Concepts in Disruptive Technology
A motion sensor within smartphones that can be used to detect what type of activity the user is doing. The accelerometer captures the X-Y-Z coordinates of the phone in G-forces, which provides information on the phone’s orientation and acceleration in space.
A procedure run on data to create a machine learning “model.”
Ambulatory Assessment (AA)
Assessment of people in their natural environments, outside constrained clinical settings or artificial laboratory environments. (See also EMA below).
Artificial Intelligence (AI)
Technology designed to perform human cognitive tasks Mimics human behavior and thinking and decision-making, e.g., Alexa, Amazon, Tesla, Siri.
Artificial Intelligence with an “assistive role” that enhances—not replaces-- human decision-making expertise and capabilities, e.g., computer chess games, autonomous vehicles, Netflix.
A technology that superimposes a computer-generated image on a user's view of the real world, thus providing a composite view.
Automatic detection of specific markers; Examples: voice, heart rate/variability, blood pressure, respiratory rate, eye tracking etc.
Used to manage and secure large amounts of data; also used for AI programs that collect enormous amounts of patient data for predictive modeling—which is encrypted on blockchain and ‘decentralized’.
Examples: CDC uses to monitor disease outbreak trails/patterns; medical records or DNA sequencing data, platforms for incentive programs based on health data, drug traceability/counterfeiting).
Common Data Element (CDE)
A standardized, precisely defined question that is paired with a set of specific allowable responses, that is then used systematically across different sites, studies, or clinical trials to ensure consistent data collection.
A method of inferring human states and behaviors through digital devices such as smartphones and smartwatches. Digital phenotyping can involve both active tasks (e.g., cognitive tasks, surveys) and passive sensing (e.g., physical activity, sleep).
Changes and innovations in a sector that are so profound they alter the way service is rendered or performed-disrupts the old market- and creates entirely new market, creates significant societal impact.
Disruptive Technology Initiative: An AACN initiative that aims to identify and share with AACN members new technologies or practices that have the capacity to fundamentally change the practice of clinical neuropsychology.
A form of Machine Learning that uses multiple-layer artificial Neural Networks through which data is progressively transformed, e.g., Chat bots, Netflix, Alexa, autonomous vehicles, facial recognition.
Use of evidence-based technology in medical measurement and intervention; data are longitudinal and highly personalized, unlike snapshot sample measures in clinic. May measure only, or measure and intervene (combination) like glucose monitoring- insulin pump or EKG reading reporting to MD who interprets data. May use biomarkers eg voice tremor, electronic assessment, eg patient survey, tools measuring safety/compliance eg wearable fall detection device, or smart mirror passive monitoring. Not the same as Digital Wellness Products (See below).
Digital Wellness Products
Measure things that can affect well being like sleep, weight etc not as strongly supported by evidence to medical in nature; not a “medical device” which has specific connotations.
Entails user input or interaction to provide correlating real-time data; Examples: cognition, grip strength, voice tracking.
Ecological momentary assessment (EMA)
A method for sampling experience by requesting input from the respondent at pre-specified intervals. It is a form of AA used to study dynamic processes via repeated assessment of cognition, self-reported symptoms, and/or physiological processes during daily regular activity using electronic devices.
Term used to describe interactive process between clinician and AI analysis.
Monitors signs of cognitive or emotional response in absence of self report; for example, Affectiva program to analyze focus groups.
System that allows one to reconstruct why an AI driven process came up with a certain decision. Used often to discuss “Clever Hans” phenomenon or reliance on spurious correlations [Lapuschkin S, Wäldchen S, Binder A, Montavon G, Samek W, Müller KR. Unmasking Clever Hans predictors and assessing what machines really learn. Nat Commun. 2019 Mar 11;10(1):1096. doi: 10.1038/s41467-019-08987-4. PMID: 30858366; PMCID: PMC6411769]
A Global Positioning System (GPS) provides location information based on signals it receives from satellites. GPS sensors within smartphones can tell us the approximate latitude, longitude, and altitude of the smartphone, which provides a proxy for the user’s location.
Internet of Bodies
Network of smart devices in or on body; Examples: Bluetooth connected cochlear implants.
Internet of Things
Network of objects/things embedded with technology that enables data connection and sharing with other things all over the internet; •Examples: smart homes, wearables, remote appliance monitoring. (for instance, Utility meters, Vacuums, Voice assistants, Baby clothes, Pill bottles, Helmets, Thermometers, Video games, Wearable devices, Implants, Drug delivery systems , Locks, Kitchen appliances, Lighting, Security cameras, Smoke alarms, Speakers, Thermostats, Toys, Water bottles, Neurostimulators, Patient ID and tracking, inhalers Monteith, S., Glenn, T., Geddes, J., Severus, E., Whybrow, P. C., & Bauer, M. (2021). Internet of things issues related to psychiatry. International journal of bipolar disorders, 9(1), 11. https://doi.org/10.1186/s40345-020-00216-y]
Just-in-time adaptive interventions
Interventions that are delivered at the moment when the person needs it the most; sensors may be used as inputs to facilitate these interventions (e.g., smartwatches can tell the user to get up and walk around after detecting a sedentary period).
Computing that, through high speed data analysis, learns from experience and modifies performance with practice without being specifically programmed to do so; used for categorization, image, speech or pattern recognition, and prediction, using enormous data sets, among other tasks; a subfield of artificial intelligence that gives computers the ability to learn without explicitly being programmed.
Data that provides information about other data, but not the content of the data. For example, communication metadata provides the number of texts/calls sent/received from unique phone numbers along with the associated timestamp, but would not provide the content of the texts/calls or the sending/receiving phone number.
An open-source smartphone application developed for research and clinical use by the Division of Digital Psychiatry at the Beth Israel Deaconess Medical Center. mindLAMP can be used to collect a range of active (e.g. survey, mobile cognitive testing) and passive (sensor) data.
A model is a specific representation learned from data by applying some machine learning algorithm. A model is also called a hypothesis.
A computer program's ability to understand human language as it is spoken and written -- referred to as natural language. It is a component of artificial intelligence (AI).
A type of machine learning, based on biological neural networks and models of cognitive processing in the brain. Examples: Data mining, monitoring and adjustment system for WiFi in a chain of grocery stores; ATM networks, real-time translation.
Data collection without direct engagement; Examples: emotion detection, skin variation, hair loss, glucose, heart rate.
Physical circadian routine
A mobility feature that can be derived from GPS data, which compares the similarity in a person’s locations over the course of a day to that of the other days in the data set. The value ranges between 0 and 1, with 1=identical routine and 0=completely different routine.
Interactions between patient and clinician, online, or remotely via platform.
The practice of neuropsychology using synchronous telecommunications methods, usually both audio and video using online platforms (e.g., Zoom).
Variability in Everyday Behavior (VIBE) model
A conceptual framework proposed by Hackett & Giovannetti (2022) that integrates known trends from the cognitive aging literature on changes in activity level and intraindividual variability; this model provides testable hypotheses and a theoretical framework for digital phenotyping studies that collect information on everyday behavior in older adults.
The computer-generated simulation of a three-dimensional image or environment that can be interacted with in a seemingly real or physical way by a person using special electronic equipment, such as a helmet with a screen inside or gloves fitted with sensors.