frameworks, this article aims to identify the underpinning evidence that enables a paramedic to reach a competent decision and the barriers experienced in the process.

scholarly journals Value-impregnated factual claims may undermine medical decision-making

2018 ◽  
Vol 13 (3) ◽  
pp. 151-158 ◽  
Author(s):  
Niels Lynøe ◽  
Gert Helgesson ◽  
Niklas Juth
Keyword(s):  
Decision Making ◽  
Medical Decision Making ◽  
Clinical Decision Making ◽  
Negative Impact ◽  
Personal Values ◽  
Healthcare Providers ◽  
Clinical Decision ◽  
Medical Decision ◽  
Clinical Decisions ◽  
Soft Laws

Clinical decisions are expected to be based on factual evidence and official values derived from healthcare law and soft laws such as regulations and guidelines. But sometimes personal values instead influence clinical decisions. One way in which personal values may influence medical decision-making is by their affecting factual claims or assumptions made by healthcare providers. Such influence, which we call ‘value-impregnation,’ may be concealed to all concerned stakeholders. We suggest as a hypothesis that healthcare providers’ decision making is sometimes affected by value-impregnated factual claims or assumptions. If such claims influence e.g. doctor–patient encounters, this will likely have a negative impact on the provision of correct information to patients and on patients’ influence on decision making regarding their own care. In this paper, we explore the idea that value-impregnated factual claims influence healthcare decisions through a series of medical examples. We suggest that more research is needed to further examine whether healthcare staff’s personal values influence clinical decision-making.

Diagnostic conversations: Clinical Decision Making in surgery – Part 2

Diagnosis ◽  
2014 ◽  
Vol 1 (2) ◽  
pp. 189-193 ◽  
Author(s):  
David Allan Watters ◽  
Spencer Wynyard Beasley ◽  
Wendy Crebbin
Keyword(s):  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Learning Opportunities ◽  
Clinical Decisions ◽  
Decision Making Processes ◽  
Royal Australasian College ◽  
Insight Into ◽  
Made In

AbstractProceduralists who fail to review their decision making are unlikely to learn from their experiences, irrespective of whether the operative outcome is successful or not. Teaching junior surgeons to develop ‘insight’ into their own decision making has long been a challenge. Surgeons and staff of the Royal Australasian College of Surgeons worked together to develop a model to help explain the processes around clinical decision making and incorporated this model into a Clinical Decision Making (CDM) training course. In this course, faculty apply the model to specific surgical cases, within the model’s framework of how clinical decisions are made; thus providing an opportunity to identify specific decision making processes as they occur and to highlight some of the learning opportunities they provide. The conversation in this paper illustrates the kinds of case-based interactions which typically occur in the development and teaching of the CDM course.The focus in this, the second of two papers, is on reviewing post-operative clinical decisions made in relation to one case, to improve the quality of subsequent decision making.

scholarly journals Medical Simulation in Relapsed Follicular Lymphoma Improves Clinical Decision Making of Hematologists/Oncologists

Blood ◽  
2020 ◽  
Vol 136 (Supplement 1) ◽  
pp. 33-34
Author(s):  
Lauren Willis ◽  
Donna Topping ◽  
Sarah Atwood ◽  
Jonathon B. Cohen
Keyword(s):  
Decision Making ◽  
Follicular Lymphoma ◽  
Treatment Option ◽  
Clinical Decision Making ◽  
Response Rates ◽  
Clinical Decision ◽  
Evidence Based ◽  
Cell Transplant ◽  
Clinical Decisions ◽  
Appropriate Treatment

Background: Frontline treatment of follicular lymphoma (FL) yields high response rates, but most patients relapse. In addition, response rates and duration of response have historically declined with subsequent treatments. These factors make management of this disease challenging. Therefore, this study was conducted to determine if an online, simulation-based continuing medical education (CME) intervention could improve clinical decision making of hematologists/oncologists (hem/oncs) regarding treatment selection for relapsed/refractory (R/R) FL. Description of Intervention: A CME certified virtual patient simulation (VPS) was made available via a website dedicated to continuous professional development. The VPS consisted of 2 cases of R/R FL presented in a platform that allows hem/oncs to assess the patients and make diagnostic and therapeutic decisions supported by an extensive database of diagnostic and treatment possibilities, matching the scope and depth of actual practice. Case 1: Patient with FL who failed 2 prior lines of therapy (R-CHOP, bendamustine/obinutuzumab), past medical history (PMH) well controlled hypertension and poorly controlled type 2 diabetes, presenting with constitutional symptoms and needs 3rd line treatment. Case 2: Patient with FL who failed 2 prior lines of therapy (bendamustine/rituximab, lenalidomide/rituximab), PMH well controlled atrial fibrillation and ulcerative colitis, patient requests intravenous therapy because he has trouble remembering to take oral medications. Methods: Clinical decisions were analyzed using a sophisticated decision engine, and tailored clinical guidance (CG) employing up-to-date evidence-base and faculty recommendations was provided after each decision. Decisions were collected post-CG and compared with each user's baseline (pre-CG) decisions using McNemar's test to determine p-values (P < .05 indicates significance). Data were collected between 11/20/19 and 2/19/20. Results: At the time of assessment, 154 hem/oncs who made clinical decisions were included in the analysis. From pre- to post-CG in the VPS, hem/oncs were more likely to make evidence-based practice decisions in: -Diagnosing patients with relapsed FL: 55% pre-CG and 73% post-CG (P < 0.001) -Starting an appropriate treatment for a patient with R/R FL ----Case 1: Ordering idelalisib: 7% pre-CG and 33% post-CG (P < 0.001) ----Case 1: Ordering lenalidomide + rituximab: 6% pre-CG and 28% post-CG (P < 0.001) ----Case 1: Ordering duvelisib: 2% pre-CG and 9% post-CG (P < 0.001) ----Case 2: Ordering copanlisib: 32% pre-CG and 73% post-CG (P < 0.001) The top rationales for selecting an appropriate treatment option were: recommended by guidelines, convenience of administration route, better efficacy compared to other agents, and best option based on patient comorbidities. Other relevant concomitant therapies ordered were consult for chimeric antigen receptor (CAR) T-cell therapy, consult for stem cell transplant, radiation therapy, refer to a clinical trial, and Pneumocystis jirovecii pneumonia (PJP) prophylaxis (Figure 1). Conclusion: This study demonstrates that VPS that immerses and engages hem/oncs in an authentic and practical learning experience improved evidence-based clinical decisions related to the management of R/R FL. This VPS increased the percentage of heme/oncs who correctly diagnosed R/R FL and selected an appropriate treatment option. This study indicates that unique educational methodologies and platforms, which are available on-demand, can be effective tools for promoting guideline-based therapy selection and clinical decision making. Acknowledgement: This CME activity was supported by an independent educational grant from Bayer, Celgene Corporation, and Verastem Oncology. Jake Cohen contributed to data analysis for this research. Reference: https://www.medscape.org/viewarticle/915986 Figure Disclosures Cohen: Janssen, Adicet, Astra Zeneca, Genentech, Aptitude Health, Cellectar, Kite/Gilead, Loxo: Consultancy; Genentech, BMS, Novartis, LAM, BioInvent, LRF, ASH, Astra Zeneca, Seattle Genetics: Research Funding.

scholarly journals Wearable technology to inform the prediction and diagnosis of cardiorespiratory events: a scoping review

PeerJ ◽  
2021 ◽  
Vol 9 ◽  
pp. e12598
Author(s):  
Hamzeh Khundaqji ◽  
Wayne Hing ◽  
James Furness ◽  
Mike Climstein
Keyword(s):  
Decision Making ◽  
Cardiac Arrhythmias ◽  
Observational Studies ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Case Control ◽  
Physiological Data ◽  
Clinical Decisions ◽  
Control Series ◽  
The Impact

Background The need for health systems that allow for continuous monitoring and early adverse event detection in individuals outside of the acute care setting has been highlighted by the global rise in chronic cardiorespiratory diseases and the recent COVID-19 pandemic. Currently, it is unclear what type of evidence exists concerning the use of physiological data collected from commercially available wrist and textile wearables to assist in clinical decision making. The aim of this review was therefore to systematically map and summarize the scientific literature surrounding the use of these wearables in clinical decision making as well as identify knowledge gaps to inform further research. Methodology Six electronic bibliographic databases were systematically searched (Ovid MEDLINE, EMBASE, CINAHL, PubMed, Scopus, and SportsDiscus). Publications from database inception to May 6, 2020 were reviewed for inclusion. Non-indexed literature relevant to this review was also searched systematically. Results were then collated, summarized and reported. Results A total of 107 citations were retrieved and assessed for eligibility with 31 citations included in the final analysis. A review of the 31 papers revealed three major study designs which included (1) observational studies (n = 19), (2) case control series and reports (n = 8), and (3) reviews (n = 2). All papers examined the use of wearable monitoring devices for clinical decisions in the cardiovascular domain, with cardiac arrhythmias being the most studied. When compared to electrocardiogram (ECG) the performance of the wearables in facilitating clinical decisions varied depending upon the type of wearable, user’s activity levels and setting in which they were employed. Observational studies collecting data in the inpatient and outpatient settings were equally represented. Eight case control series and reports were identified which reported on the use of wrist wearables in patients presenting to an emergency department or clinic to aid in the clinical diagnosis of a cardiovascular event. Two narrative reviews were identified which examined the impact of wearable devices in monitoring cardiovascular disease as well as potential challenges they may pose in the future. Conclusions To date, studies employing wearables to facilitate clinical decisions have largely focused upon the cardiovascular domain. Despite the ability of some wearables to collect physiological data accurately, there remains a need for a specialist physician to retrospectively review the raw data to make a definitive diagnosis. Analysis of the results has also highlighted gaps in the literature such as the absence of studies employing wearables to facilitate clinical decisions in the respiratory domain. The disproportionate study of wearables in atrial fibrillation detection in comparison to other cardiac arrhythmias and conditions, as well as the lack of diversity in the sample populations used prevents the generalizability of results.

scholarly journals 28 How is Postpartum Depression Currently Diagnosed and Managed? Insights from a Virtual Patient Simulation

CNS Spectrums ◽  
2019 ◽  
Vol 24 (1) ◽  
pp. 189-190
Author(s):  
Jovana Lubarda ◽  
Martin Warters ◽  
Piyali Chatterjee ◽  
Marlene P. Freeman ◽  
Roger S. McIntyre
Keyword(s):  
Decision Making ◽  
Clinical Practice ◽  
Postpartum Depression ◽  
Clinical Decision Making ◽  
Patient Simulation ◽  
Clinical Decision ◽  
Virtual Patient ◽  
Evidence Based ◽  
Clinical Decisions ◽  
Practice Gaps

AbstractObjectivesThe goal of this study was to determine physician performance in diagnosis and management of postpartum depression (PPD) and to provide needed education in the consequence free environment of a virtual patient simulation (VPS).Methods∙ A continuing medical education activity was delivered via an online VPS learning platform that offers a lifelike clinical care experience with complete freedom of choice in clinical decision-making and expert personalized feedback to address learner’s practice gaps∙ Physicians including psychiatrists, primary care physicians (PCPs), and obstetricians/gynecologists (ob/gyns) were presented with two cases of PPD designed to model the experience of actual practice by including use of electronic health records∙ Following virtual interactions with patients, physicians were asked to make decisions regarding assessments, diagnoses, and pharmacologic therapies. The clinical decisions were analyzed using a sophisticated decision engine, and clinical guidance (CG) based on current evidence-based recommendations was provided in response to learners’ clinical decisions∙ Impact of the education was measured by comparing participant decisions pre- and post-CG using a 2-tailed, paired t-test; P <.05 was considered statistically significant∙ The activity launched on Medscape Education on April 26, 2018, and data were collected through to June 17,2018.Results∙ From pre- to post-CG in the simulation, physicians were more likely to make evidence-based clinical decisions related to:∙ Ordering appropriate baseline tests including tools/scales to screen for PPD: in case 1, psychiatrists (n=624) improved from 34% to 42% on average (P<.05); PCPs (n=197) improved from 38% to 48% on average (P<.05); and, ob/gyns (n=216) improved from 30% to 38% on average (P<.05)∙ Diagnosing moderate-to-severe PPD: in case 2, psychiatrists (n=531) improved from 46% to 62% (P<.05); PCPs (n=154) improved from 43% to 55% (P<.05); and, ob/gyns (n=137) improved from 55% to 73% (P<.05)∙ Ordering appropriate treatments for moderate-to-severe PPD such as selective serotonin-reuptake inhibitors: in case 2, psychiatrists (n=531) improved from 47% CG to 75% (P<.05); PCPs (n=154) improved from 55% to 74% (P<.05); and, ob/gyns (n=137) improved from 51% to 78% (P<.05)∙ Interestingly, a small percentage of physicians (average of 5%) chose investigational agents for PPD which were in clinical trials pre-CG, and this increased to an average of 9% post-CGConclusionsPhysicians who participated in VPS-based education significantly improved their clinical decision-making in PPD, particularly in selection of validated screening tools/scales, diagnosis, and pharmacologic treatments based on severity. Given that VPS immerses physicians in an authentic, practical learning experience matching the scope of clinical practice, this type of intervention can be used to determine clinical practice gaps and translate knowledge into practice.Funding Acknowledgements: The educational activity and outcomes measurement were funded through an independent educational grant from Sage Therapeutics, Inc.

Multiple Approaches to the Diagnosis of Attention Deficit Hyperactivity Disorder

2013 ◽  
Vol 8 (4) ◽  
pp. 44-57 ◽  
Author(s):  
Rui Rijo ◽  
Ricardo Martinho ◽  
Xiaocheng Ge
Keyword(s):  
Decision Making ◽  
Attention Deficit Hyperactivity Disorder ◽  
Attention Deficit ◽  
Clinical Decision Making ◽  
Adult Life ◽  
Clinical Decision ◽  
School Age Children ◽  
Free Text ◽  
Clinical Decisions ◽  
Hyperactivity Disorder

Studies indicate that about 3-7% of school-age children have attention deficit hyperactivity disorder (ADHD). If these disorders are not diagnosed and treated early, its consequences can harshly impair the adult life of the individual. In this context, early diagnosis is critical. Clinical reasoning is a key contributor to the quality of health care. Clinical decisions at the policy level are made within a stochastic domain; decisions for individuals are usually more qualitative. In both cases, poor reasoning can result in an undesirable outcome. Clinical decisions are most typically communicated in a document through free text. Text has significant limitations (particularly ambiguity and poor structuring) whether used for analysis, or to explain the decision-making process. In safety engineering, similar problems are faced in conveying safety arguments to support certification. As a result, approaches have been developed to conveying arguments in ways which improve communication and which are more amenable to analysis. The Goal Structuring Notation (GSN) – a graphical argumentation notation for safety – was developed for those reasons. It has evolved to be one of the most widely used techniques for representing safety arguments. The use of text-mining techniques is another approach in the process of achieving or suggesting a diagnosis to the physician. This paper investigates the relative feasibility of these two approaches and discuss their complementation. Based on a case example, the benefits and problems of adopting GSN and ontology approach in clinical decision-making for ADHD are discussed and illustrated.

scholarly journals Physical Therapy Students’ Application of a Clinical Decision-Making Model

2006 ◽  
Author(s):  
Jeannie Wessel ◽  
Renee Williams ◽  
Beverley Cole
Keyword(s):  
Decision Making ◽  
Physical Therapy ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Clinical Placement ◽  
Physical Therapy Students ◽  
Full Time ◽  
Clinical Decisions ◽  
Decision Making Model ◽  
Information History

Purpose: Most educational programs in the health sciences present their students with a clinical decision-making model (CDMM) to help them define and treat client problems with a client-centered approach. However, little is known about how well students apply such a model in a clinical setting. The purpose of this study was to determine whether physical therapy students used a CDMM to make clinical decisions, and how well they used it. Method: Fifty-four physical therapy students in their first full-time clinical placement were asked to write up one of their client cases explaining how they made their clinical decisions and evaluating the success of these decisions. Three faculty members used a standardized form to assess each student’s use of various components of the CDMM. Results: Students were generally better at following the CDMM for obtaining information (history and assessment) and determining a diagnosis, than they were for planning goals and methods of treatment. Most students emphasized impairment rather than activity or participation, and did not consider the client’s specific concerns. Although few students defined measurable outcomes for their clients, they still felt that their decisions were well founded and that the clients got better. Conclusions: Physical therapy students in their first major clinical placement believe that they are using the CDMM “automatically” and are making appropriate clinical decisions for their clients. However, students need assistance to effectively use all the steps in the CDMM to design client-centered, outcome-oriented treatment.

scholarly journals Medical Simulation in High-Risk AML Improves Clinical Decision Making of Hematologists/Oncologists

Blood ◽  
2021 ◽  
Vol 138 (Supplement 1) ◽  
pp. 4985-4985
Author(s):  
Lauren Willis ◽  
Richard M. Stone ◽  
Geoffrey L. Uy
Keyword(s):  
Decision Making ◽  
Diagnostic Tests ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Learning Objectives ◽  
Evidence Based ◽  
Clinical Decisions ◽  
Community Based ◽  
Clinical Guidance ◽  
Appropriate Treatment

Abstract Background: Our understanding of the biology of acute myeloid leukemia (AML) has increased dramatically with the use of next-generation sequencing. The identification of recurrently mutated genes in AML has allowed for better risk stratification and provided novel therapeutic targets. The European Leukemia Network (ELN) 2017 prognostic system divides patients into favorable, intermediate, and adverse groups based on genetic abnormalities.[Döhner 2017] Patients with features including MDS related changes, complex karyotype and adverse molecular features including mutations in FLT3 are at high risk (HR AML) for treatment failure and relapse. Aim: This study was conducted to determine if an online, simulation-based continuing medical education (CME)-certified intervention could improve clinical decision making of hematologists/oncologists (hem/oncs) regarding treatment selection for patients with HR AML. Description of Intervention: A CME-certified virtual patient simulation (VPS) was made available via a website dedicated to continuous professional development. The VPS consisted of 2 cases of HR AML presented in a platform that allows hem/oncs to assess the patients and make clinical decisions supported by an extensive database of diagnostic and treatment possibilities, matching the scope and depth of actual practice. *CASE 1* 63-year-old male with AML-MRC, mutations detected: RUNX1, TET2, SRSF2; no mutations detected in NPM1, CEBPA, IDH1, IDH2, KIT, KRAS, NRAS, ASXL1, ASXL2, BCR-ABL1, WT1. *CASE 2* 57-year-old female with FLT3-ITD mutated AML who is a candidate for intensive induction therapy. Methods: Clinical decisions were analyzed using a sophisticated decision engine, and tailored clinical guidance (CG) employing up-to-date evidence-base and faculty recommendations was provided after each decision. Decisions were collected post-CG and compared with each user's baseline (pre-CG) decisions using McNemar's test to determine p-values (P &lt; .05 indicates significance). Data were collected between October 8, 2020 and July 22, 2021. Results: At the time of assessment, 186 hem/oncs who made clinical decisions were included in the analysis (112 case 1, 74 case 2). From pre- to post-CG in the VPS, hem/oncs were significantly more likely to make evidence-based practice decisions across all learning objectives, see the Table. *CASE 1* For the case of AML-MRC, the VPS led to a higher percentage of community-based hem/oncs ordering necessary diagnostic tests and ordering an appropriate treatment. After clinical guidance, slightly more academic-based hem/oncs identified the correct diagnosis for the patient. *CASE 2* For the patient with FLT3-ITD mutated AML, the VPS led to a higher percentage of community-based hem/oncs ordering and correctly interpreting diagnostic tests in order to make an accurate diagnosis. After clinical guidance, a higher percentage of academic-based hem/oncs ordered an appropriate treatment for the patient based on the FLT3-ITD mutation and their fitness assessment. Treatment rationales were collected and can be presented. Conclusions: This study demonstrates that VPS that immerses and engages hem/oncs in an authentic learning experience improved evidence-based clinical decisions related to the management of HR AML. Clinical guidance in the VPS improved hem/oncs clinical decision making for all learning objectives and the improvements were statistically significant. For almost all learning objectives, the activity had a significant and larger impact on improving clinical decision making of community-based hem/oncs compared to hem/oncs from other practice settings. This study indicates that unique educational methodologies and platforms, which are available on-demand, can be effective tools for promoting guideline-based therapy selection and clinical decision making. Additional education is recommended about the role for FLT3 inhibitors and the optimal treatment for AML-MRC. Acknowledgement: This CME activity was supported by an independent educational grant from Jazz Pharmaceuticals. References: 1. Döhner H, Estey E, Grimwade D, et al. Diagnosis and management of AML in adults: 2017 ELN recommendations from an international expert panel. 2017. 129(4):424-447. 2. MedSims Activity: https://www.medscape.org/viewarticle/936156 Figure 1 Figure 1. Disclosures Stone: AbbVie Inc, Actinium Pharmaceuticals Inc, Aprea Therapeutics, BerGenBio ASA, ElevateBio, Foghorn Therapeutics, GEMoaB, GlaxoSmithKline, Innate Pharma, Syndax Pharmaceuticals Inc, Syros Pharmaceuticals Inc, Takeda Oncology: Other: Advisory Committee; Agios Pharmaceuticals Inc, Novartis;: Research Funding; ACI Clinical, Syntrix Pharmaceuticals, Takeda Oncology: Other: Data Safety & Monitoring. Uy: GlaxoSmithKline: Consultancy; AbbVie: Consultancy; Agios: Consultancy; Macrogenics: Research Funding; Astellas: Honoraria, Speakers Bureau; Novartis: Consultancy; Genentech: Consultancy; Jazz: Consultancy.

scholarly journals Quantum deep reinforcement learning for clinical decision support in oncology: application to adaptive radiotherapy

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Dipesh Niraula ◽  
Jamalina Jamaluddin ◽  
Martha M. Matuszak ◽  
Randall K. Ten Haken ◽  
Issam El Naqa
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Decision Support ◽  
Clinical Decision Support ◽  
Dose Response ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Specific Information ◽  
Clinical Decisions ◽  
Nsclc Patients

AbstractSubtle differences in a patient’s genetics and physiology may alter radiotherapy (RT) treatment responses, motivating the need for a more personalized treatment plan. Accordingly, we have developed a novel quantum deep reinforcement learning (qDRL) framework for clinical decision support that can estimate an individual patient’s dose response mid-treatment and recommend an optimal dose adjustment. Our framework considers patients’ specific information including biological, physical, genetic, clinical, and dosimetric factors. Recognizing that physicians must make decisions amidst uncertainty in RT treatment outcomes, we employed indeterministic quantum states to represent human decision making in a real-life scenario. We paired quantum decision states with a model-based deep q-learning algorithm to optimize the clinical decision-making process in RT. We trained our proposed qDRL framework on an institutional dataset of 67 stage III non-small cell lung cancer (NSCLC) patients treated on prospective adaptive protocols and independently validated our framework in an external multi-institutional dataset of 174 NSCLC patients. For a comprehensive evaluation, we compared three frameworks: DRL, qDRL trained in a Qiskit quantum computing simulator, and qDRL trained in an IBM quantum computer. Two metrics were considered to evaluate our framework: (1) similarity score, defined as the root mean square error between retrospective clinical decisions and the AI recommendations, and (2) self-evaluation scheme that compares retrospective clinical decisions and AI recommendations based on the improvement in the observed clinical outcomes. Our analysis shows that our framework, which takes into consideration individual patient dose response in its decision-making, can potentially improve clinical RT decision-making by at least about 10% compared to unaided clinical practice. Further validation of our novel quantitative approach in a prospective study will provide a necessary framework for improving the standard of care in personalized RT.

Sign in / Sign up

Export Citation Format

Share Document