Tom Samuels
@thomashasamuels.bsky.social
NIHR Academic Clinical Fellow in Infectious Diseases @ UCL and soon to be NIHR Doctoral Fellow @ UCL. Infection diagnostics, data science and predictive modelling.
Explorative analysis of treatment effect demonstrated a trend towards improved outcomes in patients with low predicted risk who received the single high dose liposomal amphotericin B, compared with standard amphotericin B deoxycholate + flucytosine.
6/8
6/8
April 30, 2025 at 7:59 PM
Explorative analysis of treatment effect demonstrated a trend towards improved outcomes in patients with low predicted risk who received the single high dose liposomal amphotericin B, compared with standard amphotericin B deoxycholate + flucytosine.
6/8
6/8
Calibration, the measure of how well model predictions matched observed events, was reasonable for both regression models, although demonstrated some overprediction of risk at high-risk ranges, where training data was sparser. The machine learning model demonstrated miscalibration.
5/8
5/8
April 30, 2025 at 7:59 PM
Calibration, the measure of how well model predictions matched observed events, was reasonable for both regression models, although demonstrated some overprediction of risk at high-risk ranges, where training data was sparser. The machine learning model demonstrated miscalibration.
5/8
5/8
Both regression models discriminated well between patients who met the outcome and those who did not in held out validation data. The machine learning model did not improve performance.
4/8
4/8
April 30, 2025 at 7:59 PM
Both regression models discriminated well between patients who met the outcome and those who did not in held out validation data. The machine learning model did not improve performance.
4/8
4/8
Explorative analysis of treatment effect demonstrated a trend towards improved outcomes in patients with low predicted risk who received the single high dose liposomal amphotericin B, compared with standard amphotericin B deoxycholate + flucytosine.
6/8
6/8
April 30, 2025 at 5:21 PM
Explorative analysis of treatment effect demonstrated a trend towards improved outcomes in patients with low predicted risk who received the single high dose liposomal amphotericin B, compared with standard amphotericin B deoxycholate + flucytosine.
6/8
6/8
Calibration, the measure of how well model predictions matched observed events, was reasonable for both regression models, although demonstrated some overprediction of risk at high-risk ranges, where training data was sparser. The machine learning model demonstrated miscalibration.
5/8
5/8
April 30, 2025 at 5:21 PM
Calibration, the measure of how well model predictions matched observed events, was reasonable for both regression models, although demonstrated some overprediction of risk at high-risk ranges, where training data was sparser. The machine learning model demonstrated miscalibration.
5/8
5/8
Both regression models discriminated well between patients who met the outcome and those who did not in held out validation data. The machine learning model did not improve performance.
4/8
4/8
April 30, 2025 at 5:21 PM
Both regression models discriminated well between patients who met the outcome and those who did not in held out validation data. The machine learning model did not improve performance.
4/8
4/8