Jaya Balusu - Academia.edu (original) (raw)
Uploads
Papers by Jaya Balusu
Journal of Clinical Oncology, 2019
e20568 Background: Many targeted therapy clinical trials require a somatic gene mutation/alterati... more e20568 Background: Many targeted therapy clinical trials require a somatic gene mutation/alteration for eligibility. We assessed the feasibility of leveraging Real-World Data (RWD) to enrol NSCLC patients into clinical trials. Methods: US insurance claims data were extracted to identify lung cancer patients. These data were matched with EMR data also containing NSCLC patients’ details regarding the occurrence and results of molecular testing for EGFR, ALK, ROS1, JAK2, HER2 and RET somatic alterations, achieving a level of granular detail beyond that available in each individual dataset. A one-year extraction period was applied, with no gender or age restrictions. Results: Results for the matched dataset are summarised in the table below - the overall patient record match was 89.6%. Conclusions: The observed prevalence correlated reasonably well with literature reported prevalence for the molecular biomarkers associated commercially available targeted therapies in NSCLC (EGFR, ALK, R...
ArXiv, 2022
The COVID-19 pandemic has dramatically changed how healthcare is delivered to patients, how patie... more The COVID-19 pandemic has dramatically changed how healthcare is delivered to patients, how patients interact with healthcare providers, and how healthcare information is disseminated to both healthcare providers and patients. Analytical models that were trained and tested pre-pandemic may no longer be performing up to expectations, providing unreliable and irrelevant learning (ML) models given that ML depends on the basic principle that what happened in the past are likely to repeat in the future. ML faced to two important degradation principles, concept drift, when the underlying properties and characteristics of the variables change and data drift, when the data distributions, probabilities, co-variates, and other variable relationships change, both of which are prime culprits of model failure. Therefore, detecting and diagnosing drift in existing models is something that has become an imperative. And perhaps even more important is a shift in our mindset towards a conscious recog...
Journal of Clinical Oncology, 2019
e20568 Background: Many targeted therapy clinical trials require a somatic gene mutation/alterati... more e20568 Background: Many targeted therapy clinical trials require a somatic gene mutation/alteration for eligibility. We assessed the feasibility of leveraging Real-World Data (RWD) to enrol NSCLC patients into clinical trials. Methods: US insurance claims data were extracted to identify lung cancer patients. These data were matched with EMR data also containing NSCLC patients’ details regarding the occurrence and results of molecular testing for EGFR, ALK, ROS1, JAK2, HER2 and RET somatic alterations, achieving a level of granular detail beyond that available in each individual dataset. A one-year extraction period was applied, with no gender or age restrictions. Results: Results for the matched dataset are summarised in the table below - the overall patient record match was 89.6%. Conclusions: The observed prevalence correlated reasonably well with literature reported prevalence for the molecular biomarkers associated commercially available targeted therapies in NSCLC (EGFR, ALK, R...
ArXiv, 2022
The COVID-19 pandemic has dramatically changed how healthcare is delivered to patients, how patie... more The COVID-19 pandemic has dramatically changed how healthcare is delivered to patients, how patients interact with healthcare providers, and how healthcare information is disseminated to both healthcare providers and patients. Analytical models that were trained and tested pre-pandemic may no longer be performing up to expectations, providing unreliable and irrelevant learning (ML) models given that ML depends on the basic principle that what happened in the past are likely to repeat in the future. ML faced to two important degradation principles, concept drift, when the underlying properties and characteristics of the variables change and data drift, when the data distributions, probabilities, co-variates, and other variable relationships change, both of which are prime culprits of model failure. Therefore, detecting and diagnosing drift in existing models is something that has become an imperative. And perhaps even more important is a shift in our mindset towards a conscious recog...