Monitoring the COVID-19 epidemic with nationwide telecommunication data.

In response to the novel coronavirus disease (COVID-19), governments have introduced severe policy measures with substantial effects on human behavior. Here, we perform a large-scale, spatiotemporal analysis of human mobility during the COVID-19 epidemic. We derive human mobility from anonymized, aggregated telecommunication data in a nationwide setting (Switzerland; 10 February to 26 April 2020), consisting of ∼1.5 billion trips. In comparison to the same time period from 2019, human movement in Switzerland dropped by 49.1%. The strongest reduction is linked to bans on gatherings of more than five people, which are estimated to have decreased mobility by 24.9%, followed by venue closures (stores, restaurants, and bars) and school closures. As such, human mobility at a given day predicts reported cases 7 to 13 d ahead. A 1% reduction in human mobility predicts a 0.88 to 1.11% reduction in daily reported COVID-19 cases. When managing epidemics, monitoring human mobility via telecommunication data can support public decision makers in two ways. First, it helps in assessing policy impact; second, it provides a scalable tool for near real-time epidemic surveillance, thereby enabling evidence-based policies.

Machine learning for non-invasive sensing of hypoglycaemia while driving in people with diabetes.

AIM: To develop and evaluate the concept of a non-invasive machine learning (ML) approach for detecting hypoglycaemia based exclusively on combined driving (CAN) and eye tracking (ET) data. MATERIALS AND METHODS: We first developed and tested our ML approach in pronounced hypoglycaemia, and then we applied it to mild hypoglycaemia to evaluate its early warning potential. For this, we conducted two consecutive, interventional studies in individuals with type 1 diabetes. In study 1 (n = 18), we collected CAN and ET data in a driving simulator during euglycaemia and pronounced hypoglycaemia (blood glucose [BG] 2.0-2.5 mmol L-1 ). In study 2 (n = 9), we collected CAN and ET data in the same simulator but in euglycaemia and mild hypoglycaemia (BG 3.0-3.5 mmol L-1 ). RESULTS: Here, we show that our ML approach detects pronounced and mild hypoglycaemia with high accuracy (area under the receiver operating characteristics curve 0.88 ± 0.10 and 0.83 ± 0.11, respectively). CONCLUSIONS: Our findings suggest that an ML approach based on CAN and ET data, exclusively, enables detection of hypoglycaemia while driving. This provides a promising concept for alternative and non-invasive detection of hypoglycaemia.

Glycaemic patterns of male professional athletes with type 1 diabetes during exercise, recovery and sleep: Retrospective, observational study over an entire competitive season.

AIMS: To analyse glycaemic patterns of professional athletes with type 1 diabetes during a competitive season. MATERIALS AND METHODS: We analysed continuous glucose monitoring data of 12 professional male cyclists with type 1 diabetes during exercise, recovery and sleep on days with competitive exercise (CE) and non-competitive exercise (NCE). We assessed whether differences exist between CE and NCE days and analysed associations between exercise and dysglycaemia. RESULTS: The mean glycated haemoglobin was 50 ± 5 mmol/mol (6.7 ± 0.5%). The athletes cycled on 280.8 ± 28.1 days (entire season 332.6 ± 18.8 days). Overall, time in range (3.9-10 mmol/L) was 70.0 ± 13.7%, time in hypoglycaemia (<3.9 mmol/L) was 6.4 ± 4.7% and time in hyperglycaemia (>10 mmol/L) was 23.6 ± 12.5%. During the nights of NCE days, athletes spent 10.1 ± 7.4% of time in hypoglycaemia, particularly after exercise in the endurance zones. The CE days were characterized by a higher time in hyperglycaemia compared with NCE days (25.2 ± 12.5% vs. 22.2 ± 12.1%, p = .012). This was driven by the CE phase, where time in range dropped to 60.4 ± 13.0% and time in hyperglycaemia was elevated (38.5 ± 12.9%). Mean glucose was higher during CE compared with NCE sessions (9.6 ± 0.9 mmol/L vs. 7.8 ± 1.1 mmol/L, p < .001). The probability of hyperglycaemia during exercise was particularly increased with longer duration, higher intensity and higher variability of exercise. CONCLUSIONS: The analysis of glycaemic patterns of professional endurance athletes revealed that overall glycaemia was generally within targets. For further improvement, athletes, team staff and caregivers may focus on hyperglycaemia during competitions and nocturnal hypoglycaemia after NCE.

Machine Learning for Predicting Micro- and Macrovascular Complications in Individuals With Prediabetes or Diabetes: Retrospective Cohort Study.

BACKGROUND: Micro- and macrovascular complications are a major burden for individuals with diabetes and can already arise in a prediabetic state. To allocate effective treatments and to possibly prevent these complications, identification of those at risk is essential. OBJECTIVE: This study aimed to build machine learning (ML) models that predict the risk of developing a micro- or macrovascular complication in individuals with prediabetes or diabetes. METHODS: In this study, we used electronic health records from Israel that contain information about demographics, biomarkers, medications, and disease codes; span from 2003 to 2013; and were queried to identify individuals with prediabetes or diabetes in 2008. Subsequently, we aimed to predict which of these individuals developed a micro- or macrovascular complication within the next 5 years. We included 3 microvascular complications: retinopathy, nephropathy, and neuropathy. In addition, we considered 3 macrovascular complications: peripheral vascular disease (PVD), cerebrovascular disease (CeVD), and cardiovascular disease (CVD). Complications were identified via disease codes, and, for nephropathy, the estimated glomerular filtration rate and albuminuria were considered additionally. Inclusion criteria were complete information on age and sex and on disease codes (or measurements of estimated glomerular filtration rate and albuminuria for nephropathy) until 2013 to account for patient dropout. Exclusion criteria for predicting a complication were diagnosis of this specific complication before or in 2008. In total, 105 predictors from demographics, biomarkers, medications, and disease codes were used to build the ML models. We compared 2 ML models: logistic regression and gradient-boosted decision trees (GBDTs). To explain the predictions of the GBDTs, we calculated Shapley additive explanations values. RESULTS: Overall, 13,904 and 4259 individuals with prediabetes and diabetes, respectively, were identified in our underlying data set. For individuals with prediabetes, the areas under the receiver operating characteristic curve for logistic regression and GBDTs were, respectively, 0.657 and 0.681 (retinopathy), 0.807 and 0.815 (nephropathy), 0.727 and 0.706 (neuropathy), 0.730 and 0.727 (PVD), 0.687 and 0.693 (CeVD), and 0.707 and 0.705 (CVD); for individuals with diabetes, the areas under the receiver operating characteristic curve were, respectively, 0.673 and 0.726 (retinopathy), 0.763 and 0.775 (nephropathy), 0.745 and 0.771 (neuropathy), 0.698 and 0.715 (PVD), 0.651 and 0.646 (CeVD), and 0.686 and 0.680 (CVD). Overall, the prediction performance is comparable for logistic regression and GBDTs. The Shapley additive explanations values showed that increased levels of blood glucose, glycated hemoglobin, and serum creatinine are risk factors for microvascular complications. Age and hypertension were associated with an elevated risk for macrovascular complications. CONCLUSIONS: Our ML models allow for an identification of individuals with prediabetes or diabetes who are at increased risk of developing micro- or macrovascular complications. The prediction performance varied across complications and target populations but was in an acceptable range for most prediction tasks.

The methodologies to assess the effectiveness of non-pharmaceutical interventions during COVID-19: a systematic review.

Non-pharmaceutical interventions, such as school closures and stay-at-home orders, have been implemented around the world to control the spread of SARS-CoV-2. Their effectiveness in improving health-related outcomes has been the subject of numerous empirical studies. However, these studies show fairly large variation among methodologies in use, reflecting the absence of an established methodological framework. On the one hand, variation in methodologies may be desirable to assess the robustness of results; on the other hand, a lack of common standards can impede comparability among studies. To establish a comprehensive overview over the methodologies in use, we conducted a systematic review of studies assessing the effectiveness of non-pharmaceutical interventions between January 1, 2020 and January 12, 2021 (n = 248). We identified substantial variation in methodologies with respect to study setting, outcome, intervention, methodological approach, and effectiveness assessment. On this basis, we point to shortcomings of existing studies and make recommendations for the design of future studies.

Estimating the effect of mobility on SARS-CoV-2 transmission during the first and second wave of the COVID-19 epidemic, Switzerland, March to December 2020.

IntroductionHuman mobility was considerably reduced during the COVID-19 pandemic. To support disease surveillance, it is important to understand the effect of mobility on transmission.AimWe compared the role of mobility during the first and second COVID-19 wave in Switzerland by studying the link between daily travel distances and the effective reproduction number (Rt) of SARS-CoV-2.MethodsWe used aggregated mobile phone data from a representative panel survey of the Swiss population to measure human mobility. We estimated the effects of reductions in daily travel distance on Rt via a regression model. We compared mobility effects between the first (2 March-7 April 2020) and second wave (1 October-10 December 2020).ResultsDaily travel distances decreased by 73% in the first and by 44% in the second wave (relative to February 2020). For a 1% reduction in average daily travel distance, Rt was estimated to decline by 0.73% (95% credible interval (CrI): 0.34-1.03) in the first wave and by 1.04% (95% CrI: 0.66-1.42) in the second wave. The estimated mobility effects were similar in both waves for all modes of transport, travel purposes and sociodemographic subgroups but differed for movement radius.ConclusionMobility was associated with SARS-CoV-2 Rt during the first two epidemic waves in Switzerland. The relative effect of mobility was similar in both waves, but smaller mobility reductions in the second wave corresponded to smaller overall reductions in Rt. Mobility data from mobile phones have a continued potential to support real-time surveillance of COVID-19.

Effect of nutrition on postprandial glucose control in hospitalized patients with type 2 diabetes receiving fully automated closed-loop insulin therapy.

Fully automated closed-loop insulin delivery may offer a novel way to manage diabetes in hospital. However, postprandial glycaemic control remains challenging. We aimed to assess the effect of nutritional intake on postprandial glucose control in hospitalized patients with type 2 diabetes receiving fully closed-loop insulin therapy. The effects of different meal types and macronutrient composition on sensor glucose time-in-target (TIT, 3.9-10.0 mmol/L) and mean sensor glucose were assessed with hierarchical linear models using a Bayesian estimation approach. TIT was lower and the mean sensor glucose slightly higher, after breakfast compared with lunch and dinner, whereas the insulin dose was higher. Across meals, when carbohydrates were replaced by fat, or to a lesser extent by protein, postprandial glucose control improved. For breakfast, a 3.9% improvement in TIT was observed when 10% of the energy from carbohydrates was replaced by fat. Improvements were slightly lower during lunch and dinner (3.2% and 3.4%) or when carbohydrates were replaced by protein (2.2 and 2.7%, respectively). We suggest that reducing carbohydrate at the expense of fat or protein, could further improve glucose control during fully closed-loop insulin therapy in hospital.

The impact of postbariatric hypoglycaemia on driving performance: A randomized, single-blind, two-period, crossover study in a driving simulator.

Postbariatric hypoglycaemia (PBH) is an increasingly recognized complication of bariatric surgery, but its effect on daily functioning remains unclear. In this randomized, single-blind, crossover trial we assessed driving performance in patients with PBH. Ten active drivers with PBH (eight females, age 38.2 ± 14.7 years, body mass index 27.2 ± 4.6 kg/m2 ) received 75 g glucose to induce PBH in the late postprandial period and aspartame to leave glycaemia unchanged, on two different occasions. A simulator was driven during 10 minutes before (D0) and 20 (D1), 80 (D2), 125 (D3) and 140 minutes (D4) after the glucose/aspartame ingestion, reflecting the expected blood glucose (BG) increase (D1), decrease (D2) and hypoglycaemia (D3, D4). Seven driving features indicating impaired driving were integrated in a Bayesian hierarchical regression model to assess the difference in driving performance after glucose/aspartame ingestion. Mean ± standard deviation peak and nadir BG after glucose were 182 ± 24 and 47 ± 14 mg/dL, while BG was stable after aspartame (85 ± 4 mg/dL). Despite the lack of a difference in symptom perception, driving performance was significantly impaired after glucose versus aspartame during D4 (posterior probability 98.2%). Our findings suggest that PBH negatively affects driving performance.

Analyzing Patient Trajectories With Artificial Intelligence.

In digital medicine, patient data typically record health events over time (eg, through electronic health records, wearables, or other sensing technologies) and thus form unique patient trajectories. Patient trajectories are highly predictive of the future course of diseases and therefore facilitate effective care. However, digital medicine often uses only limited patient data, consisting of health events from only a single or small number of time points while ignoring additional information encoded in patient trajectories. To analyze such rich longitudinal data, new artificial intelligence (AI) solutions are needed. In this paper, we provide an overview of the recent efforts to develop trajectory-aware AI solutions and provide suggestions for future directions. Specifically, we examine the implications for developing disease models from patient trajectories along the typical workflow in AI: problem definition, data processing, modeling, evaluation, and interpretation. We conclude with a discussion of how such AI solutions will allow the field to build robust models for personalized risk scoring, subtyping, and disease pathway discovery.

Computer Mouse Movements as an Indicator of Work Stress: Longitudinal Observational Field Study.

BACKGROUND: Work stress affects individual health and well-being. These negative effects could be mitigated through regular monitoring of employees' stress. Such monitoring becomes even more important as the digital transformation of the economy implies profound changes in working conditions. OBJECTIVE: The goal of this study was to investigate the association between computer mouse movements and work stress in the field. METHODS: We hypothesized that stress is associated with a speed-accuracy trade-off in computer mouse movements. To test this hypothesis, we conducted a longitudinal field study at a large business organization, where computer mouse movements from regular work activities were monitored over 7 weeks; the study included 70 subjects and 1829 observations. A Bayesian regression model was used to estimate whether self-reported acute work stress was associated with a speed-accuracy trade-off in computer mouse movements. RESULTS: There was a negative association between stress and the two-way interaction term of mouse speed and accuracy (mean -0.32, 95% highest posterior density interval -0.58 to -0.08), which means that stress was associated with a speed-accuracy trade-off. The estimated association was not sensitive to different processing of the data and remained negative after controlling for the demographics, health, and personality traits of subjects. CONCLUSIONS: Self-reported acute stress is associated with computer mouse movements, specifically in the form of a speed-accuracy trade-off. This finding suggests that the regular analysis of computer mouse movements could indicate work stress.

Systematic discrepancies in the delivery of political ads on Facebook and Instagram.

Political advertising on social media has become a central element in election campaigns. However, granular information about political advertising on social media was previously unavailable, thus raising concerns regarding fairness, accountability, and transparency in the electoral process. In this article, we analyze targeted political advertising on social media via a unique, large-scale dataset of over 80,000 political ads from Meta during the 2021 German federal election, with more than 1.1 billion impressions. For each political ad, our dataset records granular information about targeting strategies, spending, and actual impressions. We then study (i) the prevalence of targeted ads across the political spectrum; (ii) the discrepancies between targeted and actual audiences due to algorithmic ad delivery; and (iii) which targeting strategies on social media attain a wide reach at low cost. We find that targeted ads are prevalent across the entire political spectrum. Moreover, there are considerable discrepancies between targeted and actual audiences, and systematic differences in the reach of political ads (in impressions-per-EUR) among parties, where the algorithm favor ads from populists over others.

Multimodal In-Vehicle Hypoglycemia Warning for Drivers With Type 1 Diabetes: Design and Evaluation in Simulated and Real-World Driving.

BACKGROUND: Hypoglycemia threatens cognitive function and driving safety. Previous research investigated in-vehicle voice assistants as hypoglycemia warnings. However, they could startle drivers. To address this, we combine voice warnings with ambient LEDs. OBJECTIVE: The study assesses the effect of in-vehicle multimodal warning on emotional reaction and technology acceptance among drivers with type 1 diabetes. METHODS: Two studies were conducted, one in simulated driving and the other in real-world driving. A quasi-experimental design included 2 independent variables (blood glucose phase and warning modality) and 1 main dependent variable (emotional reaction). Blood glucose was manipulated via intravenous catheters, and warning modality was manipulated by combining a tablet voice warning app and LEDs. Emotional reaction was measured physiologically via skin conductance response and subjectively with the Affective Slider and tested with a mixed-effect linear model. Secondary outcomes included self-reported technology acceptance. Participants were recruited from Bern University Hospital, Switzerland. RESULTS: The simulated and real-world driving studies involved 9 and 10 participants with type 1 diabetes, respectively. Both studies showed significant results in self-reported emotional reactions (P<.001). In simulated driving, neither warning modality nor blood glucose phase significantly affected self-reported arousal, but in real-world driving, both did (F2,68=4.3; P<.05 and F2,76=4.1; P=.03). Warning modality affected self-reported valence in simulated driving (F2,68=3.9; P<.05), while blood glucose phase affected it in real-world driving (F2,76=9.3; P<.001). Skin conductance response did not yield significant results neither in the simulated driving study (modality: F2,68=2.46; P=.09, blood glucose phase: F2,68=0.3; P=.74), nor in the real-world driving study (modality: F2,76=0.8; P=.47, blood glucose phase: F2,76=0.7; P=.5). In both simulated and real-world driving studies, the voice+LED warning modality was the most effective (simulated: mean 3.38, SD 1.06 and real-world: mean 3.5, SD 0.71) and urgent (simulated: mean 3.12, SD 0.64 and real-world: mean 3.6, SD 0.52). Annoyance varied across settings. The standard warning modality was the least effective (simulated: mean 2.25, SD 1.16 and real-world: mean 3.3, SD 1.06) and urgent (simulated: mean 1.88, SD 1.55 and real-world: mean 2.6, SD 1.26) and the most annoying (simulated: mean 2.25, SD 1.16 and real-world: mean 1.7, SD 0.95). In terms of preference, the voice warning modality outperformed the standard warning modality. In simulated driving, the voice+LED warning modality (mean rank 1.5, SD rank 0.82) was preferred over the voice (mean rank 2.2, SD rank 0.6) and standard (mean rank 2.4, SD rank 0.81) warning modalities, while in real-world driving, the voice+LED and voice warning modalities were equally preferred (mean rank 1.8, SD rank 0.79) to the standard warning modality (mean rank 2.4, SD rank 0.84). CONCLUSIONS: Despite the mixed results, this paper highlights the potential of implementing voice assistant-based health warnings in cars and advocates for multimodal alerts to enhance hypoglycemia management while driving. TRIAL REGISTRATION: ClinicalTrials.gov NCT05183191; https://classic.clinicaltrials.gov/ct2/show/NCT05183191, ClinicalTrials.gov NCT05308095; https://classic.clinicaltrials.gov/ct2/show/NCT05308095.

Causal machine learning for predicting treatment outcomes.

Causal machine learning (ML) offers flexible, data-driven methods for predicting treatment outcomes including efficacy and toxicity, thereby supporting the assessment and safety of drugs. A key benefit of causal ML is that it allows for estimating individualized treatment effects, so that clinical decision-making can be personalized to individual patient profiles. Causal ML can be used in combination with both clinical trial data and real-world data, such as clinical registries and electronic health records, but caution is needed to avoid biased or incorrect predictions. In this Perspective, we discuss the benefits of causal ML (relative to traditional statistical or ML approaches) and outline the key components and steps. Finally, we provide recommendations for the reliable use of causal ML and effective translation into the clinic.

Effectiveness and User Perception of an In-Vehicle Voice Warning for Hypoglycemia: Development and Feasibility Trial.

BACKGROUND: Hypoglycemia is a frequent and acute complication in type 1 diabetes mellitus (T1DM) and is associated with a higher risk of car mishaps. Currently, hypoglycemia can be detected and signaled through flash glucose monitoring or continuous glucose monitoring devices, which require manual and visual interaction, thereby removing the focus of attention from the driving task. Hypoglycemia causes a decrease in attention, thereby challenging the safety of using such devices behind the wheel. Here, we present an investigation of a hands-free technology-a voice warning that can potentially be delivered via an in-vehicle voice assistant. OBJECTIVE: This study aims to investigate the feasibility of an in-vehicle voice warning for hypoglycemia, evaluating both its effectiveness and user perception. METHODS: We designed a voice warning and evaluated it in 3 studies. In all studies, participants received a voice warning while driving. Study 0 (n=10) assessed the feasibility of using a voice warning with healthy participants driving in a simulator. Study 1 (n=18) assessed the voice warning in participants with T1DM. Study 2 (n=20) assessed the voice warning in participants with T1DM undergoing hypoglycemia while driving in a real car. We measured participants' self-reported perception of the voice warning (with a user experience scale in study 0 and with acceptance, alliance, and trust scales in studies 1 and 2) and compliance behavior (whether they stopped the car and reaction time). In addition, we assessed technology affinity and collected the participants' verbal feedback. RESULTS: Technology affinity was similar across studies and approximately 70% of the maximal value. Perception measure of the voice warning was approximately 62% to 78% in the simulated driving and 34% to 56% in real-world driving. Perception correlated with technology affinity on specific constructs (eg, Affinity for Technology Interaction score and intention to use, optimism and performance expectancy, behavioral intention, Session Alliance Inventory score, innovativeness and hedonic motivation, and negative correlations between discomfort and behavioral intention and discomfort and competence trust; all P<.05). Compliance was 100% in all studies, whereas reaction time was higher in study 1 (mean 23, SD 5.2 seconds) than in study 0 (mean 12.6, SD 5.7 seconds) and study 2 (mean 14.6, SD 4.3 seconds). Finally, verbal feedback showed that the participants preferred the voice warning to be less verbose and interactive. CONCLUSIONS: This is the first study to investigate the feasibility of an in-vehicle voice warning for hypoglycemia. Drivers find such an implementation useful and effective in a simulated environment, but improvements are needed in the real-world driving context. This study is a kickoff for the use of in-vehicle voice assistants for digital health interventions.

Message framing to promote solar panels.

Green technologies, such as solar panels, foster the use of clean energy, yet often involve large-scale investments. Hence, adoption by retail consumers has been a key barrier. Here, we show that message framing can significantly increase customers' serious commitment to adopting solar panels by providing empirical evidence in the field from a large-scale randomized controlled trial with a nationwide online retailer in the Netherlands (N = 26,873 participants). We design four messages aimed at promoting the purchase behavior of solar panel installations. Our messages present outcomes for oneself or for the environment and highlight cost savings versus earnings (for oneself) or reducing emissions versus generating green electricity (for the environment). Across all messages, we observe a higher rate of customers committing to solar panels compared to the baseline. However, the framing in terms of financial savings for oneself was by far the most effective, resulting in a 40% higher level of commitment than the baseline and 30% higher than the average of the other three messages, which were not significantly different in effect from each other. Our results show that message framing is cost-efficient and scalable among retail consumers to promote large-scale investments in green technologies and thus clean energy.

Negativity drives online news consumption.

Online media is important for society in informing and shaping opinions, hence raising the question of what drives online news consumption. Here we analyse the causal effect of negative and emotional words on news consumption using a large online dataset of viral news stories. Specifically, we conducted our analyses using a series of randomized controlled trials (N = 22,743). Our dataset comprises ~105,000 different variations of news stories from Upworthy.com that generated ∼5.7 million clicks across more than 370 million overall impressions. Although positive words were slightly more prevalent than negative words, we found that negative words in news headlines increased consumption rates (and positive words decreased consumption rates). For a headline of average length, each additional negative word increased the click-through rate by 2.3%. Our results contribute to a better understanding of why users engage with online media.

Estimating and explaining cross-country variation in the effectiveness of non-pharmaceutical interventions during COVID-19.

To control the COVID-19 pandemic, countries around the world have implemented non-pharmaceutical interventions (NPIs), such as school closures or stay-at-home orders. Previous work has estimated the effectiveness of NPIs, yet without examining variation in NPI effectiveness across countries. Based on data from the first epidemic wave of [Formula: see text] countries, we estimate country-specific differences in the effectiveness of NPIs via a semi-mechanistic Bayesian hierarchical model. Our estimates reveal substantial variation between countries, indicating that NPIs have been more effective in some countries (e. g. Switzerland, New Zealand, and Iceland) as compared to others (e. g. Singapore, South Africa, and France). We then explain differences in the effectiveness of NPIs through 12 country characteristics (e. g. population age, urbanization, employment, etc.). A positive association with country-specific effectiveness of NPIs was found for government effectiveness, gross domestic product (GDP) per capita, population ages 65+, and health expenditures. Conversely, a negative association with effectiveness of NPIs was found for the share of informal employment, average household size and population density. Overall, the wealth and demographic structure of a country can explain variation in the effectiveness of NPIs.

Machine Learning for Predicting the Risk of Transition from Prediabetes to Diabetes.

Traditional risk scores for the prediction of type 2 diabetes (T2D) are typically designed for a general population and, thus, may underperform for people with prediabetes. In this study, we developed machine learning (ML) models predicting the risk of T2D that are specifically tailored to people with prediabetes. We analyzed data of 13,943 individuals with prediabetes, and built a ML model to predict the risk of transition from prediabetes to T2D, integrating information about demographics, biomarkers, medications, and comorbidities defined by disease codes. Additionally, we developed a simplified ML model with only eight predictors, which can be easily integrated into clinical practice. For a forecast horizon of 5 years, the area under the receiver operating characteristic curve was 0.753 for our full ML model (79 predictors) and 0.752 for the simplified model. Our ML models allow for an early identification of people with prediabetes who are at risk of developing T2D.