Consisting of five separate booklets, the World Drug Report 2022 provides an in-depth analysis of global drug markets and examines the nexus between drugs and the environment within the bigger picture of the Sustainable Development Goals, climate change and environmental sustainability.

The World Drug Report 2022 is aimed not only at fostering greater international cooperation to counter the impact of the world drug problem on health, governance and security, but also, with its special insights, at assisting Member States in anticipating and address-ing threats from drug markets and mitigating their consequences.

NODC grants access to survey microdata for statistical and scientific research purposes only. Survey microdata are made available for dissemination after all the necessary steps are taken to ensure anonymity and confidentiality of individuals, households, and business entities. For data related to geographical entities, such as agriculture fields, particular care is taken to ensure anonymity of geographical locations and affected units. More information on the UNODC principles for microdata sharing can be found herePDF.

To apply for access, the Data User has to:

Be employed or affiliated to a research entity such as a university, research institution or a research department in an international organization, public administration, statistical office, bank, NGO, etc. Submit the ‘Request for access to microdataPDF’, including a brief research proposal. PhD Students should submit an application form signed by the supervisor as well. Adhere to the UNODC Terms and Conditions PDFon the access to microdata

UNODC grants access to survey microdata for statistical and scientific research purposes only. Survey microdata are made available for dissemination after all the necessary steps are taken to ensure anonymity and confidentiality of individuals, households, and business entities. For data related to geographical entities, such as agriculture fields, particular care is taken to ensure anonymity of geographical locations and affected units. More information on the UNODC principles for microdata sharing can be found herePDF.

To apply for access, the Data User has to:

Be employed or affiliated to a research entity such as a university, research institution or a research department in an international organization, public administration, statistical office, bank, NGO, etc. Submit the ‘Request for access to microdataPDF’, including a brief research proposal. PhD Students should submit an application form signed by the supervisor as well. Adhere to the UNODC Terms and Conditions PDFon the access to microdata ‘Request for microdata’ and the ‘UNODC Terms and Conditions’ are to be sent to

Real World Evidence Solutions Market size was valued at USD 1.30 Billion in 2024 and is projected to reach USD 3.71 Billion by 2032, growing at a CAGR of 13.92% during the forecast period 2026-2032.Global Real World Evidence Solutions Market DriversThe market drivers for the Real World Evidence Solutions Market can be influenced by various factors. These may include:Growing Need for Evidence-Based Healthcare: Real-world evidence (RWE) is becoming more and more important in healthcare decision-making, according to stakeholders such as payers, providers, and regulators. In addition to traditional clinical trial data, RWE solutions offer important insights into the efficacy, safety, and value of healthcare interventions in real-world situations.Growing Use of RWE by Pharmaceutical Companies: RWE solutions are being used by pharmaceutical companies to assist with market entry, post-marketing surveillance, and drug development initiatives. Pharmaceutical businesses can find new indications for their current medications, improve clinical trial designs, and convince payers and providers of the worth of their products with the use of RWE.Increasing Priority for Value-Based Healthcare: The emphasis on proving the cost- and benefit-effectiveness of healthcare interventions in real-world settings is growing as value-based healthcare models gain traction. To assist value-based decision-making, RWE solutions are essential in evaluating the economic effect and real-world consequences of healthcare interventions.Technological and Data Analytics Advancements: RWE solutions are becoming more capable due to advances in machine learning, artificial intelligence, and big data analytics. With the use of these technologies, healthcare stakeholders can obtain actionable insights from the analysis of vast and varied datasets, including patient-generated data, claims data, and electronic health records.Regulatory Support for RWE Integration: RWE is being progressively integrated into regulatory decision-making processes by regulatory organisations including the European Medicines Agency (EMA) and the U.S. Food and Drug Administration (FDA). The FDA's Real-World Evidence Programme and the EMA's Adaptive Pathways and PRIority MEdicines (PRIME) programme are two examples of initiatives that are making it easier to incorporate RWE into regulatory submissions and drug development.Increasing Emphasis on Patient-Centric Healthcare: The value of patient-reported outcomes and real-world experiences in healthcare decision-making is becoming more widely acknowledged. RWE technologies facilitate the collection and examination of patient-centered data, offering valuable insights into treatment efficacy, patient inclinations, and quality of life consequences.Extension of RWE Use Cases: RWE solutions are being used in medication development, post-market surveillance, health economics and outcomes research (HEOR), comparative effectiveness research, and market access, among other healthcare fields. The necessity for a variety of RWE solutions catered to the needs of different stakeholders is being driven by the expansion of RWE use cases.

Pharmaceutical prescribing and drug-drug interaction data underlie recommendations on drug combinations that should be avoided or closely monitored by prescribers. Because the number of patients taking multiple medications is increasing, a comprehensive view of prescribing patterns in patients is important to better assess real world pharmaceutical response and evaluate the potential for multi-drug interactions. We obtained self-reported prescription data from NHANES surveys between 1999 and 2010, and confirm the previously reported finding of increasing drug use in the elderly. We studied co-prescription drug trends by focusing on the 2009-2010 survey, which contains prescription data on 690 drugs used by 10,537 subjects. We found that medication profiles were unique for individuals aged 65 years or more, with ≥98 unique drug regimens encountered per 100 subjects taking 3 or more medications. When drugs were viewed by therapeutic class, it was found that the most commonly prescribed drugs were not the most commonly co-prescribed drugs for any of the 16 drug classes investigated. We cross-referenced these medication lists with drug interaction data from Drugs.com to evaluate the potential for drug interactions. The number of drug alerts rose proportionally with the number of co-prescribed medications, rising from 3.3 alerts for individuals prescribed 5 medications to 11.7 alerts for individuals prescribed 10 medications. We found 22% of elderly subjects taking both a substrate and inhibitor of a given cytochrome P450 enzyme, and 4% taking multiple inhibitors of the same enzyme simultaneously. By examining drug pairs prescribed in 0.1% of the population or more, we found low agreement between co-prescription rate and co-discussion in the literature. These data show that prescribing trends in treatment could drive a large extent of individual variability in drug response, and that current pairwise approaches to assessing drug-drug interactions may be inadequate for predicting real world outcomes.

Numerous studies on medicines are conducted day by day. To address shortcomings of medicines information generation, prediction, and classification models, the authors introduce a large medicines information dataset of textual data. For this motivation, the authors named our dataset ‘MID’.

• Value of the data - MID is the largest, to our knowledge, available and representative Medicines Information Dataset (MID) for a wide variety of drugs. It includes the names of over 192k medicines, making it a comprehensive collection of pharmaceutical products. - MID is the largest, making it robust for generating information about drugs such as indications or interactions. - MID offers over 192k rows distributed in 44 variety therapeutic classes, making it robust for drug classification to therapeutic label. - MID provides accurate, authoritative, and trustworthy information on medicines for enhancing predictions and efficiencies in clinical trial management. - MID includes details such as drug names, information URL, salt composition, drug introduction, therapeutic uses, side effects, drug benefits, how to use of drug, how to use of drug, how drug works, quick tips of drug, safety advice of drug, chemical class of drug, habit forming of drug, therapeutic class of drug, and action class of drug. This dataset aims to provide a useful resource for medical researchers, healthcare professionals, drug manufacturers, data scientists, and enthusiasts interested in exploring the world of medicines and healthcare products. - In contrast with the few small available datasets, MID's size makes it a suitable corpus for implementing both classical as well as deep learning models.

• MID.xlsx provides the raw data, including medicine information. The data collected to ensure an acceleration and save experimental efforts for medicines through help in predicting or generating or classifying of medicine information preclinically.

• Therapeutic_class_counts.xlsx is summarize distribution of medicines per therapeutic class.

This dataset was used for the Winter 2018 Kaggle University Club Hackathon and is now publicly available. See Acknowledgments section for citation and licensing. Note: The types of data and recommendation based solutions provided by the contestants are purely for NLP learning purposes. They are not suitable for a real world drug recommendations solutions.

Welcome to the Kaggle University Club Hackathon!

If you are interested in joining Kaggle University Club, please e-mail Jessica Li at lijessica@google.com

This Hackathon is open to all undergraduate, master, and PhD students who are part of the Kaggle University Club program. The Hackathon provides students with a chance to build capacity via hands-on ML, learn from one another, and engage in a self-defined project that is meaningful to their careers.

Teams must register via Google Form to be eligible for the Hackathon. The Hackathon starts on Monday, November 12, 2018 and ends on Monday, December 10, 2018. Teams have one month to work on a team submission. Teams must do all work within the Kernel editor and set Kernel(s) to public at all times.

Prompt

The freestyle format of hackathons has time and again stimulated groundbreaking and innovative data insights and technologies. The Kaggle University Club Hackathon recreates this environment virtually on our platform. We challenge you to build a meaningful project around the UCI Machine Learning - Drug Review Dataset. Teams are free to let their creativity run and propose methods to analyze this dataset and form interesting machine learning models.

Machine learning has permeated nearly all fields and disciplines of study. One hot topic is using natural language processing and sentiment analysis to identify, extract, and make use of subjective information. The UCI ML Drug Review dataset provides patient reviews on specific drugs along with related conditions and a 10-star patient rating system reflecting overall patient satisfaction. The data was obtained by crawling online pharmaceutical review sites. This data was published in a study on sentiment analysis of drug experience over multiple facets, ex. sentiments learned on specific aspects such as effectiveness and side effects (see the acknowledgments section to learn more).

The sky's the limit here in terms of what your team can do! Teams are free to add supplementary datasets in conjunction with the drug review dataset in their Kernel. Discussion is highly encouraged within the forum and Slack so everyone can learn from their peers.

Here are just a couple ideas as to what you could do with the data:

• Classification: Can you predict the patient's condition based on the review?
• Regression: Can you predict the rating of the drug based on the review?
• Sentiment analysis: What elements of a review make it more helpful to others? Which patients tend to have more negative reviews? Can you determine if a review is positive, neutral, or negative?
• Data visualizations: What kind of drugs are there? What sorts of conditions do these patients have?

Top Submissions

There is no one correct answer to this Hackathon, and teams are free to define the direction of their own project. That being said, there are certain core elements generally found across all outstanding Kernels on the Kaggle platform. The best Kernels are:

1. Complex: How many domains of analysis and topics does this Kernel cover? Does it attempt machine learning methods? Does the Kernel offer a variety of unique analyses and interesting conclusions or solutions?
2. Original: What is the subject matter of this Kernel? Does it have a well-defined and interesting project scope, narrative or problem? Could the results make an impact? Is it thought provoking?
3. Approachable: How easy is it to understand this Kernel? Are all thought processes clear? Is the code clean, with useful comments? Are visualizations and processes articulated and self-explanatory?

Teams with top submissions have a chance to receive exclusive Kaggle University Club swag and be featured on our official blog and across social media.

IMPORTANT: Teams must set all Kernels to public at all times. This is so we can track each team's progression, but more importantly it encourages collaboration, productive discussion, and healthy inspiration to all teams. It is not so that teams can simply copycat good ideas. If a team's Kernel isn't their own organic work, it will not be considered a top submission. Teams must come up with a project on their own.

Submission Styling

The final Kernel submission for the Hackathon must contain the following information:

• All team members added as collaborators to the Kernel
• Somewhere at the top of your Kernel, find a space to put down all team member names, university name, club name, and team name (as specified whe...

This report contains results from an annual survey of secondary school pupils in England in years 7 to 11 (mostly aged 11 to 15). 12,051 pupils in 177 schools completed questionnaires in the autumn term of 2016. This is the most recent survey in a series that began in 1982. Each survey since 1998 has included a core set of questions on smoking, drinking and drug use. In 2000, the survey questions changed to focus on smoking and drinking or on drug use in alternate years and in 2016, the survey reverted back to including both drinking/smoking and drugs focused questions in one survey. The survey report presents information on the percentage of pupils who have ever smoked, tried alcohol or taken drugs and their attitudes towards these behaviours. It also includes breakdowns by age, gender, ethnicity and region. Other areas covered include the use of new psychoactive substances (also known as legal highs), beliefs about drinking, whether pupils had ever got drunk and consequences of drinking. Questions on the use of nitrous oxide have also been asked for the first time. The attachments below include a summary report showing key findings in slides format, excel tables with more detailed findings, technical appendices and a data quality statement. An anonymised record level file of the underlying data on which users can carry out their own analysis will be made available via the UK Data Service in 2018. UPDATE 03/05/2018 Since the original publication of this report, NHS Digital discovered an error in tables 4.4 and 4.5. This relates to the proportion of pupils who reported having been ‘exposed to second hand smoke in a home or in a car in the last year’. There was an error in the calculation of the previously published figures in this row for both tables. Other rows were not affected. The impact of the correction has been to increase the percentage for all pupils from 48% to 62%. This figure has also been corrected on page 23 of the main report. NHS Digital apologises for any inconvenience caused. UPDATE 11/12/2018 NHS Digital discovered errors that affected tables 6.21 and 6.22 (number of occasions drunk in last 4 weeks), and 9.1 to 9.8, 9.17, 9.19 and 9.20 (various drug use prevalence figures). These tables have now been corrected. The impact on the prevalence estimates for the tables affected was: Tables 6.21 and 6.22: Maximum change was 0.05 percentage points. Tables 9.1 to 9.3: Maximum change was 0.7 percentage points Tables 9.4 and 9.5: Maximum change for “ever taking drugs excluding volatile substances” is 5.9 percentage points. “Taken drugs in the last year excluding volatile substances” and “taken drugs in the last month excluding volatile substances” were also affected but not by more than 1.5 percentage points. Table 9.6: Maximum change for “any drug (excluding psychoactive substances)”, “any drug (excluding volatile substances)” and “any class A drug” is 0.8 percentage points. Table 9.7: The same estimates as in table 9.6 are affected but this time the maximum change is 1.5 percentage points. Table 9.8: The same estimates as in tables 9.6 and 9.7 are affected but this time the maximum change is 4.3 percentage points. Table 9.17: Maximum change was 0.02 percentage points. Table 9.19: The only change was 3 percentage points for “any drug (excluding psychoactive substances)”. Table 9.20: The only changes were for “any drug (excluding psychoactive substances)” and the maximum change was 3.3 percentage points. One figure on page 58 of the pdf report (taken drugs in the last month excluding psychoactive substances) was also corrected from 8% to 9%. NHS Digital apologises for any inconvenience caused.

Background: Reference to so-called real-world data is more often made in marketing authorization applications for medicines intended to diagnose, prevent or treat rare diseases compared to more common diseases. We provide granularity on the type and aim of any external data on efficacy aspects from both real-world data sources and external trial data as discussed in regulatory submissions of orphan designated medicinal products in the EU. By quantifying the contribution of external data according to various regulatory characteristics, we aimed at identifying specific opportunities for external data in the field of orphan conditions.Methods: Information on external data in regulatory documents covering 72 orphan designations was extracted. Our sample comprised public assessment reports for approved, refused, or withdrawn applications concluded from 2019–2021 at the European Medicines Agency. Products with an active orphan designation at the time of submission were scrutinized regarding the role of external data on efficacy aspects in the context of marketing authorization applications, or on the criterion of “significant benefit” for the confirmation of the orphan designation at the time of licensing. The reports allowed a broad distinction between clinical development, regulatory decision making, and intended post-approval data collection. We defined three categories of external data, administrative data, structured clinical data, and external trial data (from clinical trials not sponsored by the applicant), and noted whether external data concerned the therapeutic context of the disease or the product under review.Results: While reference to external data with respect to efficacy aspects was included in 63% of the approved medicinal products in the field of rare diseases, 37% of marketing authorization applications were exclusively based on the dedicated clinical development plan for the product under review. Purely administrative data did not play any role in our sample of reports, but clinical data collected in a structured manner (from routine care or clinical research) were often used to inform on the trial design. Two additional recurrent themes for the use of external data were the contextualization of results, especially to confirm the orphan designation at the time of licensing, and reassurance of a large difference in treatment effect size or consistency of effects observed in clinical trials and practice. External data on the product under review were restricted to either active substances already belonging to the standard of care even before authorization or to compassionate use schemes. Furthermore, external data were considered pivotal for marketing authorization only exceptionally and only for active substances already in use within the specific therapeutic indication. Applications for the rarest conditions and those without authorized treatment alternatives were especially prominent with respect to the use of external data from real-world data sources both in the pre- and post-approval setting.Conclusion: Specific opportunities for external data in the setting of marketing authorizations in the field of rare diseases were identified. Ongoing initiatives of fostering systematic data collection are promising steps for a more efficient medicinal product development in the field of rare diseases.

Background: Alzheimer’s disease (AD) is a debilitating neurodegenerative condition with few treatment options available. Drug repurposing studies have sought to identify existing drugs that could be repositioned to treat AD; however, the effectiveness of drug repurposing for AD remains unclear. This review systematically analyzes the progress made in drug repurposing for AD throughout the last decade, summarizing the suggested drug candidates and analyzing changes in the repurposing strategies used over time. We also examine the different types of data that have been leveraged to validate suggested drug repurposing candidates for AD, which to our knowledge has not been previous investigated, although this information may be especially useful in appraising the potential of suggested drug repurposing candidates. We ultimately hope to gain insight into the suggested drugs representing the most promising repurposing candidates for AD.Methods: We queried the PubMed database for AD drug repurposing studies published between 2012 and 2022. 124 articles were reviewed. We used RxNorm to standardize drug names across the reviewed studies, map drugs to their constituent ingredients, and identify prescribable drugs. We used the Anatomical Therapeutic Chemical (ATC) Classification System to group drugs.Results: 573 unique drugs were proposed for repurposing in AD over the last 10 years. These suggested repurposing candidates included drugs acting on the nervous system (17%), antineoplastic and immunomodulating agents (16%), and drugs acting on the cardiovascular system (12%). Clozapine, a second-generation antipsychotic medication, was the most frequently suggested repurposing candidate (N = 6). 61% (76/124) of the reviewed studies performed a validation, yet only 4% (5/124) used real-world data for validation.Conclusion: A large number of potential drug repurposing candidates for AD has accumulated over the last decade. However, among these drugs, no single drug has emerged as the top candidate, making it difficult to establish research priorities. Validation of drug repurposing hypotheses is inconsistently performed, and real-world data has been critically underutilized for validation. Given the urgent need for new AD therapies, the utility of real-world data in accelerating identification of high-priority candidates for AD repurposing warrants further investigation.

Public health-related decision-making on policies aimed at controlling the COVID-19 pandemic outbreak depends on complex epidemiological models that are compelled to be robust and use all relevant available data. This data article provides a new combined worldwide COVID-19 dataset obtained from official data sources with improved systematic measurement errors and a dedicated dashboard for online data visualization and summary. The dataset adds new measures and attributes to the normal attributes of official data sources, such as daily mortality, and fatality rates. We used comparative statistical analysis to evaluate the measurement errors of COVID-19 official data collections from the Chinese Center for Disease Control and Prevention (Chinese CDC), World Health Organization (WHO) and European Centre for Disease Prevention and Control (ECDC). The data is collected by using text mining techniques and reviewing pdf reports, metadata, and reference data. The combined dataset includes complete spatial data such as countries area, international number of countries, Alpha-2 code, Alpha-3 code, latitude, longitude, and some additional attributes such as population. The improved dataset benefits from major corrections on the referenced data sets and official reports such as adjustments in the reporting dates, which suffered from a one to two days lag, removing negative values, detecting unreasonable changes in historical data in new reports and corrections on systematic measurement errors, which have been increasing as the pandemic outbreak spreads and more countries contribute data for the official repositories. Additionally, the root mean square error of attributes in the paired comparison of datasets was used to identify the main data problems. The data for China is presented separately and in more detail, and it has been extracted from the attached reports available on the main page of the CCDC website. This dataset is a comprehensive and reliable source of worldwide COVID-19 data that can be used in epidemiological models assessing the magnitude and timeline for confirmed cases, long-term predictions of deaths or hospital utilization, the effects of quarantine, stay-at-home orders and other social distancing measures, the pandemic’s turning point or in economic and social impact analysis, helping to inform national and local authorities on how to implement an adaptive response approach to re-opening the economy, re-open schools, alleviate business and social distancing restrictions, design economic programs or allow sports events to resume.

Introduction: Drug-induced QT prolongation and (or) Torsade de Pointes (TdP) is a well-known serious adverse reaction (ADR) for some drugs, but the widely recognized comprehensive landscape of culprit-drug of QT prolongation and TdP is currently lacking.Aim: To identify the top drugs reported in association with QT prolongation and TdP and provide information for clinical practice.Method: We reviewed the reports related to QT prolongation and TdP in the FDA Adverse Event Reporting System (FAERS) database from January 1, 2004 to December 31, 2022, and summarized a potential causative drug list accordingly. Based on this drug list, the most frequently reported causative drugs and drug classes of QT prolongation and TdP were counted, and the disproportionality analysis for all the drugs was conducted to in detect ADR signal. Furthermore, according to the positive–negative distribution of ADR signal, we integrated the risk characteristic of QT prolongation and TdP in different drugs and drug class.Results: A total of 42,713 reports in FAERS database were considered to be associated with QT prolongation and TdP from 2004 to 2022, in which 1,088 drugs were reported as potential culprit-drugs, and the largest number of drugs belonged to antineoplastics. On the whole, furosemide was the most frequently reported drugs followed by acetylsalicylic acid, quetiapine, citalopram, metoprolol. In terms of drug classes, psycholeptics was the most frequently reported drug classes followed by psychoanaleptics, analgesics, beta blocking agents, drugs for acid related disorders. In disproportionality analysis, 612 drugs showed at least one positive ADR signals, while citalopram, ondansetron, escitalopram, loperamide, and promethazine were the drug with the maximum number of positive ADR signals. However, the positive-negative distribution of ADR signals between different drug classes showed great differences, representing the overall risk difference of different drug classes.Conclusion: Our study provided a real-world overview of QT prolongation and TdP to drugs, and the presentation of the potential culprit-drug list, the proportion of reports, the detection results of ADR signals, and the distribution characteristics of ADR signals may help understand the safety profile of drugs and optimize clinical practice.

BackgroundSeveral anti-cancer drugs have been linked to new onset atrial fibrillation (AF) but the true association of these drugs with AF is unknown. The FDA Adverse Event Reporting System (FAERS), a publicly available pharmacovigilance mechanism provided by the FDA, collects adverse event reports from the United States and other countries, thus providing real-world data.ObjectivesTo identify anti-cancer drugs associated with AF using the FAERS database.MethodsThe FAERS database was searched for all drugs reporting AF as an adverse event (AE). The top 30 anti-cancer drugs reporting AF cases were shortlisted and analyzed. Proportional reporting ratio (PRR) was used to measure disproportionality in reporting of adverse events for these drugs.ResultsWhen analyzed for AF as a percentage of all reported AE for a particular drug, Ibrutinib had the highest percentage (5.3%) followed distantly by venetoclax (1.6%), bortezomib (1.6%), carfilzomib (1.5%), and nilotinib (1.4%). The percentage of cardiac AE attributable to AF was also highest for ibrutinib (41.5%), followed by venetoclax (28.4%), pomalidomide (23.9%), bortezomib (18.2%), and lenalidomide (18.2%). Drugs with the highest PRR for AF included ibrutinib (5.96, 95% CI= 5.70–6.23), bortezomib (1.65, 95% CI = 1.52–1.79), venetoclax (1.65, 95% CI = 1.46–1.85), carfilzomib (1.53, 95% CI = 1.33–1.77), and nilotinib (1.46, 95% CI = 1.31–1.63).ConclusionsWhile newer anti-cancer drugs have improved the prognosis in cancer patients, it is important to identify any arrhythmias they may cause early on to prevent increased morbidity and mortality. Prospective studies are needed to better understand the true incidence of new onset AF associated with anti-cancer drugs.

China Export: Fludiazepam, Flunitrazepam, Flurazepam & their Salt data was reported at 0.000 USD th in Jun 2017. This stayed constant from the previous number of 0.000 USD th for Dec 2016. China Export: Fludiazepam, Flunitrazepam, Flurazepam & their Salt data is updated monthly, averaging 0.000 USD th from May 2011 (Median) to Jun 2017, with 10 observations. The data reached an all-time high of 0.000 USD th in Jun 2017 and a record low of 0.000 USD th in Jun 2017. China Export: Fludiazepam, Flunitrazepam, Flurazepam & their Salt data remains active status in CEIC and is reported by General Administration of Customs. The data is categorized under China Premium Database’s Pharmaceutical Sector – Table CN.RTB: Pharmaceutical Trade: Drugs for Circulatory and Central Nervous Systems.

The 21st Century Cures Act of 2016 includes a provision for the U.S. Food and Drug Administration10.13039/100000038 (FDA) to evaluate the potential use of Real-World Evidence (RWE) to support new indications for use for previously approved drugs, and to satisfy post-approval study requirements. Extracting reliable evidence from Real-World Data (RWD) is often complicated by a lack of treatment randomization, potential intercurrent events, and informative loss to follow-up. Targeted Learning (TL) is a sub-field of statistics that provides a rigorous framework to help address these challenges. The TL Roadmap offers a step-by-step guide to generating valid evidence and assessing its reliability. Following these steps produces an extensive amount of information for assessing whether the study provides reliable scientific evidence, including in support of regulatory decision-making. This article presents two case studies that illustrate the utility of following the roadmap. We used targeted minimum loss-based estimation combined with super learning to estimate causal effects. We also compared these findings with those obtained from an unadjusted analysis, propensity score matching, and inverse probability weighting. Nonparametric sensitivity analyses illuminate how departures from (untestable) causal assumptions affect point estimates and confidence interval bounds that would impact the substantive conclusion drawn from the study. TL’s thorough approach to learning from data provides transparency, allowing trust in RWE to be earned whenever it is warranted.

BackgroundMedroxyprogesterone acetate (MPA), a synthetic progestogen, is extensively used for the treatment of various conditions, including contraception, irregular menstruation, functional uterine bleeding, and endometriosis. However, like all pharmaceutical agents, MPA is associated with adverse drug reactions. This study aimed to evaluate the adverse events (AEs) associated with MPA in by analyzing real-world data from the U.S. Food and Drug Administration’s Adverse Event Reporting System (FAERS). By providing a comprehensive assessment of the safety profile of MPA, this study seeks to support informed clinical decision-making.MethodsData covering the period from the first quarter of 2004 to the first quarter of 2024 were collected from the FAERS database. Disproportionality analyses were conducted using several statistical methods, including reporting odds ratio (ROR), proportional reporting ratio (PRR), empirical Bayesian geometric mean (EBGM). Additionally, time-to-onset (TTO) analysis was employed to quantify the signals of the MPA-associated AEs.ResultsA comprehensive dataset comprising 21,035,995 AE reports was compiled. Among these, 3,939 women reported using MPA as a contraceptive method. The reports covered 27 system organ classes (SOCs) and 25 high-frequency AE signals. Notably, significant AEs were identified, some of which were not previously detailed in the medication’s prescribing information. Unforeseen significant AEs such as unintended pregnancy (n = 623; ROR, 6.65; ROR025, 6.1; χ2, 2,482.38; PRR, 6.41; EBGM, 5.69; EBGM05, 5.29), bone pain (n = 35; ROR, 13.78; ROR025, 9.4; χ2, 311.2; PRR, 13.75; EBGM, 10.59; EBGM05, 7.69), gait disturbance (n = 34; ROR, 2.82; ROR025, 1.99; χ2, 37.31; PRR, 2.88; EBGM, 2.7; EBGM05, 2.02), dental caries (n = 15; ROR, 23.16; ROR025, 12.32; χ2, 204.26; PRR, 23.14; EBGM, 15.23; EBGM05, 8.98), decrease in blood pressure (n = 15; ROR, 3.88; ROR025, 2.29; χ2, 29.35; PRR, 3.88; EBGM, 3.63; EBGM05, 2.33), and osteonecrosis (n = 9; ROR, 23.44; ROR025, 10.36; χ2, 123.67; PRR, 23.43; EBGM, 15.35; EBGM05, 7.75) were identified as AEs that were not previously outlined in the prescribing information of the medication.ConclusionOur findings align with clinical observations, highlighting the emergence of previously unreported AE signals associated with MPA and their demographic and TTO characteristics. Further pharmaco-epidemiological studies are required to substantiate these observations.

The dataset is designed to assist in predicting recommended medications for patients based on their fever condition, symptoms, medical history, and other relevant factors. It incorporates a mix of patient health data, environmental variables, and lifestyle choices to improve model accuracy and better simulate real-world scenarios.

Dataset Characteristics: Total Samples: 1000 (modifiable based on user needs). Number of Features: 19 features + 1 target column. File Format: CSV (enhanced_fever_medicine_recommendation.csv). Features Description: Column Name Description Data Type Temperature Body temperature of the patient in Celsius (e.g., 36.5 - 40.0). Float Fever_Severity Categorized fever severity: Normal, Mild Fever, High Fever. Categorical Age Age of the patient (1-100 years). Integer Gender Gender of the patient: Male or Female. Categorical BMI Body Mass Index of the patient (e.g., 18.0 - 35.0). Float Headache Whether the patient has a headache: Yes or No. Categorical Body_Ache Whether the patient has body aches: Yes or No. Categorical Fatigue Whether the patient feels fatigued: Yes or No. Categorical Chronic_Conditions If the patient has any chronic conditions (e.g., diabetes, asthma): Yes or No. Categorical Allergies If the patient has any allergies to medications: Yes or No. Categorical Smoking_History If the patient has a history of smoking: Yes or No. Categorical Alcohol_Consumption If the patient consumes alcohol: Yes or No. Categorical Humidity Current humidity level in the patient’s area (e.g., 30-90%). Float AQI Current Air Quality Index in the patient’s area (e.g., 0-500). Integer Physical_Activity Daily physical activity level: Sedentary, Moderate, Active. Categorical Diet_Type Diet preference: Vegetarian, Non-Vegetarian, or Vegan. Categorical Heart_Rate Resting heart rate of the patient in beats per minute (e.g., 60-100). Integer Blood_Pressure Blood pressure category: Normal, High, or Low. Categorical Previous_Medication Medication previously taken by the patient: Paracetamol, Ibuprofen, Aspirin, or None. Categorical Recommended_Medication Target variable indicating the recommended medicine: Paracetamol or Ibuprofen. Categorical

I was seeking data on tuberculosis (TB) cases, along with information on each country's population size and income level, to conduct a comprehensive analysis. Unfortunately, I couldn’t locate this specific data on the WHO website, so I decided to devise a solution on my own. This involved a data pre-analysis step, which included merging multiple datasets and transforming them into the format I had envisioned. This notebook serves as the foundation for that preparation, and will be followed by another notebook dedicated to the actual data analysis. I obtained the WHO TB data from the WHO website, specifically the Case notifications [>2Mb] CSV file. The population data was sourced from the World Bank, as well as the income classification information for countries was also retrieved from the World Bank, extracted from the Current Classification by Income table in XLSX format. All relevant files are available in the data/raw_data folder.

WHO TB Dataset Variable Descriptions

Geo & Time Identifiers

• country, iso2, iso3, iso_numeric – Country and standard ISO codes
• g_whoregion – WHO region (AFR - African Region, AMR - Region of the Americas, EMR - Eastern Mediterranean Region, EUR - European Region, SEA - South-East Asia Region, WPR - Western Pacific Region)
• year – Reporting year
• population_size - The number of people living in that country at that particular year
• income_level - The income level of that country at that particular year. Low income (L), Lower middle income (LM), Upper middle income (UM), High income (H).

Case Counts by Type & Treatment Category
(numeric counts of cases reported in the given year)

• new_sp – New smear‑positive pulmonary TB
• new_sn – New smear‑negative pulmonary TB
• new_su – New pulmonary TB with unknown smear status
• new_ep – New extrapulmonary TB
• new_oth – New ‘other’ TB cases (unspecified/mixed)
• ret_rel – Relapse cases (previous treatment, now bacteriologically confirmed again)
• ret_taf – Retreatment after failure
• ret_tad – Retreatment after default (loss-to-follow-up)
• ret_oth – Other retreatment cases
• newret_oth – Other new/retreatment cases not covered above

Diagnostic Confirmation Indicators
(how cases were confirmed or diagnosed)

• new_labconf – New cases confirmed via laboratory (smear, culture or molecular)
• new_clindx – New cases diagnosed clinically (without lab confirmation)
• ret_rel_labconf, ret_rel_clindx – Relapse cases by confirmation method
• ret_rel_ep – Relapse extrapulmonary cases
• ret_nrel – Retreatment cases not relapse
• notif_foreign – Cases notified among foreign nationals
• c_newinc – Total new incident cases (across all types)

Age & Sex Disaggregated Counts
(cases broken down by age group & sex)

• new_sp_m04, new_sp_m514, … new_sp_f65 – New smear‑positive cases by age & sex
• Similar naming for new_sn_* (smear-negative) and new_ep_* (extrapulmonary)
• new_sp_mu, new_sn_mu, new_ep_mu – Male & unknown sex totals
• new_sp_fu, new_sn_fu, new_ep_fu – Female & unknown sex totals

Relapse by Age/Sex

• newrel_m04, newrel_f1524, etc. – Relapse cases by age group & sex
• rel_in_agesex_flg, agegroup_option – Flags for available disaggregation

Drug Resistance & Testing Indicators

• rdx_data_available – Is drug-resistance data present?
• newinc_rdx, newinc_pulm_labconf_rdx, etc. – New (and pulmonary) cases with drug-resistance testing
• rdxsurvey_newinc, rdxsurvey_newinc_rdx – Survey-derived drug resistance data
• rdst_new, rdst_ret, rdst_unk – DST status among new, retreatment, unknown
• conf_rrmdr, conf_mdr – Confirmed rifampicin-resistant/MDR cases
• rr_sldst, all_conf_xdr, etc. – SL-DST and XDR confirmation
• Numerous *_tx variables – Treatment counts for drug-resistant cases, by regimen type

TB & HIV Co-infection Indicators

• newrel_tbhiv_flg – Flag if relapse-TB HIV data available
• newrel_hivtest, newrel_hivpos, newrel_art – Among relapse cases: tested for HIV, positive, on antiretroviral therapy
• tbhiv_014_flg, newrel_hivtest_014, etc. – Same but for 0–14 age group
• hivtest, hivtest_pos, hiv_cpt, hiv_art, hiv_tbscr, hiv_reg, hiv_ipt, etc. – HIV-related services among TB patients (testing, prophylaxis, treatment, registration).

To see the code for how the data was obtained you can check it out on my github repo.

Mental Illness Prevalence Across the US

Substate Level Estimates

By Substance Abuse and Mental Health Services Organization [source]

About this dataset

This dataset contains estimates of serious mental illness in the US by state and substate region from 2012-2014. This data helps to understand better the mental health disparities that exist between states and different regions within states. By looking at this data, researchers can identify the parts of the country with particularly high or low rates of serious mental illness, which can help prioritize resources for affected areas.

The dataset includes estimates along with 95% confidence intervals based on a survey-weighted hierarchical Bayes estimation approach and are generated by Markov Chain Monte Carlo techniques. Columns labeled Map Group can be used to distinguish substate regions included in corresponding maps as well as numerical order for sorting original sort order. For definitions in Substate Region, refer to the National Survey on Drug Use and Health's Substate Region Definitions found here: https://www.samhsa.gov/data/sites/default/files/NSDUHsubstateRegionDefs2014/NSDUHsubstateRegionDefs2014.pdf

This reliable information is provided by SAMHSA, Center for Behavioral Health Statistics and Quality through their National Survey on Drug Use and Health from 2012-2014; helping us gain insights into America’s overall mental health picture – revealing more about where help is needed most urgently so that we can take steps towards a healthier future for all Americans!

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

How to use the dataset

Welcome to this dataset! This dataset contains estimates of Serious Mental Illnesses in the United States by state and substate region from 2012 to 2014. It is designed for researchers, analysts, and data scientists looking for information about the prevalence of Serious Mental Illnesses across the US.

Research Ideas

• Performing a trend analysis to identify changes in the estimates of serious mental illnesses over time and across different geographic regions.
• Exploring disparities in serious mental illnesses among certain minority groups or deprived socio-economic subgroups by comparing estimates at the substate level.
• Developing targeted public health strategies and interventions for states with higher than average rates of serious mental illness prevalence

Acknowledgements

If you use this dataset in your research, please credit the original authors. Data Source

License

License: Dataset copyright by authors - You are free to: - Share - copy and redistribute the material in any medium or format for any purpose, even commercially. - Adapt - remix, transform, and build upon the material for any purpose, even commercially. - You must: - Give appropriate credit - Provide a link to the license, and indicate if changes were made. - ShareAlike - You must distribute your contributions under the same license as the original. - Keep intact - all notices that refer to this license, including copyright notices.

Columns

File: 2012-2014_Substate_SAE_Table_24.csv | Column name | Description | |:--------------------|:----------------------------------------------------------------------------------------------------------------------------------------------| | Order | A numerical order that can be used to sort the data back to its original order. (Numeric) | | State | The US state associated with the data. (String) | | Substate Region | The substate region associated with the data. (String) | | 95% CI (Lower) | The lower bound of the 95 percent confidence interval for the estimated number of people with serious mental illness in the region. (Numeric) | | 95% CI (Upper) | The upper bound of the 95 percent confidence interval for the estimated number of people with serious mental illness in the region. (Numeric) | | Map Group | A numerical value which can distinguish between different substate regions included in the maps. (Numeric) |

...

Context

Many drugs are introduced to the market for commercial and household use each year. Thus it is important to know the characteristics of these drugs.

Content

In this dataset you'll find info from hundreds of drugs that were introduced in 2019.

Acknowledgements

This data comes from https://data.world/chhs/e54d331c-65d3-4c6e-b4ba-390bd7024248.

Japan Production Value: Other Drug: Home Use: Urogenital Organ and Anus Drug data was reported at 0.000 JPY th in Jan 2018. This stayed constant from the previous number of 0.000 JPY th for Dec 2017. Japan Production Value: Other Drug: Home Use: Urogenital Organ and Anus Drug data is updated monthly, averaging 0.000 JPY th from Jan 2006 (Median) to Jan 2018, with 145 observations. The data reached an all-time high of 4,217.000 JPY th in May 2009 and a record low of 0.000 JPY th in Jan 2018. Japan Production Value: Other Drug: Home Use: Urogenital Organ and Anus Drug data remains active status in CEIC and is reported by Ministry of Health, Labour and Welfare. The data is categorized under Global Database’s Japan – Table JP.RT007: Production Value by Application and Therapeutic Category.

Taiwan Sales: DS: Medical Goods: Other Drugs & Medicines data was reported at 2,045,456.000 NTD th in May 2018. This records an increase from the previous number of 1,798,076.000 NTD th for Apr 2018. Taiwan Sales: DS: Medical Goods: Other Drugs & Medicines data is updated monthly, averaging 1,369,798.000 NTD th from Jan 1982 (Median) to May 2018, with 437 observations. The data reached an all-time high of 2,256,126.000 NTD th in Jan 2018 and a record low of 289,977.000 NTD th in Feb 1982. Taiwan Sales: DS: Medical Goods: Other Drugs & Medicines data remains active status in CEIC and is reported by Ministry of Economic Affairs. The data is categorized under Global Database’s Taiwan – Table TW.C0002: Sales: By Products: Domestic Sales: Value.