Home >> Savana’s Reality Checks.

Savana's Reality Checks

01 - Major bleeding events and recurrence of venous thromboembolism in anticoagulated cancer patients:

WHAT

  • An AI predictive model for prediction of bleeding and thromboemobolism among anticoagulated cancer patients.

WHY THIS WORK IS REMARKABLE 

  • Because through the analysis of a multicentric 2,893,208 patients population, it created one of the first AI algorithms for this purpose. The methodology included techniques that prevented bias and class imbalance.

WHAT WAS THE CONSEQUENCE 

  • Medical Oncologists now have an available predictive model for deciding about anticoagulation.

WHAT THIS WORK DEMONSTRATES

  • The RWE generated through NLP applied to EMR, in combination with a Machine Learning approach, facilitates the generation of predictive models in cancer patients, with direct clinical impact.

02 - Rheumatoid arthritis:

WHAT

  • Prevalence and comorbidities of rheumatoid arthritis-associated interstitial lung disease.

WHY THIS WORK IS REMARKABLE 

  • Because the analysis of a multicentric population using Natural Language Processing showed remarkably similar results to those recently obtained through a traditional manual data collection.

WHAT WAS THE CONSEQUENCE 

  • Using this study, awareness is being raised among rheumatologists about the need to consider testing for interstitial lung disease in rheumatoid arthritis populations, given that its prevalence is higher than previously known.

WHAT THIS WORK DEMONSTRATES

  • Natural Language Processing applied to EMR looks like an agyle way to obtain reliable epidemiological information, without the effort of manual data collection.

03 - Crohn's Disease

WHAT

  • An AI predictive model for Crohn’s disease relapses.

WHY THIS WORK IS REMARKABLE 

  • Because through the analysis of almost 6.000 patients and the ranking of 25.000 variables, it created one of the first AI algorithms in Inflammatory Bowel Disease.

WHAT WAS THE CONSEQUENCE 

  • Gastroenterologists now have an available predictive model for this disease.

WHAT THIS WORK DEMONSTRATES

  • The RWE generated through NLP applied to EMR, in combination with a Machine Learning approach, facilitates the generation of predictive models in inflammatory diseases.
European Journal of Gastronterology & Hepatology logo

04 - Coronary Type 2 Diabetes

WHAT

  • High rates of cardiovascular events in a large real-world series of PCI-revascularized patients with Type 2 Diabetes and Coronary Artery Disease with no history of Miocardial Infarction or stroke.

WHY THIS WORK IS REMARKABLE

  • Because through NLP it was possible to analyse +200.000 diabetes patients from 12 representative hospitals from a European region, without having to create any database or registry.

WHAT WAS THE CONSEQUENCE 

  • Due to knowing the prevalence,  agreements regarding the most appropriate management of the disease could be facilitated.

WHAT THIS WORK DEMONSTRATES 

  • NLP applied to EMR is an improved and more innovative method for generating epidemiology for almost any disease.

05 - Systemic corticosteroids - Bronchial Asthma

WHAT 

  • Systemic corticosteroids are frequently prescribed to patients with asthma, especially in primary care. Its use is associated with a greater number of adverse events.

WHY THIS WORK IS REMARKABLE

  • Because it was able to jointly analyze patients  from both Primary Care and Specialized Care, in a healthcare system where the information from these two environments were previously disconnected.

WHAT WAS THE CONSEQUENCE 

  • Awareness was raised about the overprescription of systemic corticosteroids in clinical practice.

WHAT THIS WORK DEMONSTRATES 

  • Savana’s NLP and Machine Learning techniques represent a robust way of identifying variability and quality issues in clinical practice.
Journal of Investigational Allergology and Clinical Immunology logo

06 - COVID

WHAT

  • Inhaled corticosteroids may be associated with a protective effect against severe COVID-19.

WHY THIS WORK IS REMARKABLE

  • Because these results were consistent (months ahead) with the NEJM-published RECOVERY clinical trial, led by Oxford.

WHAT WAS THE CONSEQUENCE 

  • The pulmonologists were able to reinforce their observed clinical impression regarding steroids and COVID, in real time during the pandemic. 

WHAT THIS WORK DEMONSTRATES 

  • Savana’s NLP and ML methodology are reliable for establishing associations between disease and treatments, with no manual data collection efforts required.
European Respiratory journal logo

07 - COPD

WHAT 

  • Clinical management and burden of disease of COPD in a European region.

WHY THIS WORK IS REMARKABLE

  • Because it scanned a complete +1million population, analysing every patient with COPD in a few days, avoiding the manual creation of any registry or database.

WHAT WAS THE CONSEQUENCE 

  • Decisions regarding innovative therapies in COPD were taken.

WHAT THIS WORK DEMONSTRATES 

  • Savana’s NLP and ML methodology enables clinicians to make informed decisions around drugs indications and serves in understanding health economics.

08 - COVID in COPD

WHAT

  • A higher incidence of COVID-19 in COPD patients and higher rates of hospital admissions and mortality, mainly associated with pneumonia.

WHY THIS WORK IS REMARKABLE

  • Because it was able to scan every patient with COPD and COVID in a European Region in the middle of the first wave of the pandemic, applying NLP to EMRs at scale enabled us to extract pioneering insights faster than any traditional method could have achieved.

WHAT WAS THE CONSEQUENCE

  • It was the first source of information confirming the intersection of these two conditions.

WHAT THIS WORK DEMONSTRATES

  • Savana’s Research Network and methodology facilitates the accelerated generation of updated evidence in a novel manner  unrivalled by more traditional methods of data collection.
Journal of Clinical Medicine logo

09 - Major Adverse Cardiovascular Events in Coronary Type 2 Diabetic Patients: Identification of Associated Factors Using Electronic Health Records and Natural Language Processing

WHAT

  • Identification of Associated Factors in Major Adverse Cardiovascular Events in Coronary Type 2 Diabetic Patients.

WHY THIS WORK IS REMARKABLE

  • Because a national scientific society lead the investigation and used AI to solve a clinical question.

WHAT WAS THE CONSEQUENCE 

  • Awareness about the role of statins in major adverse cardiovascular events among diabetic patients has been arisen.

WHAT THIS WORK DEMONSTRATES 

  • That AI and Natural Language Processing are ideal tools for the identification of risk factors in chronic diseases.

Journal of Clinical Medicine logo

10 - Prevalence of cancer among patients with hypothyroidism: Analysis using big data tools

WHAT 

  • Prevalence of cancer among patients with hypothyroidism.

WHY THIS WORK IS REMARKABLE

  • Because using AI and machine learning, it could be addressed the intersection of two clinical entities which are normally separate and difficult to assess jointly.

WHAT WAS THE CONSEQUENCE 

  • There is new awareness about the possibility of developing cancer among patients with hypothyroidism.

WHAT THIS WORK DEMONSTRATES 

  • Natural Language Processing applied to Electronic Medical Records reuse represents an excellent tool in order to intersect the epidemiology of different clinical entities.

ELSEVIER logo

11 - Patient journey of individuals tested for HCV in Spain: LiverTAI, a retrospective analysis of EHRs through Natural Language Processing

WHAT

  • Patient journey of individuals tested for HVC.

WHY THIS WORK IS REMARKABLE

  • Because using Natural Language Processing a complete population from 6 hospitals, including 2,440,358 patients, could be scrutinized, finding every patient tested for HVC, across all departments.

WHAT WAS THE CONSEQUENCE

  • It was signalled the lack of testing in certain departments, as long as the lack of RNA ang genotype determination.

WHAT THIS WORK DEMONSTRATES

  • Natural Language Processing on Electronic Medical Records as a unique tool for patient journey evaluation.

12 - Oral Communication: Diabetes type 1 and type 2

WHAT

  • Hospital prevalence and characterization of diabetes type 1 and type 2.

WHY THIS WORK IS REMARKABLE

  • Because an AI model was developed to be able to identify type 1 and type 2 diabetes even when it wasn’t explicitly stated in the clinical notes.

    Because 638,730 individuals with diabetes could be evaluated without any human data collection.

WHAT WAS THE CONSEQUENCE 

  • There is new evidence about the actual epidemiology of diabetes among hospital populations.

WHAT THIS WORK DEMONSTRATES 

  • AI and Natural Language Processing as an asset to evaluate massive amounts of patients in prevalent diseases, saving countless hours of human labor.

13 - Use of N-Acetylcysteine as a COVID-19 treatment

WHAT 

  • Use of N-Acetylcysteine at high doses as an oral treatment for patients hospitalized with COVID-19.

WHY THIS WORK IS REMARKABLE

  • Because through the analysis of 19,208 patients with a diagnosis of COVID-19 hospitalized, including both Primary Care and Specialized care information, it could be found the association of N-Acetylcysteine with significant lower mortality.

WHAT WAS THE CONSEQUENCE 

  • There is new evidence about N-Acetylcysteine as a beneficial treatment for COVID-19, which poses a relevant hypothesis for future clinical trials.

WHAT THIS WORK DEMONSTRATES 

  • The RWE generated through NLP applied to EMR facilitates the evaluation of drugs.

14 - Thyroid carcinoma in elderly people

WHAT

  • Characterization of thyroid carcinoma among elderly people.

WHY THIS WORK IS REMARKABLE

  • Because using big data tools, the researchers were able to describe the histological particularities and the resource consumption in a particular subpopulation.

WHAT WAS THE CONSEQUENCE

  • There is now awareness about the routine management of this type of carcinoma across different epidemiological groups.

WHAT THIS WORK DEMONSTRATES

  • Natural Language Processing applied to Electronic Medical Records reuse represents an excellent tool in order to generate Health Economics data in Oncology.

16 - Type 2 Diabetes Mellitus and Stable Coronary Artery Disease

WHAT

  • Impact of Advanced Age on the Incidence of Major Adverse Cardiovascular Events in Patients with Type 2 Diabetes Mellitus and Stable Coronary Artery Disease in a Real-World Setting.

WHY THIS WORK IS REMARKABLE

  • Because it shows how the analysis of remarkable amounts of chronic patients using AI can help tell untold stories about the variables behind their evolution.

WHAT WAS THE CONSEQUENCE 

  • Now patients with MACE and T2DM+CAD are better known at older age and in the presence of further comorbidities.

WHAT THIS WORK DEMONSTRATES 

  • The generation of RWE using AI is an excellent tool for scientific tools to better know the populations they handle.

Journal of Clinical Medicine logo

17 - Chronic Lymphocytic Leukemia

WHAT 

  • Real-World Evidence on the Clinical Characteristics and Management of Patients with Chronic Lymphocytic Leukemia in Spain Using Natural Language Processing: The SRealCLL Study.

WHY THIS WORK IS REMARKABLE

  • Because it shed light about facts such as the increased use of precise target therapies and the decreased reliance on chemoimmunotherapy in both first-line and relapsed/refractory cases.

WHAT WAS THE CONSEQUENCE 

  • Thanks to AI, there is now new evidence to help professionals move away from one-size-fits-all strategies and instead, optimize clinical management, tailoring treatments for each patient.

WHAT THIS WORK DEMONSTRATES 

  • That in malignant hematological disease, the use of Natural Language Processing for Electronic Medical Records analysis helps the pathway towards precision medicine.

We send a weekly email for you to start making friends with AI. 

It's not for those who want to generate evidence by traditional means, filling registries by hand and using logistic regression. This is for those who want to leverage machine learning in order to generate evidence in a more automated way and with higher granularity of variables.

Subscribe here:

I don't want to subscribe, I want to read the blog

By the way, if you register you will receive our masterclass about AI in healthcare:

  • 54 min of content. 
  • An astonishing simple explanation about what AI and machine learning are. (Minute 0)
  • Specific and tangible examples of its application in healthcare. (Minute 10)
  • The exact steps to follow in order to start a project in AI. (Minute 21)
  • How to critically read the projects of others. (Minute 34)
  • A tip to distinguish bullshit from truth when buying AI. (Minute 50)
  • A gift: a compelling newsletter which you subscribe to in order to be continually updated, providing you with a quick 5 minute overview just once a week. 
  • Another gift: the best more extensive course to follow providing you with an insightful deeper dive into AI applications in healthcare.

Want to use it?:

Start with your proposed AI + RWE use case:

This is the first step for AI + RWE: