Deciphering clinical abbreviations with a privacy protecting machine learning system.

Physicians write clinical notes with abbreviations and shorthand that are difficult to decipher. Abbreviations can be clinical jargon (writing "HIT" for "heparin induced thrombocytopenia"), ambiguous terms that require expertise to disambiguate (using "MS" for "multiple sclerosis" or "mental status"), or domain-specific vernacular ("cb" for "complicated by"). Here we train machine learning models on public web data to decode such text by replacing abbreviations with their meanings. We report a single translation model that simultaneously detects and expands thousands of abbreviations in real clinical notes with accuracies ranging from 92.1%-97.1% on multiple external test datasets. The model equals or exceeds the performance of board-certified physicians (97.6% vs 88.7% total accuracy). Our results demonstrate a general method to contextually decipher abbreviations and shorthand that is built without any privacy-compromising data.

User-centred design for machine learning in health care: a case study from care management.

OBJECTIVES: Few machine learning (ML) models are successfully deployed in clinical practice. One of the common pitfalls across the field is inappropriate problem formulation: designing ML to fit the data rather than to address a real-world clinical pain point. METHODS: We introduce a practical toolkit for user-centred design consisting of four questions covering: (1) solvable pain points, (2) the unique value of ML (eg, automation and augmentation), (3) the actionability pathway and (4) the model's reward function. This toolkit was implemented in a series of six participatory design workshops with care managers in an academic medical centre. RESULTS: Pain points amenable to ML solutions included outpatient risk stratification and risk factor identification. The endpoint definitions, triggering frequency and evaluation metrics of the proposed risk scoring model were directly influenced by care manager workflows and real-world constraints. CONCLUSIONS: Integrating user-centred design early in the ML life cycle is key for configuring models in a clinically actionable way. This toolkit can guide problem selection and influence choices about the technical setup of the ML problem.

Modelled effects of prawn aquaculture on poverty alleviation and schistosomiasis control.

Recent evidence suggests that snail predators may aid efforts to control the human parasitic disease schistosomiasis by eating aquatic snail species that serve as intermediate hosts of the parasite. Potential synergies between schistosomiasis control and aquaculture of giant prawns are evaluated using an integrated bio-economic-epidemiologic model. Combinations of stocking density and aquaculture cycle length that maximize cumulative, discounted profit are identified for two prawn species in sub-Saharan Africa: the endemic, non-domesticated Macrobrachium vollenhovenii, and the non-native, domesticated Macrobrachium rosenbergii. At profit maximizing densities, both M. rosenbergii and M. vollenhovenii may substantially reduce intermediate host snail populations and aid schistosomiasis control efforts. Control strategies drawing on both prawn aquaculture to reduce intermediate host snail populations and mass drug administration to treat infected individuals are found to be superior to either strategy alone. Integrated aquaculture-based interventions can be a win-win strategy in terms of health and sustainable development in schistosomiasis endemic regions of the world.