Table 3.

Potential AI applications in space health.

Potential AI Applications
Risk Prediction Models
Risk prediction models for development of cancer due to ionizing radiation exposure based on animal models [78,79]
Inflight AI assisted multi-omic research using the Edge TPU to generate novel risk prediction scores [80]
Risk prediction models for the development of cardiovascular disease based on carotid-femoral pulse wave velocity obtained via Doppler ultrasound or AI-guided analysis of 3D printed tissue models [81]
Risk prediction models such as the modified Astro-CHARM model which combines a patient’s CAC score with non-traditional risk factors associated with space travel (e.g., radiation exposure, microgravity exposure, dysbiosis of gut microbiota, etc.) to identify those at risk for accelerated atherosclerosis [82]
Predicting antimicrobial resistance of novel bacterial species (e.g., Methylobacterium ajmalii sp. nov., Methylobacterium rhodesianum, etc.) based on whole genome sequencing data [83]
AI-based models for the identification of causal relationships between various exposures and subsequent cancer development (e.g., CRISP) [84]
Medical Screening Preflight and Inflight Monitoring
AI monitoring for gut microbiota dysbiosis using smart toilets during pre-, intra-, and post-flight periods [2,85,86]
Screening for latent virus infection or reactivation based on immunological variables, which can then be used as a biomarker for assessment of adaptive immune function [87,88]
The Edge TPU and other similar low-power AI ASICs could be used to monitor genomic imprinting (e.g., DNA methylation signatures or epigenetic/transcriptomic-based tests) for inflight lung cancer screening (may be equivalent to low-dose CT chest screening) [63,89,90]
AI screening for mental illness through facial recognition and vocal analysis [68,69]
A combination of AI and imaging could potentially identity abnormal or misfolded proteins [91,92]
Deep learning algorithms for the inflight telediagnosis of various conditions (e.g., skin lesions or SANS) [93,94,95]
AI-integrated wearable technology for space suits (e.g., exoskeletons) to monitor biodata (e.g., electrocardiogram, blood pressure, sleep cycle, body temperature, etc.) [96,97]
AI monitoring of metabolomics-based biomarkers for assessment of sleep quality and circadian rhythm [98]
AI can be used to analyze retinal fundus photography to identify and monitor space anemia [99]
Medical Diagnostic Tools
The Edge TPU and other similar low-power AI ASICs (i.e., Google Coral Edge TPU, NVIDIA Jetson Nano, Intel Neural Compute Stick 2) could advance image segmentation AI models, allowing for these models to be feasibly deployed in ultrasound point-of-care settings (e.g., detection of DVT, structural heart disease, hemodynamic changes), even procedural guidance [100].
AI-based system designed to guide non-physicians on the proper acquisition of medical diagnostic testing using The Edge TPU and deep reinforcement learning
AI-enhanced 3D-imaging technology (e.g., micro-CT scanners) [101]
Utilization of the Edge TPU and other similar low-power AI ASICs to provide the necessary processing power for high-performance parallel-processing space research [102]
Intervention
AI-guided minor surgical procedures [such as incision and drainage (I&D)] using next-generation High Performance Spaceflight Computing (HPSC) [103]
AI-assisted, remotely controlled robotic PCI and robotic laparoscopic surgery (e.g., telecholecystectomy and teleappendectomy); made possible by a reduction in communication latency beyond a lag of 200 ms [103,104,105,106,107]
Using AI predictions of drug metabolism and effectiveness based on an individual’s multiomic data prior to medication or supplement distribution (e.g., melatonin, immune supplements, probiotics) [108,109]
Disease Prevention
AI-integrated space suits (e.g., exoskeletons) to maximize EVA time and operating pressure, and minimize space radiation exposure [110,111]
3D printing of personalized devices (e.g., ear plugs to prevent noise source generated from man-made sources), space shields, space suits for use in emergency scenarios [112,113,114]
AI-based chatbots or social media could potentially be used to prevent anxiety and depression during long-duration space travel. The Edge TPU could potentially be used in advancing an internet or social media for the moon, known as LunaNet [115].
AI-improved augmented reality/virtual reality to reduce/prevent Spaceflight-Associated Neuro-Ocular Syndrome (SANS), space motion sickness (SMS), and post-flight motion sickness (PFMS) [116,117,118]
AI identification of an individual’s radiosensitivity (genotype-phenotype) using multiomics to prevent the negative effects of ionizing radiation [119,120,121]
Emerging technology could allow for the transfer of large volumes of data at faster rates in order to facilitate medical research in space [122]
AI can be used to create novel metrics (e.g., travelers’ satisfactions, post spaceflight measurements for travelers) and ethics (e.g., health insurance)