The implementation of remote care requires tele-health technology to evolve. Such systems must be responsive and adaptable to the local exigencies of the healthcare system. The increased capability for healthcare offered by patient monitoring must therefore make maximal use of information analysis / diagnosis; and engage in collaboration by medical professionals. And for diagnostic purposes, many clues lie in patient history; which means that the system must have wide access to all electronic health / patient records (EHRs / EPRs).

In recent years, there has been a rapid increase in health-related digital data (that is: EHRs / EPRs) generated by healthcare providers. Consequently, there has been prodigious improvement towards universal electronic health-record systems, which will enable automated aggregation of patient information. Advances in HIT (healthcare information technology) married with AI will make this vision a reality.

AI can help to make evaluations of patient history much quicker and more thorough–without consuming vital human resources (time and energy). A “smart” system can do this by serving as a prosthetic: providing prompts to the process, as well as clues to diagnostic possibilities based on a super-charged parsing of all available data. As a compliment to human intelligence, AI can prime healthcare workers to ask the right set of questions at any given juncture, thereby freeing them up to focus on other tasks. Medical diagnosis has moved from in-person clinical examination to largely evidence-based support. It is here that AI is playing a key role in analyzing evidence in order to determine the best course of action.

This has special relevance in oncology: considering the progress of diseases that could relate to the formation of various cancers, different diagnostic patterns might reflect different chances of cancer risks. Modeling disease progression and variants in disease trajectories helps in prediction…and thus prevention. By applying machine-learning methods to large data-sets (viz. of disease populations), AI will soon have a significant impact on the way doctors diagnose potential diseases.

A well-known area for tele-diagnosis is tele-dermatology, which lends itself well to automation through AI. Currently, diagnostic accuracy for melanoma is dependent on the experience and training of the treating doctor. A recent study has shown that a computer algorithm using CNNs (convolutional neural networks) outperformed the majority of dermatologists tested in accurately diagnosing melanoma.

Another study demonstrated classification of epidermal lesions using “deep” CNNs. This enabled the system to be trained end-to-end, from images directly, using only pixels and disease labels as inputs. The CNN achieves performance on par with all tested experts when it comes to identifying the most common cancers (spec. the identification of malignant melanoma), demonstrating that is AI capable of classifying skin cancers with a level of competence comparable to dermatologists. Similar promise is offered in other areas of automated diagnosis such as breast cancer or cervical cancer screening.

In addition, the contribution of imaging (ultrasounds, CT scans, MRIs, etc.) will bolster an AI’s ability to dependably make accurate diagnoses. The global reach of such systems reminds us that provision of care transcends the local concerns of any single clinical provider. By leveraging the power of AI technology, the marked increase in quality of healthcare delivery will encompass search / tracking, logistics, planning, statistical analysis, decision-making in treatment, problem-solving / diagnostics, communication, education, and service delivery.

Improvements in tele-health (a.k.a. “eHealth”/”mHealth”; i.e. remote healthcare) is based in large part on advances in HIT–which, in turn, is primarily contingent on the growing role of AI technology. The availability of large data-sets combined with the evolution of machine-learning offers promising opportunities for diagnostics and better clinical decision-making. This quantum leap in technology has the potential to significantly improve health outcomes.