Background Mental health policy makers require evidence-based information to optimise effective care provision based on local need, but tools are unavailable. Aims To develop and validate a population-level prediction model for need for early intervention in psychosis (EIP) care for first-episode psychosis (FEP) in England up to 2025, based on epidemiological evidence and demographic projections. Method We used Bayesian Poisson regression to model small-area-level variation in FEP incidence for people aged 16–64 years. We compared six candidate models, validated against observed National Health Service FEP data in 2017. Our best-fitting model predicted annual incidence case-loads for EIP services in England up to 2025, for probable FEP, treatment in EIP services, initial assessment by EIP services and referral to EIP services for ‘suspected psychosis’. Forecasts were stratified by gender, age and ethnicity, at national and Clinical Commissioning Group levels. Results A model with age, gender, ethnicity, small-area-level deprivation, social fragmentation and regional cannabis use provided best fit to observed new FEP cases at national and Clinical Commissioning Group levels in 2017 (predicted 8112, 95% CI 7623–8597; observed 8038, difference of 74 [0.92%]). By 2025, the model forecasted 11 067 new treated cases per annum (95% CI 10 383–11 740). For every 10 new treated cases, 21 and 23 people would be assessed by and referred to EIP services for suspected psychosis, respectively. Conclusions Our evidence-based methodology provides an accurate, validated tool to inform clinical provision of EIP services about future population need for care, based on local variation of major social determinants of psychosis.

Combining machine learning with social network analysis (SNA) can leverage vast amounts of social media data to better respond to crises. We present a case study using Twitter data from the March 2019 Nebraska floods in the United States, which caused over $1 billion in damage in the state and widespread evacuations of residents. We use a subset of machine learning, deep learning (DL), to classify text content of 11,982 tweets, and we integrate that with SNA to understand the structure of tweet interactions. Our DL approach pre‐trains our model with a DL language technique, BERT, and then trains the model using the standard training dataset to sort a dataset of tweets into classes tailored to crisis events. Several performance measures demonstrate that our two‐tiered trained model improves domain adaptation and generalization across different extreme weather event types. This approach identifies the role of Twitter during the damage containment stage of the flood. Our SNA identifies accounts that function as primary sources of information on Twitter. Together, these two approaches help crisis managers filter large volumes of data and overcome challenges faced by simple statistical models and other computational techniques to provide useful information during crises like flooding.

Background: Mental health service policymakers require evidence-based information to optimise effective care provision based on local need, but tools are unavailable. We developed and validated a population-level prediction model to forecast need for early intervention in psychosis [EIP] services in England up to 2025.Methods: We fitted six candidate Bayesian Poisson regression models, combining epidemiological data on psychosis risk, to predict new annual caseload of referrals, assessed, treated, and probable first episode psychosis [FEP] cases in EIP services, aged 16-64 years at small-area level. Models were validated against observed NHS Mental Health Services Data Set [MHSDS] data at Clinical Commissioning Group [CCG] and national levels for 2017. Projections were made up to 2025, based on small-area demographic forecasts. Outcome: In 2017, our best-fitting model predicted 8,112 (95% interval: 7,623 to 8,597) individuals with probable FEP in England, compared with 8,038 observed in the MHSDS (difference: n=+74; +0·92%), after accounting for psychosis risk by age, sex, ethnicity, small area-level deprivation, social fragmentation and regional cannabis use. In 2020, this model forecasted 9,066 new treated FEP cases (8,485 to 9,618), rising 1% annually up to 2025. For every ten treated cases, we forecasted that 23 and 21 people would be referred to and assessed by EIP services, respectively, for “suspected FEP”. Interpretation: Our methodology provides an accurate, validated toolkit to inform planners, commissioners and providers about future population need for psychosis care at different stages of the referral pathway, based on local determinants of need.Funding: Wellcome Trust, Royal Society, National Institute for Health Research