Description:
Fast track proposals will be accepted. Direct-to-Phase II proposals will not be accepted. Number of anticipated awards: 2-3 Budget (total costs, per award): Phase I: up to $400,000 for up to 9 months; Phase II: up to $1,680,879 for up to 2 years
PROPOSALS THAT EXCEED THE BUDGET OR PROJECT DURATION LISTED ABOVE MAY NOT BE FUNDED.
Summary
The rapid adoption of wearable, cyber-physical, and ambient sensing platforms since 2015 by the consumer health market have begun to pave the way for similar platforms to act as objective measures for continuous, out-of-clinic cancer research and patient assessment. They collectively will be a key component of the perceived future for Smart and Connected communities via a continually linked internet of health sensors. The passive, continuously measured data streams generated by current or future physical and chemical/biological sensors will allow direct/indirect measures of cancer progression and its symptoms. Increased out-of-clinic patient and clinician engagement via these tools will allow more precise delivery of cancer care after as well as during cancer remission. Ultimately, these passive sensing platforms’ data for digital biomarkers will afford clinicians: 1) more objective metrics of response to therapeutics; 2) control and auto-reporting of symptoms and their fluctuations; 3) monitoring of side-effects of experimental or standard of care therapies; and 4) more ecologically valid clinical endpoints, all decreasing assessment burden via increased continuity of physiological measurement sampling and patient context in the ambulatory setting.
Near real-time analytical capability such as what these devices offer represents an opportunity to measure population-based statistics from large cohorts of cancer patients by way of the myriad of devices currently available or being developed. From vital signs, physical activity, or non-invasive patch based measures of biochemistry from bodily fluids to external monitoring of environment, these tools will offer a more complete picture of patient performance status, fatigue, other symptoms, cachexia, and patient monitoring (e.g., drug metabolism, toxicity, adherence, adverse events or side effects) during clinical trials, in convenient small form factors with the ability to auto-report these data for research purposes or informed clinical assessment of patients outside of the clinic.
In order to ascertain the potential of these tools for more precise delivery of cancer care and patient monitoring, much clinical cancer research must be performed to understand sensor measurement versus cancer progression and patient context outside of the clinic. As much of the power of these technologies lie in their ability to offer a granularity not seen before in patient-specific data, the research to advance this to the clinical setting will rely on tools already commercialized or of research grade platforms not yet translated. Moreover, as any one wearable sensor-specific parameter will unlikely allow for both patient physiology and context in which the measurement was taken, multiple devices and subsequent parameters will be necessary to enable commercialization of more targeted and specific devices for clinical cancer care or assessment.
There is a considerable need for scalable informatics tools that allow automated data aggregation, integration and machine learning/artificial intelligence (AI)/predictive analytics that can pull from disparate data sets across device vendors and have the flexibility to add new measures as they are developed. Furthermore, a central software platform that could obtain wearable, implantable, or external device data and uniformly compare/contrast/couple data streams to understand physiology versus patient context with respect to time will advance this unique approach to aid cancer patients, clinician assessment and clinical trial design.
Project Goals
The goal is in development, and subsequent commercialization, of scalable informatics tools and resources for their broad adoption across the burgeoning clinical cancer research applications that continuous, passive monitoring of multiple biological parameters via wearable platform technologies are beginning to be used. A limitation to their current use in cancer research, to more objectively understand cancer patient progression or cancer-specific symptoms, is that device manufacturers and platform technology developers do not utilize identical data sets / standards and no resources are available to easily assess large multiparameter data sets via traditional bioinformatics methods. As such, the primary focus of this contract topic is on data agnostic informatics tools and resources that can be easily adopted in the cancer research communities for cohort studies involving their monitoring platform(s) of choice to understand their specific research problem / patient cohort of choice. Informatics tools include mobile apps for sensor data retrieval; computer software tools and platforms to aggregate, integrate and organize data streams from multiple devices; and machine/deep learning or predictive analytic informatics ‘AI’ platforms for subsequent interpretation of integrated data streams derived from a myriad of continuous passive monitoring devices that could be used by cancer researchers. The informatics resources include sensor and patient data repositories and platforms that provide data, workflow, and a workspace for online research collaboration, evaluation as well as dissemination of informatics tools and resources, and support for population-based research.
The overall scope of proposed funding approach includes the entire spectrum of passive continuous monitoring devices being commercialized or developed, extending from wearable sensor platforms and implantable devices to external monitoring devices for all phases of cancer clinical research. Offerors will be expected to formulate and execute well-
designed project plans with clearly defined milestones that will eventually lead to commercially viable solutions for: 1) sustained development and evolution of passive continuous monitoring platform informatics tools and resources; and 2) their broad adoption in clinical cancer research.
Activities outside the scope of this Topic:
Tools that do not allow the integration and subsequent interpretation of a myriad of current wearable sensor platforms simultaneously, or that use only data from inertial sensing wearables; tools that are not scalable to future wearable, implantable or external out of clinic monitoring; tools that do not incorporate safeguards to protect privacy and confidentiality of information; design approaches that don’t account for scalability, interoperability or user-centered design; approaches that don’t plan for using tools in diverse sites and IT systems.
Phase I Activities and Deliverables
• Establish a project team including proven expertise in: sensor technology for physiological monitoring, wireless sensor integration with mobile devices, secure wireless transport of health data using standards based protocols, secure cloud computing models, bioanalytical technologies, epidemiology, biostatistics/bioinformatics, and systems architecture
• Provide a report including a detailed description and/or technical documentation of the proposed:
o Development of bioinformatic methods or algorithms (e.g., machine/deep learning, etc.) for wearable sensor data integration across data inputs from diverse wearable bio-/sensor platforms, including harmonization of data of the same biometric from different vendor device platforms
o Evaluation of a wide range of wearable, implantable, and external sensor platforms that would be of legitimate use for out of clinic patient monitoring and / or understanding disease / symptom progression (e.g., therapy-induced fatigue, patient performance status, cachexia, experimental therapeutic side effects, toxicity, etc.) vs. the myriad of potential physical and / or physiological factors
o Development of the database structure for the proposed system's chem-/bio-/physical sensor-based data inputs and metadata requirements
o Database formats that support the import and export of individual datasets and coalesced datasets, store structured data from different sources of wearable sensor data, and are readily used for data integration and Quality Control (QC) protocols
o Specific approach to QC
o Technology compatibility matrix for Phase I and Phase II wearable sensor data sources by platform, sensor type, sensor technology, and differing device data streams as well as and back-end server systems to be developed
o Data visualization, feedback, and reporting systems for population or clinical monitoring and research applications
o Data integration approaches to leverage multiple data input streams
o Data types for exchange of physiological-metrics between mobile platforms and secure servers
o Data standards for transfer and importation of individual wearable sensor data and storage of individual and coalesced wearable sensor data
o Transparent, documented, and non-proprietary bio-/informatic methods
o Description of additional software and hardware required for use of the tool.
• Provide wireframes and user workflows for proposed Graphical User Interface (GUI) and software functions that:
o Support the import and export of individual datasets and coalesced datasets
o Implement, script or automate all features and functions of the data integration tool(s)
o Conduct QC of coalesced datasets
• Develop a functional prototype system from the planned Phase I compatibility matrix that includes:
o Front-end mobile applications to facilitate and control the collection and transport of multiple wearable chem-/bio-/physical sensor data inputs and any associated metadata used within the system
o Integration with several wearable chem-/bio-/physical sensor
o Automated data screening algorithms and importation protocols for data transferred from the mobile application to the back-end server systems
o Software systems GUI (web- or computer-based)
o Software tools as mobile and web applications
o Back-end user-interface controls for custom data integration and visualization for individual or group-level data
o Finalize database formats and structure, data collection, transport, and importation methods for targeted data inputs
• Include funds in the budget to present Phase I findings in a detailed report and demonstrate the final prototype to an NCI evaluation panel.
Phase II Activities and Deliverables
• Expand the informatic methods to include other research grade sensor data points or streams, in addition to already identified commercialized wearable sensor data, and demonstrate data integration across inputs from diverse sensor platforms
• Demonstrate database integration capability to collect data from four different parameters and collected from three distinct wearable device platforms, as well as to be adaptable to at least 20 more current or future platforms designed for physiological or objective measurements of patients outside of the clinic
• Participate in validation and scale-up between the contractor, NCI, and / or contractor-identified third party sources to access relevant input data types for the proposed project. Validation within established cohort studies with wearable sensor data (e.g., pre-identified analytes of use to monitoring of syndrome-specific therapeutics, patient fatigue, or similar cancer cachexia-specific physiological metric, etc.) will serve to: 1) train and validate the expanded bioinformatic methods; and 2) demonstrate the application of these methods through scalable software to automate complex data integration tasks for wearable sensor data sources
• Beta-test and finalize front-end mobile applications developed in Phase I
• Beta-test and finalize automated file transfer, screening, and database importation protocols and systems
• Perform regression testing for both front-end and back-end system functions
• Demonstrate usability of scalable software through the following:
o Beta-test and finalize automated file transfer, database importation protocols, wearable biosensor data integration applications and reporting tools developed in Phase I
o Develop beta-test, finalize, and demonstrate the GUI
o Demonstrate the software systems ability to integrate data from planned Phase II technology compatibility matrix data sources using automated algorithms and analytic methods
• Conduct usability testing of the GUI elements of the sensor-specific data integration tool(s)
• Conduct usability testing of consumer/patient-facing mobile applications and any associated web portals and care team/researcher-facing user interface features including system management, analyses, and reporting applications
• Develop systems documentation to support the software and informatic methods
• In the first year of the contract, provide the Program and Contract officers with a letter(s) of commercial interest
• In the second year of the contract, provide the Program and Contract officers with a letter(s) of commercial commitment
