Predicting health outcomes using data modeling approaches is an emerging field that can reveal important insights into disproportionate spending patterns. This book presents data driven methods, especially machine learning, for understanding and approaching the high utilizers problem, using the example of a large public insurance program.Five years ago I explained in this blog our experience on predictive modeling. This a key reference book.
It is difficult to assess to what extent performance-based MEAs have so far been successful. Few countries have formally evaluated their experience. Confidentiality of agreements continues to be a barrier to independent evaluation and little evidence is public. However, information available from expert interviews and from prior studies indicates that CED agreements have so far had a poor track record of reducing uncertainty around the performance of medicines. As a result, some countries have recently reformed CED schemes and some are discontinuing CED agreements altogether in favour of alternatives. The latter include restricted or conditional coverage without a MEA, whereby coverage is initially restricted to certain indications or patient groups and only broadened if and when additional evidence becomes available. Payment-by-result agreements continue to be used quite widely, but they do not always generate evidence
on product performance because data used for triggering payments are not always aggregated and analysed.
Clinicians, or their respective healthcare institutions, are facing a dilemma: while there is plenty of evidence of machine learning algorithms outsmarting their human counterparts, their deployment comes at the costs of high degrees of uncertainty. On epistemic grounds, relevant uncertainty promotes risk-averse decision-making among clinicians, which then might lead to impoverished medical diagnosis. From an ethical perspective, deferring to machine learning algorithms blurs the attribution of accountability and imposes health risks to patients. Furthermore, the deployment of machine learning might also foster a shift of norms within healthcare. It needs to be pointed out, however, that none of the issues we discussed presents a knockout argument against deploying machine learning in medicine.
Current clinical trials using the CRISPR platform aim to improve chimeric antigen receptor (CAR) T cell effectiveness, treat sickle cell disease and other inherited blood disorders, and stop or reverse eye disease. In addition, clinical trials to use genome editing for degenerative diseases including for patients with muscular dystrophy are on the horizon.
Notably, all of the genome-editing therapeutics under development aim to treat patients through somatic cell modification. These treatments are designed to affect only the individual who receives the treatment, reflecting the traditional approach to disease mitigation. However, genome editing offers the potential to correct disease causing mutations in the germline, which would introduce genetic changes that would be passed on to future generations.
At the time of writing, international commissions convened by the World Health Organization (WHO) and by the US National Academy of Sciences and National Academy of Medicine, together with the Royal Society, are drafting detailed requirements for any potential future clinical use.Meanwhile, CRISPR is closer than you think.
Human germline alteration is possible, due in part to democratization of genetic tools required for genome editing, and international scientific and legislative bodies are developing frameworks to manage the ramifications of this technology. Common among these frameworks are two pillars: public engagement and foundational principles. These components are necessary for respecting the autonomy of individuals and for fair processes and respecting diverse values.
However, they are not sufficient for protecting the most vulnerable members of society who may not even be in a position to participate in democratic processes. We propose implementing a HRIA, which captures concerns of public health and offers an opportunity to evaluate and anticipate the societal impact of GGE iteratively as the technology advances, public sentiments evolve, and cultural contexts shift. We recognize that this will raise new challenges of how such assessments are shared and implemented and how they can be enforced. We urge regulatory bodies and policy makers to consider this assessment approach in helping to establish robust regulatory frameworks necessary for the global protection of human rights.And the Geneva Statement on Heritable Human Genome Editing says:
No decision about whether to pursue heritable human genome modification can be legitimate without broadly inclusive and substantively meaningful public engagement and empowerment. Such deliberations may be challenging and messy. They will take time and organizing them will necessitate creativity, hard work, and significant human and financial resources. The course correction proposed here is essential to these efforts.I agree.
We must in the meantime respect the predominant policy position against pursuing heritable human genome modification, if we are to prevent individual scientists or small committees from making this momentous decision for us all. This will preserve time to cultivate an informed and engaged public that can consider and discuss the societal consequences of altering the genes of future generations and make wise, democratic decisions about the shared future we aspire to build.
Telemedicine services have the potential to improve effectiveness, efficiency and equity in health care, helping policy makers respond to increasing patient demands and needs. However, telemedicine interventions can also introduce new risks and amplify existing inequalities. In order for countries to maximise the benefits and limit the risks, telemedicine services need to improve the quality of care and provide clear benefits for patients. Telemedicine programmes that do not have benefits for patients are not worth pursuing and detract attention from other more effective interventions.
The provision of relevant, accurate, and timely performance information can play a pivotal role in ensuring the health system is able to deliver effective and efficient health services. Through its capacity to secure accountability in the health system, to determine appropriate treatment paths for patients, and to plan for future service patterns and structures, information can be used to identify and implement potential improvements in service delivery
