Rx

Rx#

Our WebApp offers six improvements on what is available in the literature and practice: sampling distribution, absolute risks, distinct hazards by phenotype, confidence intervals for individualized risk, explicitly reveals the footprint of missingness by parameter, and personalizes risk on a kaplan-meier curve for the user

                1. f(t)
                      \
           2. S(t) -> 4. y:h'(f)=0;t(X'X).X'Y -> 5. b -> 6. SV'
                      /
                      3. h(t) 

Specialist#

With any individualized prediction in science, a patient can’t say “that resonates” with me. The numbers are abstract and they’ve never experienced the outcome
But with art or tragedy the eternal recurrence of the same is encoded in the latent-space or collective unconscious and so it can resonate
Our way around this is by handing the end-user an app in which they might update their risk-profile and see if it changes the risk prediction
If there’s no change, then we could say the app is “mirroring” humanity so abominably; the backend model has no beta-coefficients for what has been tested
The structure of this discourse is : \(\mu\): base-case, \(\sigma\) varcov-matrix, \(\%\) predictive-accuracy

\(\mu\) Base-case#

\(f(t)\) l’homme moyen. But with five pdf’s, reflecting modalities
- Vision
  - Static Images
  - Videos (with audio)
  - GIFs
- Auditory
  - Unimodal
  - Bimodal e.g. audiovideo
- Chemistry
  - Smell (e.g. volatile substances)
  - Blood, serum, urine, etc
- Language
  - Text
  - Audio
  - Multilingual
- Tactile
  - Palpation or echo
  - Etc
\(S(t)\) somewhere ages and ages hence
- Cumulative datasets on which all the pdfs are trained
\(h(t)\) two roads diverged in a wood, and i—
- Instantaneous prediction utilizing speed & a lot of data on the fly

\(\sigma\) Varcov-matrix#

var[\((X'X)^T \cdot X'Y\)] think: the variability of courses & items in italian cuisine & modes-qualities-relatives in chopin
- ChatGPT Solving Complex Kidney Transplant Cases: A Comparative Study with Human Respondents
- This paper only offers 6 clinical scenarios
- GPT models have a real edge in being “large” and having been trained on the entire pdf including extreme tails
- No clinician has the “experience” & ability to pay “attention” even to traits associated with tails & produce stable & accurate predictions

\(\%\) Predictive-accuracy#

\(\beta\) my palate craves very diverse things over time & i can only tell what i want on a given day
\(SV'\) \(\ge 85\) only a very rich culture can throw me a bone to chew on that will keep me engaged
- Clinicians can’t be interrogated in frequent iterations without accruing a bill or their irate responses

Generalist#

Arte (Imitation) & Scienza (Prediction) = Tragedy (Representation). When the products of art, science, or tragedy resonate with us, they have been accurately decoded with all the parameter coefficients similar to our own

                     1. Observing
                                \
           2. Time = Compute -> 4. Collective Unconscious -> 5. Decoding -> 6. Imitation-Prediction-Representation
                                /
                                3. Encoding

Rx

Contents

Rx#

Specialist#

\(\mu\) Base-case#

\(\sigma\) Varcov-matrix#

\(\%\) Predictive-accuracy#

Generalist#