In a real-world clinical setting, busy oncologists lack the time for investigative case analysis across all feasibletreatment options, frequently updated treatment guidelines and payor specific requirements. This results in sub-optimal decision making, incomplete pre-authorization (pre-auth) documentation, and problems withreimbursement. Overall, this increases medical costs and payment deficits within oncology. For example, pre-auth inefficiencies are estimated to add $83,000 a year per physician to healthcare costs, which is $1.1 billionannually in oncology alone. To devise a treatment plan, oncologists reference National Comprehensive CancerNetwork Guidelines® (NCCN), other clinical society standards, and payor specific requirements in the contextof a patient's medical history, tumor characteristics, and phase of treatment. One of the most used oncologytreatment guidelines referenced by oncologists and adhered to by most payors is the National ComprehensiveCancer Network (NCCN) Guidelines®. These guidelines are presented as a schema that span 100s of pages. A technology driven clinical decision support (CDS) system could be employed to address the need tostreamline treatment guideline analysis, payor rules review, and treatment decision documentation forreduced overall cost to oncology practices. This proposal focuses on developing an innovative and first-of-a-kind technology for CDS using non-small cell lung cancer (NSCLC) as the initial test case and incorporatingNCCN Guidelines, general payor specific requirements and patient data overlaid to compute feasible treatmentpathways. The team proposes the following Phase I Specific Aims:Aim 1: Develop a graph-based mathematical model and visual presentation of NSCLC NCCN treatmentguidelines with generalized payor specific requirements. Develop a visually interactive graph-basedrepresentation of NCCN Guidelines®. Modeling guidelines as a visual graph (nodes and arcs) will enableoncologists to identify the optimal treatment pathway for their patients.Aim 2: Build an analytics engine that highlights the NCCN graph model with feasible treatment optionsgiven the patient's case details and common payor requirements. Use an opensource tool to createsynthetic patient data and common payor constraints with an oncologist and health plan experts. Develop alibrary of graph traversal algorithms to overlay and visualize the patient data in a visual user interface.Aim 3: Execute, validate and test a proof-of-concept CDS workflow using OncoPath. Run the completeend-to-end CDS workflow with documentation of patient details, NCCN guideline, payor requirements andtreatment decision using synthetic patient data and payor constraints generated in Aim 2. OncoPath will enable an efficient, oncologist-friendly approach to treatment decisions and documentation,subsequently benefitting the patient and decreasing oncology cost. Phase II will deploy a real-time instance ofOncoPath in a single thoracic oncology practice for integrated workflow and time savings validation. Project Narrative
In a real-world clinical setting, busy oncologists lack the time for investigative case analysis across all feasible
treatment options, frequently updated treatment guidelines and payor specific requirements. This results in
sub-optimal decision making, incomplete pre-authorization (pre-auth) documentation, and problems with
reimbursement. Overall, this increases medical costs and payment deficits within oncology. To address this
unmet need, this proposal aims to build OncoPath, a prototype tool in non-small cell lung cancer providing a
first-of-a-kind visual representation of the NCCN Guidelines® with patient data overlaid to easily review, select,
and document the patient information, treatment selection with NCCN supporting evidence, payor constraints,
and any clinical narrative. Algorithms ; Automobile Driving ; driving ; Malignant Neoplasms ; Cancers ; Malignant Tumor ; malignancy ; neoplasm/cancer ; Non-Small-Cell Lung Carcinoma ; NSCLC ; NSCLC - Non-Small Cell Lung Cancer ; Non-Small Cell Lung Cancer ; Nonsmall Cell Lung Carcinoma ; nonsmall cell lung cancer ; Communication ; Decision Making ; Goals ; Intelligence ; Libraries ; Manuals ; Maps ; New York ; Paper ; Patients ; Physicians ; Production ; Running ; Savings ; Societies ; Technology ; Testing ; Time ; Health Care Costs ; Health Costs ; Healthcare Costs ; Businesses ; Medical Care Costs ; medical costs ; Selection for Treatments ; therapy selection ; Guidelines ; base ; improved ; Clinical ; Phase ; insight ; Intuition ; Visual ; Oncologist ; Medical History ; Personal Medical History ; Personal Medical History Epidemiology ; Oncology ; Oncology Cancer ; Clinical Pathways ; tool ; Complex ; Location ; Clinical Decision Support Systems ; treatment planning ; payment ; Graph ; Coding System ; Code ; Thorace ; Thoracic ; Thorax ; Chest ; Modeling ; Math Models ; mathematic model ; mathematical modeling ; mathematical model ; Documentation ; Cancer Treatment ; Malignant Neoplasm Therapy ; Malignant Neoplasm Treatment ; anti-cancer therapy ; anticancer therapy ; cancer-directed therapy ; cancer therapy ; Address ; Health system ; Data ; NCCN ; National Comprehensive Cancer Network ; Thoracic Oncology ; Cancer Patient ; Patient-Focused Outcomes ; Patient outcome ; Patient-Centered Outcomes ; Small Business Innovation Research Grant ; SBIR ; Small Business Innovation Research ; Update ; Validation ; Characteristics ; Process ; Authorization documentation ; Authorization ; Permission ; Development ; developmental ; Pathway interactions ; pathway ; Metadata ; meta data ; cost ; digital ; Treatment Efficacy ; intervention efficacy ; therapeutic efficacy ; therapy efficacy ; innovation ; innovate ; innovative ; open source ; prototype ; tumor ; mathematical methods ; math methodology ; math methods ; mathematical approach ; mathematical methodology ; mathematics approach ; mathematics methodology ; mathematics methods ; cloud based ; support tools ; software as a service ; health plan ; health plans ; clinical decision support ; treatment guidelines ; optimal treatments ; optimal therapies ; Visualization ; efficacy outcomes ;