Data Driven Doc: The Ampulla of Vater

shutterstock_262687568

The Ampulla of Vater sounds like something straight out of Hogwarts, but it’s a special vase we all carry within our gut. Digestive juices from the bile ducts and the pancreas pool together in the ampulla to meet the food coming into the small intestine (duodenum) from the stomach in this action-packed area of the GI tract.

Naturally, even small tumors in and around the ampulla cause major problems. Blocking bile ducts causes a quick yellowing of the skin and eyes. When the ampulla is blocked and the juices do not flow freely, the pancreas, the liver and the stomach all start to back up.

Ms. Khan had been living in South Korea for years. Recently, her skin had started to get a jaundiced look, and she wondered if it was something in her diet catching up to her liver. The gastroenterologists at South Koreas premier hospital unfortunately diagnosed her with a periampullary mass in the duodenum, and the surgeons promptly completed a Whipple procedure – named after the surgeon who devised the elaborate surgery to remove the head of the pancreas, common bile duct and duodenum from a patient.

Her surgery was a success! The tumor was completely removed. But three nodes near the duodenum were positive. Mr. Khan wanted to ensure that the cancer didn’t come back or spread.

Experience matters. Indian oncologists see a large number of young patients with advanced GI tumors. Gallbladder and ampullary malignancies appear to affect Indians more frequently, younger and at more advanced stages.

Experience matters.

Mr. Khan reached out to Navya for a review of his wife’s case. Promptly, the Navya Expert System, Vyas matched her case with similar patients seen before. Experience matters again- not just for humans.

Confronted with a duodenal periampullary cancer, Vyas looked up data related to duodenal/intestinal malignancies and recommended fluorouracil based therapies. The structured summary was quickly compiled and sent to an Indian medical expert in London affiliated with Tata Memorial Center for review.

The expert quickly responded, correcting Vyas. Treating the tumor as periampullary rather than as dudodenal/intestinal made more sense, said the expert. The treatment recommended was a two-drug regimen recently shown to increase survival in pancreatic cancer at ASCO 2016. The periampullary arm of the trial was still recruiting, but the true experts were treating ahead of the data, as always.

The patient report reached South Korea within 13 hours of Mr. Khan reaching out to Navya. Needless to say, Mr. Khan’s family was grateful and impressed.

Vyas learned something new from the case. The experts quick review and feedback pointed Vyas to emphasize periampullary origin over intestinal origin of cancers while looking for treatment options. Vyas integrated the knowledge it already had about the ESPAC4 trial from ASCO’s conference in 2016 for pancreatic cancers in a new manner into its experience engine for ampullary tumors.

Experience matters. For patients, experience is the bedrock on which they extend their faith to a physician. For Vyas, the wealth of experience of experts and patients at Tata Memorial Center give it an enormous head start in deciphering complex cases. The opportunity to learn from every patient in the engine with expert feedback makes Vyas an enormously rich and accurate predictor of decisions. Vyas starts out with a bedrock of evidence and guidelines. And with every case it sees, it gets stronger and better at guiding patients towards the best treatments.

The experience of seeing Vyas learn is truly magical. Some days, it feels like something out of Hogwarts.

-Dr. Naresh Ramarajan

Online Expert Opinion: navyanetwork.com/tmh

Tata Trusts: tatatrusts.org

Tata Memorial Center: tmc.gov.in

Navya: navyanetwork.com

 

Evidence

Navya Blog post image 1

Today I was reminded that evidence matters.   Evidence is the premise of Navya.  It is where we started.   Why we started.  We added on Experience, Experts, Patient Preference, and always knew that Guidelines are a sum total of many things but not enough to make a patient-specific decision.  With so much noise about so many systems and so many sources of information, (from structured guidelines to unstructured patient blogs and doctor’s notes and specific institution practices), all away from the core of Evidence, (clinical trial data), I began to wonder whether our premise was not what many would value.  (What a convoluted sentence construction – pretty similar to the obscurity of that thought).  Evidence matters.  Experts (or should I say mother of all experts…!) at Tata Memorial Centre are singularly focused on how an evidence based system can empower their decisions, above and beyond what their experience and standard guidelines can already do.  That, is the hallmark of expertise.  The definition.  An evidence based expert decision.

When I was asked to momentarily scrap everything else and home in on the evidence based results of the Navya Expert System, and the informatics that enables it, I knew that my system is in the hands of the right critiques and the perfect users who will use it to empower their patients.  When I was reminded that it is the Navya Evidence Engine that is the heart and core of what an expert desires, I was reassured, reaffirmed, reignited to remain focused on what we set out to do:  use evidence to make treatment decisions that are uniquely applicable to an individual patient.

Thank you, Dr. G and Dr. B for your constant push and faith in evidence based expert decision making; and for the opportunity, the privilege, to build Navya with you.

 

Unstructured data versus structured data – what is better for clinical decision making, in cancer?

12112187_1657595951146623_5360463258418917956_n

A lot of talk has been ongoing on unstructured data – as in this Facebook note, your blog post, a patient’s question on a support group, a doctor’s response on a newsgroup, a PDF scan copy of your aunt’s prescription, a journal article, its rebuttal, and you get the idea. There clearly is a lot of information pertaining to health and it may be an overkill, when it comes to decision making. Ask a cancer expert. They trust raw data, primary data from clinical trials that are high quality, randomized control. They trust their own experience treating large volumes of patients firsthand, observing the toxicities and managing the comorbidities (other health conditions like a weak heart or compromised liver) that may complicate a cancer treatment. And ultimately, data is only valuable when it is credible and lends itself to crisp, crystal clear, decision making: i.e. 1) sources of data matter (a randomized controlled clinical trial versus many doctors’ notes… or outcomes of patients at an expert cancer center versus self reported comments by patients on an online forum), and 2) structuring data in a way that doctors think from the get go, allows valuable information to be retrieved for decision making.

Hence, I am a fan of structuring data, which in and of itself is a complex challenge (Navya has developed an ontology for decision making, cancer by cancer, and that ontology is derived from the credible sources of data itself – like clinical trials and international guidelines and the handful of true experts themselves), rather than spinning cycles (computational power, manual processes, resources in time and money), on parsing mountains and mountains of any and all health related data and then trying very hard to derive accurate, usable, precise meaning from it for clinical decision making.

When it comes to cancer care, start with structured credible data and focus (spin wheels if you must) on analyzing it for decision making.