Targeting with machine learning: An application to a tax rebate program in Italy

Andini, Monica; Ciani, Emanuele; Blasio, Guido de; D’Ignazio, Alessio; Salvestrini, Viola

doi:10.1016/j.jebo.2018.09.010

Cited by 72 publications

(28 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…UTI is one of the most common types of infections requiring antibiotic treatment and can be diagnosed with relative ease by microbiological analysis of urine samples. 2 However, laboratory testing has the important and general limitation 1 Antibiotics are used to treat bacterial infections by killing or inhibiting growth of bacteria in the body. Their effectiveness is decreasing due to antibiotic resistance threatening to render simple infections, such as pneumonia or infections in wounds, a fatal risk.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Battling Antibiotic Resistance: Can Machine Learning Improve Prescribing?

Ribers

Ullrich

2019

SSRN Journal

View full text Add to dashboard Cite

Antibiotic resistance constitutes a major health threat. Predicting bacterial causes of infections is key to reducing antibiotic misuse, a leading driver of antibiotic resistance. We train a machine learning algorithm on administrative and microbiological laboratory data from Denmark to predict diagnostic test outcomes for urinary tract infections. Based on predictions, we develop policies to improve prescribing in primary care, highlighting the relevance of physician expertise and policy implementation when patient distributions vary over time. The proposed policies delay antibiotic prescriptions for some patients until test results are known and give them instantly to others. We find that machine learning can reduce antibiotic use by 7.42 percent without reducing the number of treated bacterial infections. As Denmark is one of the most conservative countries in terms of antibiotic use, this result is likely to be a lower bound of what can be achieved elsewhere.that results arrive with a delay of several days, corresponding to nearly a complete course of antibiotic treatment. Machine learning predictions promise a so far unavailable instantaneous bacterial risk assessment. We train a machine learning algorithm, a random forest, on high-dimensional, administrative data from Denmark in 2010-2012 to predict the risk of bacterial presence in laboratory test results from patient samples in primary care, the main source of antibiotic prescribing. 3 The outcome variable, an indicator variable taking the value of one when bacteria are isolated in a patient sample, is based on the microbiological test result physicians receive several days after sending in a sample. The covariates in the prediction model include each individual patient's medical outpatient claims histories, past antibiotic prescriptions, past microbiological test results, a rich set of personal characteristics such as gender, age, detailed employment status and type, education, income, civil status and more, as well as the same information on each individuals' household members. We find that machine learning applied to these data is highly capable of predicting realizations of bacterial UTI in out of sample patient test results.The relevant criterion on which our predictions need to be evaluated, however, is whether or not they can be used to improve human expert decision making. For this purpose, we model prescription decisions as a trade-off between the social cost of prescribing, i.e. promoting resistance, and the health benefits of antibiotic treatment. We build on Kleinberg et al. (2018), who use machine learning predicted risk of defendants committing a crime to show the potential improvements of judges' bail decisions. The model allows us to evaluate reassignment of antibiotic treatment based on the algorithm's prediction of risk, that is, delaying prescriptions for low risk patients until test results are available and instantly giving prescriptions to high risk patients. This reassignment is similar in spirit to Currie and MacLeod (2017) who eva...

show abstract

Section: Introductionmentioning

confidence: 99%

“…The World Health Organization considers antibiotic resistance one of the greatest threats to global health given its immense costs in terms of life and treatment expenses (WHO 2012(WHO , 2014. 2 Foxman (2002) According to Bjerrum and Lindaek (2015), each year 10 percent of women receive antibiotic treatment for UTI.…”

Section: Introductionmentioning

confidence: 99%

Battling Antibiotic Resistance: Can Machine Learning Improve Prescribing?

Ribers

Ullrich

2019

SSRN Journal

View full text Add to dashboard Cite

show abstract

“…Although our dataset is a panel of Italian municipalities, in our benchmark models, we consider the data as pooled, following Andini et al ( 2018 ). In fact, we treat each municipality–year pair as if it was a single observation.…”

Section: Methodsmentioning

confidence: 99%

Local mortality estimates during the COVID-19 pandemic in Italy

et al. 2021

View full text Add to dashboard Cite

Estimates of the real death toll of the COVID-19 pandemic have proven to be problematic in many countries, Italy being no exception. Mortality estimates at the local level are even more uncertain as they require stringent conditions, such as granularity and accuracy of the data at hand, which are rarely met. The “official” approach adopted by public institutions to estimate the “excess mortality” during the pandemic draws on a comparison between observed all-cause mortality data for 2020 and averages of mortality figures in the past years for the same period. In this paper, we apply the recently developed machine learning control method to build a more realistic counterfactual scenario of mortality in the absence of COVID-19. We demonstrate that supervised machine learning techniques outperform the official method by substantially improving the prediction accuracy of the local mortality in “ordinary” years, especially in small- and medium-sized municipalities. We then apply the best-performing algorithms to derive estimates of local excess mortality for the period between February and September 2020. Such estimates allow us to provide insights about the demographic evolution of the first wave of the pandemic throughout the country. To help improve diagnostic and monitoring efforts, our dataset is freely available to the research community.

show abstract

“…2 Specifically, we study antibiotic treatment decisions for urinary tract infections (UTI) in primary care, combining rich, administrative data on individual patients with diagnostic outcomes from gold standard microbiological laboratory test results in Denmark. 3 These test outcomes are observed by physicians but with a delay of several days, often corresponding to a complete course of antibiotic treatment. Due to the acute nature of 1 For example, in health settings such as the diagnosis of heart attacks considered in Mullainathan and Obermeyer (2019), a patient is defined as recovered when no subsequent return to the hospital is observed.…”

mentioning

confidence: 99%

“…In the US alone, antibiotic-resistant infections result in an estimated 23,000 deaths, $20 billion in direct healthcare costs, and $35 billion in lost productivity each year (CDC 2013). 3 UTI are one of the most common classes of bacterial infections. Foxman (2002) reports almost half of all women contract a UTI once in their lifetime.…”

mentioning

confidence: 99%

Machine Predictions and Human Decisions with Variation in Payoffs and Skills

Ribers

Ullrich

2020

SSRN Journal

View full text Add to dashboard Cite

Human decision-making differs due to variation in both incentives and available information. This generates substantial challenges for the evaluation of whether and how machine learning predictions can improve decision outcomes. We propose a framework that incorporates machine learning on large-scale administrative data into a choice model featuring heterogeneity in decision maker payoff functions and predictive skill. We apply our framework to the major health policy problem of improving the efficiency in antibiotic prescribing in primary care, one of the leading causes of antibiotic resistance. Our analysis reveals large variation in physicians' skill to diagnose bacterial infections and in how physicians trade off the externality inherent in antibiotic use against its curative benefit. Counterfactual policy simulations show the combination of machine learning predictions with physician diagnostic skill achieves a 25.4 percent reduction in prescribing.

show abstract

Targeting with machine learning: An application to a tax rebate program in Italy

Cited by 72 publications

References 11 publications

Battling Antibiotic Resistance: Can Machine Learning Improve Prescribing?

Battling Antibiotic Resistance: Can Machine Learning Improve Prescribing?

Local mortality estimates during the COVID-19 pandemic in Italy

Machine Predictions and Human Decisions with Variation in Payoffs and Skills

Contact Info

Product

Resources

About