Home

E-Commerce

Data

Services

About Us

Events

Resources

Success stories

Blog

Insights

Work At Arbusta

Contact

a-logo-arbusta.png

arbusta-logo-arbusta.png

Arbusta

Upcoming events

Schedule

Próximos eventos

Agenda

Recursos

Casos de éxito

Mamotest is a company from Argentina that leverages technology to make routine studies more accessible for women, regardless of their place of residence. Operating from 13 health centers, Mamotest supports both the public and private sectors by offering telediagnosis breast examinations, ranging from digital and 3D mammography to breast ultrasounds and stereotactic biopsies. Mamotest reached out to Arbusta in order to find a comprehensive solution to a big problem: they had over 200,000 medical results, crucial for early detection and treatment of breast cancer, stored across two different software systems. They had an urgent need to consolidate their database.

Our Data Services team initiated the process of structuring and reclassifying the information stored in two distinct sources. This allowed us to extract essential data from each study and organize it according to the defined standards. To enhance efficiency, we enlisted a specialized automation team from Arbusta, which significantly improved delivery times and data quality. As a result, we successfully normalized a total of 5 terabytes of information stored in over 7,000 folders. Currently, this integrated database serves as the foundation for a prototype artificial intelligence model capable of identifying areas of risk and prioritizing studies that require urgent medical review.

1.png

The challenge

The solution

We streamlined the decision-making process for doctors, providing quick and secure access to files in a single source of information. 

We enhanced Mamotest’s mission

We cleaned, classified, and normalized over 7,000 folders and 5 TB of information that were dispersed across two distinct software systems.

We normalized the data

This entailed efficient renaming and movement of files, as well as automated spreadsheet completion.

We automated tasks

Through the implementation of automation, we went from normalizing 300 studies per week to 700 studies per week.

We accelerated processes

We integrated more than 200,000 breast studies on the Mamotest server, which facilitated access to timely diagnoses and treatments.

We optimized diagnoses

We fueled Mamotest's artificial intelligence model, which identifies risk areas and studies that require urgent review.

We promoted AI learning

Rectangle 3.png

Key results

Learn how we standardized 200,000 telemammography study results that were scattered across two different software systems.

small_hq720_2.jpg

thumbnail_hq720_2.jpg

hq720_2.jpg

Descubre cómo normalizamos más de 200 mil estudios de telemamografías que estaban dispersos en dos softwares diferentes.

Caso de éxito: Mamotest

Success Story: Mamotest

Swiss Medical Group, a group of companies committed to safeguarding people, provides private health services, insurance, labor risk insurance, among other services, to more than 1 million associates in Argentina. Due to its extensive scope, in 2022 the organization recognized the need to address a common challenge faced by many companies worldwide: the shortage of IT talent. Swiss Medical Group embarked on a search for new programmers who could seamlessly integrate into their development teams to work on various digital products within their business systems. To address this, they enlisted our "Jumps" service, a program that enables us to assemble teams with the necessary technical and socioemotional skills to integrate into our clients' IT teams.

At Arbusta, we implemented the "Jumps" talent acceleration program, which involves recruiting young individuals with no prior experience but great potential and training them in the skills that companies require. We began the training program with a group of 5 individuals, providing them with sessions on the organization's systems, training in full stack development, agile methodologies, and essential socioemotional skills such as leadership, assertive communication, and emotional intelligence. Additionally, we included practical projects. Within a few months, these new talents successfully passed client assessments and were seamlessly integrated into the company's programming team.

2.png

Arbusta experts accompanied talent throughout the incorporation process, providing them with technical and emotional support.

We took care of the onboarding

By developing new talents wh just starting their careers in technology and who could grow within SMGs workforce.

We brought diversity to its teams

The people we recruited wanted to unleash their full potential in organizations that give opportunities to launch a career in technology.

We promoted retention in IT

We trained 5 young individuals who joined to strengthen SMG's programming team.

Tailored talent development

We prepared the new talents in SMG's proprietary system, as well as various programming languages and agile methodologies.

We developed technical skills

The new programmers acquired socioemotional skills that allowed them to easily integrate into the SMG working environment.

We trained soft skills

Key achievements

We provided training to programmers, enabling them to become part of this team of top companies in the health market.

medium_Casos éxito - Swiss-Medical.jpg

small_Casos éxito - Swiss-Medical.jpg

thumbnail_Casos éxito - Swiss-Medical.jpg

Casos éxito - Swiss-Medical.jpg

Success story: Swiss Medical Group

Mercado Libre is an electronic commerce and payment platform that runs in more than 18 Latin American countries. On this platform, almost 73 million people interact, between buyers and sellers.  In 2020 alone, it generated the delivery shipment of 1,7 million packages per day and added 57 million new users. The company has managed to position itself as a leader in the region by guaranteeing a reliable ecosystem for users. However, the growing volume of data and exchanges in the marketplace made them turn to Arbusta: Mercado Libre needed an external team that could improve image and text labeling to help its Machine Learning model prevent frauds and verify the quality of transactions.

Our Machine Learning Training team took on the manual training of the model supervised by Mercado Libre to help it become more accurate in the detection of frauds and irregularities. We initiated a process of manual labeling of the platform's images and texts to assist the algorithm in verifying the authenticity of logos (image annotation), identifying publications that violate counterfeit policies or involve forbidden articles (fakes), verifying the accuracy of information provided by sellers to buyers, and ensuring correct filling of text fields in each publication.

data 2.jpg

We formed a team 100% focused on labeling, so as to incorporate an ever-growing volume of data and inputs into Mercado Libre’s AI model.

We improved the AI learning

In the first quarter of 2021, the number of identified irregularities tripled.

We increased detection

Mercado Libre now has a larger and better quality dataset for training its Machine Learning model.

We escalated the labeling

By delegating these tasks to us, Mercado Libre reduced the operational burden on their data science and technology team.

We took on the manual work

Discover how we successfully optimized fraud and irregularity detection on the platform and trained its Machine Learning model.