Custom Pages
[vc_separator type='transparent' color='' thickness='' up='20' down='7']
Portfolio
[vc_separator type='transparent' color='' thickness='' up='20' down='7'] [social_icons type="normal_social" icon="fa-twitter" use_custom_size="yes" size="fa-lg" custom_size="17" link="http://twitter.com" target="_blank"] [social_icons type="normal_social" icon="fa-facebook" use_custom_size="yes" size="fa-lg" custom_size="17" link="http://www.facebook.com" target="_blank"] [social_icons type="normal_social" icon="fa-google-plus" use_custom_size="yes" size="fa-lg" custom_size="17" link="https://plus.google.com" target="_blank"] [social_icons type="normal_social" icon="fa-instagram" use_custom_size="yes" size="fa-lg" custom_size="17" link="http://instagram.com" target="_blank"] [social_icons type="normal_social" icon="fa-tumblr" use_custom_size="yes" size="fa-lg" custom_size="17" link="https://www.tumblr.com" target="_blank"]
KardioFit Logo

KardioLytix is a real-time data analytics tool for the measurement and reporting of outcomes-based health and predictive or future risk assessment, as well as decision making. 

 

At BrandMed, we believe that by combining scientific literature, expert knowledge and state-of-the-art machine learning with data analytics, better decisions can be made within the construct of the current healthcare environment and its challenges.

 

With contextual data expansion, the KardioLytix system has the ability to transition to the automated calculation of risk of a wide range of future healthcare outcomes, such as:

 

  • Identifying patients presenting the greatest healthcare risks during a future period, often within the following  12, 24 or 36 months
  • Identifying patients most at risk of developing  chronic comorbidities
  • Identifying patients most at risk of a deteriorating  health status
  • Identifying patients most at risk of specific adverse health events, for example, a cardiovascular event or invasive back surgery
  • Predicting patients most at risk of unplanned hospital admissions, readmissions, or emergency care visits
  • Predicting the mortality risk of patients in hospital
  • Predicting the risk of complications for patients in hospital

Our Actuaries
Christine Mannie

Academic Qualifications: BPharm (NMMU), MPH Graduate

(Johns Hopkins Bloomberg School of Public Health (JHSPH)),

Certifications in Global Health (JHSPH), Health Finance

and Management (JHSPH), Quantitative Methods in Clinical

Public Health Research (Harvard), Descriptive statistics,

probabilities, statistical inference (UNISA).


Christina is the Co-Founder and Director at MAST

Stefan Strydom

 

Academic Qualifications: BSc (Hons) (Mathematical

Statistics) (Stellenbosch), MSc (CS/ML) (Stellenbosch).

Healthcare Fellow of the South African Actuarial Society.

CSMM.103x: Robotics (Columbia University (CU), New York

City), edX Verified Certificate for CSMM.101x: Artificial

Intelligence (AI) (CU), CSMM.102x: Machine Learning (CU).

BrandMed Team DR TOM MABIN

Mannie and Strydom’s philosophy centres on understanding

the health status of populations, developing risk

stratification models to identify significant factors to inform

the design of effective initiatives, such as care management

programmes or alternative payment models, and measuring

the outcomes of the interventions implemented.


Mannie and Strydom have developed award-wining risk

stratification models for care-management and have

been acknowledged for their contribution to designing

innovative solutions.

 
NerveIQ Logo White