top of page
From thousands of voices to structured data
  • Voices for Women aims to improve healthcare for women

  • The organization received a vast amount of unstructured text from women with unexplained health complaints  

  • GenAI transformed these unstructured stories into a structured dataset, allowing simple yet effective analysis techniques to create valuable insights

  • The project was a rewarding experience where the team - motivated by the stories shared by women - leveraged their expertise on LLMs and healthcare, pragmatism, and a structured approach to deliver significant value

At a glance:

Voices for Women (VfW) is a foundation dedicated to gender-specific care. Traditionally, medical research has focused on men, even though the female body responds to illness differently than the male body. Consequently, a staggering 80% of patients with unexplained health complaints are women. By examining just four specific diseases, timely recognition, accurate diagnosis and appropriate treatment could save €7.6 billion annually for women in the Netherlands alone [1]! Furthermore, the projected ‘unnecessary’ costs are estimated to reach €750 billion across the European Union [2]. VfW’s mission is crystal clear: give women with unexplained health complaints a voice and improve healthcare for all women. 


Since experience expert Mirjam Kaijer founded the organization, thousands of women with unexplained health complaints have contacted VfW. The overwhelming volume of responses posed a challenge: How to extract valuable insights from the vast sea of unstructured text? That’s why IG&H stepped in. Our team, consisting of healthcare and AI experts, provided support to VfW during a 3-week project in which a GenAI solution was built to extract those insights. With confidentiality in mind, we are unable to disclose the findings of our research. However, we would like to share our approach and lessons learned. 


The GenAI Solution  

As a first step, we created focus on the most critical topics for VfW, while ensuring that we could deliver high-quality results on these topics. For example, exploring whether valuable insights could be derived on these topics by solely asking questions that yield numerical or “Yes/No” responses. While understanding the most common unexplained health issues for women with unexplained health complaints is both interesting and valuable, it requires relatively complex GenAI modeling that may not yield high-quality results. In contrast, extracting the length of a woman’s patient journey can be done relatively easily. 


The next step was setting up the data processing process. GenAI performs very well on bite-sized chunks of information. Rather than overwhelming it with all the data at once, we processed each story individually and always asked a separate question for extracting a single data point. Once we set the scope and decided how we were going to process the data, we used a three-step approach to create powerful insights: 


1) Unstructured to Structured 

An LLM (GenAI) transformed the unstructured stories into a structured dataset consisting of columns and rows, instead of numerous separate text files. 


2) Data Analysis Techniques

Once we had a structured dataset, we applied simple yet effective analysis techniques. The data only consisted of simple categories and numbers, allowing very useful insights to be gathered without complex data processing techniques.  


3) Compelling Storytelling  

Insights alone are powerful, but when put into a compelling story supported by strong visuals, it extracts even more value from the data. In only a few visualizations we were able to tell the stories of over a thousand women. 

3 Key Learnings & Results 

We were humbled by the stories shared by so many women. What so many of them have gone through is beyond what most of us could imagine. This fuelled our motivation to help Voices for Women in their fight for better healthcare for women. This project was undeniably a rewarding and special experience, where we combined a powerful technique with our expertise both in LLM and healthcare to deliver significant value. We identified several crucial success factors for any GenAI solution project: 

1) Have a proper understanding of how LLMs work 

This includes understanding their strengths and weaknesses. LLMs have a unique ability to generate creative and complex sentences, which is a significant advantage in tasks requiring nuanced and detailed responses. However, this strength can also be a weakness in scenarios that require precise and straightforward answers.  


Asking simple and concrete questions was important, along with putting a strong emphasis on the answering possibilities. As an additional strength, LLMs are fast and easily scalable, which significantly contributed to the efficient training and testing of our model. This understanding allowed us to define all realistic analyses and create the most value possible within the three-week timeframe. 


2) Be pragmatic 

We acknowledged that while LLMs immediately work well in some cases, others might need more time on finetuning. To ensure high-quality results in a short timeframe, we accepted the necessity of manual checks on approximately 10% of the data. This ensured a good balance between finetuning the LLM for outputting high-quality results and timely project delivery.  


3) Manage complexity with a structured approach 

Working towards a solution with a good training and testing structure was essential. Using training and test sets ensured consistent and reliable results. This structured approach was instrumental in navigating through the complexities of the project and achieving our goals. 


After they became one of the winners of the IG&H Dragons' Den, we continued helping VfW (pro bono) in gathering the right information and supporting women's health. We believe that with our insights a better voice can be given to women with unexplained health issues and that this project will be the beginning of a successful partnership.




[2] Mind-the-Gap-Costs-Consequences-and-Correction-of-Gender-Inequality-in-Medicine.pdf (

Read more healthcare client cases

Ready to transform your business?

Stay ahead of your competitors by transforming your business. We have more than 30 years experience in helping clients innovate, deliver superior experiences and execute on their strategies. Curious how we can help?