Technologies leveraging big data, including predictive algorithms and machine learning, are playing an increasingly important role in the delivery of healthcare. However, evidence indicates that such algorithms have the potential to worsen disparities currently intrinsic to the contemporary healthcare system, including racial biases. Blame for these deficiencies has often been placed on the algorithm—but the underlying training data bears greater responsibility for these errors, as biased outputs are inexorably produced by biased inputs. The utility, equity, and generalizability of predictive models depend on population-representative training data with robust feature sets. So while the conventional paradigm of big data is deductive in nature—clinical decision support—a future model harnesses the potential of big data for inductive reasoning. This may be conceptualized as clinical decision questioning, intended to liberate the human predictive process from preconceived lenses in data solicitation and/or interpretation. Efficacy, representativeness and generalizability are all heightened in this schema. Thus, the possible risks of biased big data arising from the inputs themselves must be acknowledged and addressed. Awareness of data deficiencies, structures for data inclusiveness, strategies for data sanitation, and mechanisms for data correction can help realize the potential of big data for a personalized medicine era. Applied deliberately, these considerations could help mitigate risks of perpetuation of health inequity amidst widespread adoption of novel applications of big data.
Objective The development of machine learning (ML) algorithms to address a variety of issues faced in clinical practice has increased rapidly. However, questions have arisen regarding biases in their development that can affect their applicability in specific populations. We sought to evaluate whether studies developing ML models from electronic health record (EHR) data report sufficient demographic data on the study populations to demonstrate representativeness and reproducibility. Materials and Methods We searched PubMed for articles applying ML models to improve clinical decision-making using EHR data. We limited our search to papers published between 2015 and 2019. Results Across the 164 studies reviewed, demographic variables were inconsistently reported and/or included as model inputs. Race/ethnicity was not reported in 64%; gender and age were not reported in 24% and 21% of studies, respectively. Socioeconomic status of the population was not reported in 92% of studies. Studies that mentioned these variables often did not report if they were included as model inputs. Few models (12%) were validated using external populations. Few studies (17%) open-sourced their code. Populations in the ML studies include higher proportions of White and Black yet fewer Hispanic subjects compared to the general US population. Discussion The demographic characteristics of study populations are poorly reported in the ML literature based on EHR data. Demographic representativeness in training data and model transparency is necessary to ensure that ML models are deployed in an equitable and reproducible manner. Wider adoption of reporting guidelines is warranted to improve representativeness and reproducibility.
Background NGLY1 deficiency is a rare autosomal recessive disorder caused by loss in enzymatic function of NGLY1, a peptide N -glycanase that has been shown to play a role in endoplasmic reticulum associated degradation (ERAD). ERAD dysfunction has been implicated in other well-described proteinopathies, such as Alzheimer’s disease, Parkinson’s disease, and Huntington’s disease. The classical clinical tetrad includes developmental delay, hypolacrima, transiently elevated transaminases, and hyperkinetic movement disorders. The musculoskeletal system is also commonly affected, but the orthopaedic phenotype has been incompletely characterized. Best practices for orthopaedic clinical care have not been elucidated and considerable variability has resulted from this lack of evidence base. Our study surveyed patients enrolled in an international registry for NGLY1 deficiency in order to characterize the orthopaedic manifestations, sequelae, and management. Results Our findings, encompassing the largest cohort for NGLY1 deficiency to date, detail levels of motor milestone achievement; physical exam findings; fracture rates/distribution; frequency of motor skill regression; non-pharmacologic and non-procedural interventions; pharmacologic therapies; and procedural interventions experienced by 29 participants. Regarding the orthopaedic phenotype, at time of survey response, we found that over 40% of patients experienced motor skill regression from their peak. Over 80% of patients had at least one orthopaedic diagnosis, and nearly two-thirds of the total had two or more. More than half of patients older than 6 years had sustained a fracture. Related to orthopaedic non-medical management, we found that 93 and 79% of patients had utilized physical therapy and non-operative orthoses, respectively. In turn, the vast majority took at least one medication (including for bone health and antispasmodic therapy). Finally, nearly half of patients had undergone an invasive procedure. Of those older than 6 years, two-thirds had one or more procedures. Stratification of these analyses by sex revealed distinctive differences in disease natural history and clinical management course. Conclusions These findings describing the orthopaedic natural history and standard of care in patients with NGLY1 deficiency can facilitate diagnosis, inform prognosis, and guide treatment recommendations in an evidence-based manner. Furthermore, the methodology is notable for its partnership with a disease-specific advocacy organization and may be generalizable to other rare disease populations. This study fills a void in the existing literature for this population and this methodology offers a precedent upon which future studies for rare diseases can build.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.