commit 3cfba3f60516e311e4349239340304e0df7e73bf
parent 147dd21bfc8573eabf4f1493f1b994506a88e1a3
Author: beau hilton <cbeauhilton@gmail.com>
Date: Fri, 20 Oct 2023 17:50:14 -0500
update about section (needs more)
Diffstat:
2 files changed, 261 insertions(+), 12 deletions(-)
diff --git a/site/about.md b/site/about.md
@@ -1,34 +1,279 @@
## husband and father
-These are the most important roles I play.
-If we meet, and you're interested, we can talk about it.
+Talented, beautiful people surround me.
+The [now page](beauhilton.com/now)
+usually has the most current updates in this arena.
## physician
+Dates are for the academic year, e.g. academic year 2026 ends in 2027.
Oncology fellow, Vanderbilt 2022-2026.
Internal medicine resident, Vanderbilt 2020-2022.
Medical school, Cleveland Clinic Lerner College of Medicine
of Case Western Reserve University 2015-2020.
+I enjoy treating people with any cancer,
+but have a particular affinity for
+head-and-neck and upper GI cancers
+(together, 2/3 of the "aerodigestive" cancers, the other 1/3 being lung).
+There are many right ways to be a doctor,
+but the way I understand my role is this:
+to be with people in their suffering and their joy (suffering is everywhere, but there is a special joy known only in the oncology clinic),
+to see and know the soul within the body (whatever the tumor or the scalpel or the radiation beam or the drug has done to that body),
+to cure when I can (and deal with the fallout from that cure),
+and help always (to the end and beyond).
+
+There are glimmers of hope and serious advances in recent years,
+but these remain horrible diseases,
+many of which have few treatment options
+once they've reached an advanced stage,
+and the treatments we do have tend to be quite difficult to tolerate.
+Most cancers can be disfiguring,
+but these especially so,
+whether from the tumors themselves or from the therapies.
+Aerodigestive cancers also disproportionately affect
+folks who live out in the country,
+or in the cities but with few resources,
+and these folks are my folks.
+
+We need to help each other, and there is much to do.
+
## educator
Harvard Macy Institute faculty, 2018-2020.
Health Care Education 2.0.
-<https://vimbook.org>
+<https://vimbook.org>, 2020-present.
+The Vanderbilt Internal Medicine Handbook
+was started by Mike Neuss, MD/PhD
+in the late 2010s when he was a resident.
+It's an incredible resource,
+primarily envisioned as a physical book
+to keep in your white coat pocket
+for quick, authoritative reference.
+It had a website when I came to Vandy,
+but the UX... left something to be desired.
+I rebuilt it into its current state
+(website and infrastructure only - each section has its own author(s)),
+and help maintain the back end.
+
+Chase Webber is the faculty support, and has been amazing.
+
+It's used globally,
+and one of my goals is to make it easier for smaller,
+particularly international programs to have their own versions
+(I built <https://medical-humanities.org>
+for the certificate program here,
+partially as an exercise in creating more user-friendly tooling,
+and it works well,
+but I haven't been able to integrate those learnings
+back to vimbook.org just yet).
+It uses only free and open-source software,
+and fits comfortably into pretty much any free tier server
+despite being a fairly large book with multimedia,
+but updating the content is just this side
+of too developer-y for broad uptake
+(login to GitHub,
+edit some markdown files,
+figure out how to get the formatting you want, etc.).
+
+What it really needs is funding,
+and a part-time developer with protected time.
## data scientist
-Machine learning and data science approaches to
-diagnosis and prognosis of blood cancers;
-healthcare disparities in hospital medicine;
-predictive modeling of hospital readmissions and length of stay.
[Google Scholar profile](https://scholar.google.com/citations?user=Ng5AgXAAAAAJ)
+*If you are interested data science consulting, [contact me](beauhilton.com/contact).
+Current rate is listed at that link.*
+
+*If you want to see an overview of projects,
+skip the following pontification
+on my identity as a researcher and overall goals
+and go to the sections between the horizontal lines.
+They are in reverse chronological order (roughly),
+newest projects at the top.*
+
+
+My research has morphed over the years,
+as everyone's does,
+but the consistent thread and drive throughout
+has been on coaxing large, messy, complex data
+to tell us a story about ourselves,
+about all of us as societies and neighborhoods
+as well as each one of us individually,
+to empower us to speak our own sequels.
+
+To translate that into buzzwords,
+for your bingo game:
+I'm a data scientist,
+anthropologist,
+and oncologist
+who uses explainable artificial intelligence
+among other techniques
+to diagnose and address healthcare disparities,
+including democratizing personalized medicine
+and pursuing synergies in the
+global academic-industrial complex.
+
+I was trained as an anthropologist,
+where reductionism is an insult,
+at the same time that I was trained as a scientist,
+where reductionism is the central conceit.
+Despite the way I set up that last sentence,
+there is no true conflict,
+as the goal for most scientists and anthropologists is the same:
+to make things at least a little better for someone,
+but hopefully a lot better for everyone.
+Modern anthropology is inherently activist,
+far from crusty sepia-toned image of the staid researcher
+sitting just outside the village campfire furiously scribbling in a notebook,
+and so is modern medical research
+(we all read Tuskegee and are appalled and want to do better,
+though precious few become [Paul Farmer](https://en.wikipedia.org/wiki/Paul_Farmer)).
+
+Data science was an unexpected boon,
+a set of tools that lets me deal with
+staggering complexity
+in a disciplined way,
+to a degree unifying the
+anthropologist's drive to let the data be itself (messy, human)
+with the scientist's drive to simplify.
+
+I became acquainted with using code to model the world
+when I was doing physics research
+(equivalent circuit modeling
+and scanning laser doppler vibrometry
+on a Nigerian-style clay pot drum,
+total hoot,
+I [presented](https://doi.org/10.1121/1.3654998) it
+at the Acoustical Society of America Annual Meeting
+and we published it in
+[JASA](https://doi.org/10.1121/1.4789892)),
+and the research-centric medical school at Cleveland Clinic
+gave me the better part of five years
+and a supportive environment
+to dive in deeper to computer science, machine learning, etc.
+
+Now that I am working towards becoming an independent researcher,
+data science projects that were informed by anthropology
+but had centroids in other disciplines have become
+squarely within the overlap of my personal Venn diagram.
+
+[Information almost wants to be free](https://en.wikipedia.org/wiki/Information_wants_to_be_free),
+and there is now so much of it,
+that a lot can be done for free or at a low cost.
+(I'm take special glee in byproducts,
+"digital waste,"
+some say,
+but there is gold in them there hills -
+[Shigeru Ban](https://en.wikipedia.org/wiki/Shigeru_Ban) is my hero).
+Whenever possible,
+I use free and public data sources,
+free and open-source software,
+and attach permissive licensing to my own code,
+which is generally available at
+my own git repository (link in the navigation at the top of this page)
+as well as on GitHub.
+(I'm not opposed to making money,
+but the way I see it,
+public good (government money) ->
+public good (primary research) ->
+public good (data science using the output from that primary research)).
+
+Though I think of myself as a digital anthropologist,
+I will usually describe myself as a data scientist,
+which is more commonly recognized and not at all inaccurate,
+because it focuses on the tools rather than the subjects or goals.
+
+
+---
+
+write about the abstracts project
+
+---
+
+While at Cleveland Clinic,
+I was one of the founding members of the
+Center for Clinical Artificial Intelligence,
+and its first dedicated analyst.
+We had the delightful opportunity to work with
+a rich dataset from one of the world's largest hospitals,
+focused on predicting the risk of
+readmission (discharging from the hospital and "bouncing back" too soon)
+and extended length of stay.
+We had access to not only health data,
+but socioeconomic data,
+for millions of patients,
+and I further enriched this with census data.
+
+With only an address and a date,
+one can learn about a person's neighborhood
+in incredible detail
+(though not the person themselves -
+the US Census is wise about privacy in the data they publish).
+It turns out that a person's neighborhood
+is a major predictor in their health outcomes,
+as is their insurance provider,
+in addition to a host of health parameters and hospital process clues.
+
+I used interpretable machine learning techniques,
+with a focus on revealing actionable items
+that the patients and medical teams could hope to influence,
+as well as to call out structural issues
+that organizations and governments need to know.
+One of the problems with machine learning
+is that it can only ever restate
+(and in some cases, as it feeds back on itself, more firmly entrench)
+the biases that led to the historical data you fed to it.
+If you design it to show you these biases,
+show you *all* of its biases, explicitly,
+to tell you exactly how much a person's race, ethnicity, gender, and neighborhood
+played a role in its predictions (alongside medical diagnoses and lab values),
+you have transformed an algorithm from a
+potentially destructive tool,
+a heinous thing that pushes hurting people farther down,
+into a tool for positive change.
+If these biases are shown in an easy-to-read visual,
+that patients, clinicians, and administrators can all understand,
+all the better.
+See what it looks like [here](https://doi.org/10.1038/s41746-020-0249-z).
+
+---
+
+Initially, when I was going to be a malignant hematologist
+(I still think it is a beautiful field, but was drawn away to other pastures),
+I wanted to level the playing field for advanced diagnostics.
+A world-class hematopathologist together with a world-class clinician,
+preferably a whole group of these together,
+are required to make certain diagnoses,
+and these only after at least one invasive biopsy.
+What if we could mobilize the rich genetic and phenotypic data
+available in simple blood samples and from the electronic medical record
+to support diagnostics, and, eventually, democratize them?
+Further, what if the answer the machine gives could be not only accurate,
+but interpretable?
+What if we could get the machine to explain itself and its reasoning,
+both as a check against biological implausibility
+(and more insidious problems such as systemic racism),
+and to reveal more areas for research?
+What if a high resolution bone marrow biopsy image
+could be read in moments by a smart phone in
+rural Arkansas/Kandahar/Mogadishu/Kushalnagar/etc.,
+instead of having to be shipped to
+one of a handful of academic centers while the patient waits,
+still sick, for an answer?
+We made [some](https://doi.org/10.1182/blood-2019-126967)
+[progress](https://doi.org/10.1182/bloodadvances.2021004755),
+but these problems remain largely unsolved.
+
+---
+
+
## internal links
diff --git a/site/posts/history-egc.md b/site/posts/history-egc.md
@@ -19,9 +19,13 @@ I'm not interested in every small technical advance,
only major firsts and practice-changing updates).
As a side note, it would be cool if [HemOnc.org](hemonc.org) had
-tables of all drug approvals
-(with dates and indications)
+tables (*a* table? for comparative work?)
+of all oncologic drug approvals, with dates and indications,
for every global approval agency.
+Maybe with a link to the trial that led to each approval?
+(It's not always 1:1 between trial:approval,
+but would be nice to know for the majority of cases
+where that pattern holds).
It's a huge task,
but would be so useful for clinicians, researchers, and investors.
I'm amazed nobody has done this yet,
@@ -69,7 +73,7 @@ please contact me.
<tr>
<td>0 BCE</td>
<td>First description of EC, written in China.</td>
- <td>Epidemiologic links to EC described between alcohol, hot drinks, and advanced age</td>
+ <td>Epidemiologic links to EC described between alcohol, hot drinks, and advanced age.</td>
</tr>
<tr>
<td>131-200</td>
@@ -84,7 +88,7 @@ please contact me.
<tr>
<td>1543</td>
<td>First detailed illustrations and descriptions of the upper gastrointestinal tract.</td>
- <td>Vesalius, De Humanis Corporis Fabrica</td>
+ <td>Vesalius, <i>De Humanis Corporis Fabrica</i></td>
</tr>
<tr>
<td>1690</td>
@@ -94,7 +98,7 @@ please contact me.
<tr>
<td>1770</td>
<td>First written Western hypothesis of the epidemiologic link between alcohol and EC.</td>
- <td>Ernst Gottfried Gyser, Medical inaugural dissertation on the fatal hunger, caused by callous narrowing of the esophagus, with phenomena worthy of attention which are detected in certain abdominal viscera.</td>
+ <td>Ernst Gottfried Gyser, <i>Medical inaugural dissertation on the fatal hunger, caused by callous narrowing of the esophagus, with phenomena worthy of attention which are detected in certain abdominal viscera.</i></td>
</tr>
<tr>
<td>1857</td>
