Year: 2018

Posted on by

Why Radiologists Should Consciously Love Subconscious Learning

subconscious learning

Given the opportunity, many of you would jump at the chance to read a new exciting imaging presentation of sarcoidosis or esthesioneuroblastoma. Sounds sexy, right? And I am the first to admit those disease entities seem attractive to me, something entirely different from the usual. But what about the seventeenth case of questionable overlapping shadows from soft tissue artifact versus pulmonary parenchymal disease at the left base on chest film? I mean, who cares about shadows at the bottom of the film, huh? We see them all the time. Or how about the 112th case of seeing a left adrenal gland that happens to have a medial limb that appears a little bit more concave than most others? I mean, this may not even register in our forethoughts as anything. However, I would argue that this second form of knowledge, what I like to call subconscious learning, is just as important, if not more so, than the sexy conscious education we all love to talk about every day- those cases of sarcoidosis and esthesioneuroblastoma. Nevertheless, many radiologist residents poo-poo, the second form of learning. I mean, why even bother with that other stuff when we can talk about that great case of esthesioneuroblastoma?

The Reality Of The Situation

Unfortunately, our reality as radiologists does not match the sexy image of a diagnostician frequently making unusual diagnoses. Instead, first and foremost, we are purveyors of normal findings that we register unconsciously every day.

For example, on any day that we may read a hundred chest films, only a small percentage, maybe 5 percent or less, will have these sexy undercurrents. The majority will have plain old garden variety mundane findings. But, it’s these common findings that we all need to either ignore or understand. If not, you will go down the tubes at your peril.

Why Is Subconscious Learning More Important?

So, why do I believe making these common subconscious findings that we gloss over during readout is more critical? Well, in reality, those findings that we see every day impact patient care more. Knowing whether that shadow at the lung base is significant on any given day may affect maybe 2 or 3 patients. On the other hand, that case of sarcoidosis, you may see a few times a month or year, or that case of esthesioneuroblastoma, you may see once or twice in a career (unless, of course, you work at an esthesioneuroblastoma center of excellence!)

Furthermore, overcalling findings can cause more harm to patients than you might think at first glance. For example, think about that patient with the adrenal gland with slightly increased concavity. You may send this patient to an MRI for an adrenal workup without knowing that this finding is within the normal range. And, of course, you find a nonspecific liver lesion. And guess what? Now you have to do a hemangioma scan. And the hemangioma scan comes back negative. The clinician then orders a biopsy, and the patient develops a subcapsular hematoma. And the complications roll on in “ad nauseum” at a cost to the patient and the health care system.

How Do We Increase Our Subconscious Learning?

I’ve said it before, and I will repeat it because it is that important. We have never found a substitute for sitting down (or standing up) and reading many films. You can only say what is within the normal range after seeing 10,000 livers, 85,000 heart shadows, and 12,000 gallbladders. And we accomplish that by registering these findings over time in our mental databank. No, it’s not glamorous, and our conscious brain may not realize it. But it works.

Conclusion

So, the next time you sit next to your radiology attending, think twice before you say that you will hit the books to increase your understanding of radiology. Truthfully, instead, you accomplish just as much by looking at your next case even though it is “nothing special.” No, you may not realize that you are learning anything new. And, no, it may not prepare you as much for the boards. But, over time, your subconscious learning will eventually win out. It is not only your sexy conscious knowledge but also your databank of common unconscious findings that will allow you to become the radiologist you want to be!

Posted on by

Knowing Normal Variants: Experience Vs. Reading Books in Radiology (Doximity Article)

normal variants

A while back, I was looking at a stream of comments on one of the social media outlets. And, as the conversation flowed between residents and attendings, I noticed one significant distinction. The attendings tended to emphasize seeing thousands of cases to understand normal variants. While at the same time, the residents talked much more about books and case review series.

Within my residency program, I also notice a similar discrepancy between the resident and faculty opinions on learning normal variants. Therefore, since both parties vary widely on this topic, this would be the perfect forum to discuss the conflict. Here we go!

How Can You Best Learn Normal In Radiology?

To understand all of the normal variants in the world, you would have to practice radiology for hundreds of years. And as much as I love “thorough” books like Keats (linked to my Amazon affiliate!), they do not cover even half of the normal findings on plain film that you can easily confuse with pathology. Also, Keats does not include CT, ultrasound, MRI, mammography, or nuclear medicine. Since you cannot find all the variants in the literature, reading lots of books alone, in my opinion, does not enable you to learn enough to become proficient.

Additionally, the information inside rarely sticks if you are reading a book without context. If I were to go through the entire Keats book without any real-life images, I probably would not remember all that much.

This point brings me back to the essence of this article. How do you best learn normals? To maximize stickiness, I believe looking at lots of real-time cases within books, like Keats at your side, and having an attending sit next to you allows you to remember and understand normal variants the best. Context is key.

Reading Lots Of Films: Painful But Necessary?

In addition, it is not just about knowing the normals. You also need to read scores of films rapidly to identify the normal variants appropriately. There is no room to perseverate forever on every case you read. Rapid assessment of normals has become critical to thriving in a bustling private practice.

You cannot practice radiology without reading tons of cases with normal variants unless you find yourself shielded from many films within a large academic center or decide on an alternative career path. So, we recognize that you need to start reading early to produce insightful reports that differentiate normal as an attending. And, what better place than residency to learn these skills?

To that end, you may not believe it, but most program directors do not derive pleasure in causing undue pain to the residents by saying you need to spend “x” hours on a rotation. Instead, we seek to make sure that in addition to reading books, you also read enough studies to identify normal versus abnormal sufficiently. We want nothing more than to create an upstanding/quality radiologist.

What Is The Correct Balance To Develop A Feel For Normal Variants?

The perfect balance is difficult to figure out; we need to tweak it for the individual trainee and program. But, I would recommend spending more time at work with your faculty instead of dedicating too much time to study books.

Moreover, the government pays for you to perform clinical services. It’s hard to justify reading books when Medicare pays you to work. And just as importantly, nighttime after work tends to be the best time to reinforce your day’s learning.

The Bottom Line

Remember, you can always look at films by yourself later in your career or while on call. But, you will not always have the advantage of a readout with an experienced radiologist. So, I have to side with the faculty in this situation. Granted, I am biased, but they make the best point!

_____________________________________________________________________

Check out the original article at the following Doximity link!!!

https://opmed.doximity.com/articles/knowing-normal-experience-vs-reading-books-in-radiology

Posted on by

2018-2019 More Competitive For Radiology? A Midyear Perspective

At our program, we have completed a little more than half the radiology residency interviews through this season so far. And in the midst of interview season, many of you, applicants and radiologists alike, are wondering has radiology become more competitive this year compared to years past? To answer that question, I will analyze the current facts and give you a preliminary conclusion. And then, I will provide you with a little summary of what to do with all this information.

The Hard Evidence

So, which individual pieces of evidence highly suggest increasing competitiveness? First and foremost, we need to look at board scores. Overall, applicants to our institution have had a significant increase in the USMLE board scores year over year. Based on the current candidates, I would say overall, USMLE scores have increased by 5 to 10 points compared to the previous year.

What else? Our institution looks at the Caribbean, American Osteopathic, and American Allopathic medical students. Noticeably, when the numbers of American Allopathic and Osteopathic applicants increase compared the Caribbean applicants, that is a hard sign that the competitiveness of our program has climbed. We see exactly that.

The Soft Evidence 

This year, the applicants have more numerous and exciting extracurricular activities. Typically, I notice this trend when the applicant pool expands. Likewise, we tend to interview more of these applicants instead of the bread-and-butter type. I believe we are following this pattern.

Moreover, applicants have stated that they have heard that the landscape has become more competitive. To support this theory, on interviews, many have indicated that they understand more than usual are applying to radiology from their medical school.

Interestingly, many applicants have explicitly stated that they are no longer worried about artificial intelligence (AI) taking over the world (or the radiologist’s job!). A few years back, many more interviewees had expressed this fear. I believe that the more accurate information about how AI will function as a tool to assist the radiologist has worked its way to the applicants versus the message of replacing radiologists from Silicon Valley. 

And finally/most propitiously, interviewees are well aware of the improved job market in radiology. Usually, the applicants follow the money!

So What Does More Competitive Mean For Applicants This Year?

OK. What to do about it is the critical point. We are pretty sure that applications have become very competitive. But, that must mean something for the applicant, right?

Well, yes. I am going to make a short list of the critical tasks that you should complete. For many of you, make sure that you rank enough programs on the list. Occasionally, some of you may feel that you are likely to match at your first few choices and that’s it. So, some folks will make a short list. Instead, make sure to rank a few more than you may think you need.

Also, you should write thank you letters to all programs of interest. Some programs will use them as a way to bump up your application in the rank list a tad. It does show interest in the program. And, some use it as a marker of a possible good match. It can make the smallest difference between ranking and not ranking. 

Then, for some of you, make sure to take a second look at the programs that interest you, if you can. Like the thank-you letter, coming back for a second look expresses that you are serious about a program. Occasionally, it can help your chances.

Lastly, be prepared for the possibility of having to scramble in the SOAP. What will you do if you do not match? You will need to collect your thoughts and get it to together rapidly if the process does not go the way you wanted.

Are you going to be willing to do a prelim year in medicine or surgery and reapply again next year? Or, are you going to try to match in a different specialty entirely. You should think about these possibilities just in case it does not work out.

Summary

So, there you have it, a review of my thoughts about the competitive environment for the radiology residency applications of 2018-2019. My final piece of advice- make sure to remain humble throughout this process. Unfortunately, as much as we do not like to admit, there is an element of chance in the application. Therefore all applicants should hope for the best, but plan for any eventuality. Good luck!

Posted on by

I Want No Patient Contact And A High Salary- Which Fellowship Should I Choose?

high salary

Question About High Salary/Patient Contact

Dr. Julius, I read the article you wrote last year on how to choose a fellowship. Have you any new insights since then? Also, could you help me narrow down my specialty?

What I am looking for: a very high salary, independence, being able to work from home would be a luxury, minimal patient contact, be a specialist.

My background: I finished two years of general surgery and switched to radiology. R1.

Thanks for starting this website,

Unsure Resident

Answer:

Hi,

I’m glad you have developed specific criteria for what you require in a fellowship. Often, that can be the hardest part. Of course, I wouldn’t tell the folks interviewing you that you would want minimal patient contact unless you know the interviewers well. Radiology 3.0 has become part of the vocabulary of most academic departments. And that implies some patient care — just a word of warning. But, between you and me (and the wall), we both know that not all subspecialties carry the same amount of patient interaction! So, which specialties have less contact? Most of the pure imaging subspecialties are without procedures. MSK or Neuro would be specialties more likely to have less patient contact. 

High Salary Issue

Returning to the main question, which fellowship should you choose? Let’s start with the first criterion, a very high salary. Unfortunately, compensation is more tied to the number of reads and the location where you work than the type of fellowship you do. And, every year, the benefits of any given modality can change. For example, at one point, interventional radiology was the highest-paying specialty per procedure. Now, it generally pays less than most others. Currently, MRI probably reimburses better than most other studies. However, you would be chasing a moving target if I were to tell you that it would remain the same.

Independence Issue

Regarding independence, you ultimately rely on your referrers and patients, so you are never truly independent. But, if you want to become a group of 1, something like teleradiology would enable you to get your business paid with a 1099 form instead of a W-2. Also, teleradiology would allow you to interpret films as much or as little as you want. So, theoretically, you can “create” your desired high salary if you’re going to read like crazy! Additionally, teleradiology would naturally allow you to work from home. 

Summary

So, there you have it. Based on your criteria, a possibility would be a teleradiologist specializing in MRIs such as MSK, body MRI, or neuro MRI. However, the two things that you failed to tell me were whether you wanted to work late hours or what procedures you enjoyed the most. You should probably consider that in this “equation” as well. Let me know what you think!

Regards,

Barry Julius, MD

 

 

Posted on by

Calling For Help- A Sign Of Weakness Or Strength?

help

Back in the day (in the dark ages!), when I began taking call years ago, each radiology faculty member brought home the beeper on occasion to cover any resident issues from home. Meanwhile, the resident would give independent reads overnight without the attending help. Imagine no real nighthawk or night-attending coverage whatsoever!

Rarely, if ever, would a resident dial the attending (god forbid!) for some help. Moreover, if the resident spoke to the faculty member past 10 PM, he would place him on a blackball list. (Kind of like the McCarthy era) In essence, this resident’s name would ring throughout the department as “incompetent” and “childish” for having to make the phone call for the next several years.

Nowadays, at least at my program (and hopefully at most), the faculty members encourage phone calls at nighttime. If an event significantly affects the department, I, as a faculty member and associate program director, would rather hear about it at night than have a disaster in the morning. And that goes for all the radiologists in the department. Today, I consider the ability to know when to call an attending a sign of significant strength. But is there something useful about the old-fashioned approach? Or was it pure hazing, no more, no less?

Strengths Of Discouraging Nighttime Calls For Help (The Blackball Era)

Were there any net positives of feeling that you could not call your superiors for fear of a severe backlash? Well, I would like to say that it was all bad. But in reality, several net positives overwhelmed many of the negatives. And unfortunately, newer residents lose out on some of these experiences.

First, once you start having backups, whether a nighthawk, in-house attendings, or senior residents, you lose the independence of judgment. No longer do you worry about missing findings. Instead, you know an attending will eventually find it later.

Moreover, knowing you have a backup makes call a less practical learning experience. Knowing that your decision will make the difference between patient injury and a good outcome, you will treat the case differently.

In that same vein, the learning experience of call was much more intense. One of my attendings used to say, “pressure builds diamonds.” Well, I believe that statement contains some truth. Those evenings I spent making the tough decisions alone stuck with me for years. And I am thankful for that.

Finally, you developed a camaraderie with your fellow residents in other disciplines who were in the same boat. These connections carried through for the remainder of the residency. Today, it’s not quite the same. Each department in the hospital has its backup system. And in a sense, we rely on each other slightly less.

Weaknesses Of Discouraging Nighttime Calls For Help (The Blackball Era)

First and foremost, you can see why a junior resident commanding a whole radiology department cannot lead to the best patient care outcomes. And, rightfully so. I would rather have a seasoned attending reading my films than a junior resident.

That premise leads to the next issue, delays in patient management. ER attendings were less likely to allow the resident to make a final disposition. Often, they would keep the patient in the emergency department to wait for a “final read.” For instance, if a resident reads a case without backup, patients sometimes slip through the cracks. Based on an occasional discrepant radiologist read, an ER attending may occasionally fail to work up the patient appropriately. Or, the ER attending would rarely send patients with appendicitis or ectopic pregnancies home based on a faulty resident read. So therefore, some ER attendings would choose to delay management until the attending radiologist returns.

And finally, does a resident that seeks help from an attending deserve placement on a blacklist? Probably not. It is an unfair practice. I could easily compare it to a fraternity that requires its new members to guzzle a case of beer. It doesn’t make it right.

Preponderance of Evidence

So, which way serves the radiology resident, the patients, and the institution the best? Based on my arguments for both sides, this call is not as easy to make as you might think. However, as much as I learned from being discouraged from calling my superiors, I believe that patient care should take priority. We all took some form of the Hippocratic oath. And therefore, we should try to lower patient morbidity to the best of our ability. Also, decreasing the time spent in the ER improves patient outcomes. Even though today’s residents lose some of the independence we had not too long ago, trainees and faculty have to think of patients first.

So, call your attendings for help if you need it. And, faculty, please treat your residents respectfully after they call. We no longer live in the dark ages. Calling your attending is appropriate for the best patient care. And patient care should come first!

Posted on by

Stuck In Pathology- Get Me Out!

pathology

Question About Changing From Pathology:

Hello,

I am a pathology intern halfway through the year. Now, I am confident that I have made a terrible mistake. Radiology was my dream residency throughout medical school. However, due to my spouse and I entering the couple’s match, I convinced myself that pathology was a better strategic option. I deeply regret not following my interests. And now, I feel that I may be trapped in this field forever, wishing I had stayed in my first course. I have no academic limitations that would have prevented me from being accepted into radiology had I applied. My question for you: Would switching from pathology to radiology be possible? And if so, how would you recommend I approach this difficult situation? Thank you very much for your time and advice.

Regards,

Stuck in Pathology

Answer:

It is still possible to switch to radiology. All is not lost. But, at least, it will involve an extra couple of years of residency. Unfortunately, the ACGME has changed the rules for what counts as a clinical year for radiology residency. At one time, you could apply pathology toward the “clinical year.” Per the ACGME, you must take another internship year in preliminary medicine, preliminary surgery, ob-gyn, emergency medicine, neurology, or a transitional clinical year. The biggest problem you may encounter, assuming that you have not applied this year already, is that you will have to wait until the following year to apply to prelim medicine and radiology. That will give you two years in pathology. When you take that third year of preliminary medicine, you will already have three years of residency before radiology residency. Due to Medicare funding issues, some programs may not have funding for your entire residency. Some programs will care about that more than others. But it shouldn’t prevent you from applying.

The Good News

However, you have a spot in a pathology program right now. So, if you applied for both a clinical year and a radiology slot simultaneously and didn’t get into a program, you would still have your current pathology residency position available as a backup. So, if you still desire radiology, it is worth a try regardless of the “funding issues.” It’s a bit of a longer path for you to get into a radiology residency, but certainly not impossible.

Also, I would recommend getting to know the radiology department faculty at your current institution by completing an elective rotation or stopping by to talk to the program directors. If they like you, that may also help to get you an interview and recommendations for a radiology residency. Knowing someone personally is always better than a blind bid for a residency slot.

Good luck,

Barry Julius, MD

Posted on by

Do Applicant Photographs Belong On The NRMP Residency Application?

Do you believe in the common cliché, “A picture is worth a thousand words?” And, are you interested in how to apply it to the interview process? Then, take a look at the recent paper in Academic Medicine entitled The Ethical and Legal Conundrum Posed by Requesting Residency Applicants to Submit Photographs of Themselves, and the Medscape article of an interview with the same author of this study in an article called Are Residency Application Photos Used for Discrimination?   Both pieces made lots of interesting points about the use of photographs for interviewing residents. However, I found the discussion in both of these articles to be a bit unsettling. And, let me show you why.

Well, take a look at the following quote as one of the final statements in the interview as a summary for the articles, “The photograph does not provide useful information that is necessary for selecting qualified candidates. Unless there’s a compelling argument for why you need a photograph, which so far no one has brought to me, I think it is unnecessary. Everyone I’ve shown the article to has agreed with our point of view. I am concerned that this is a possibly illegal practice, that it can cause people to be discriminated against, and that it is unfair.”

What The Articles Got Right

Let’s step back for a moment and think about this statement. At first glance, I initially agreed with the concept behind the article. Programs should never use a photograph to prescreen candidates. For instance, let’s say that one of the screeners in a program happened to hate nose rings. And, the image of an applicant showed her wearing a nose ring. Then, we might have excluded this applicant from the interview pool not based on credentials, but rather a nose ring on a photograph.  It could theoretically work that same way for race or ethnicity. That should never happen. I get it.

Where The Articles Went Too Far

But, let’s take it to the next level. Once applicants have made it through the prescreening process and have arrived at our site for an interview, pictures can be beneficial to the applicant and the process. We’ve already seen the candidate. And, every time I look at a picture of the applicant, it jogs my memory about the person, the conversation, and the time. Often, the picture saves the day since so many interviews on a busy day can blur the lines between the candidates. Why would you want to get rid of such a tool?

Furthermore, we all have eyes and faces. You can’t ask all applicants to wear masks to an interview. Likewise, you cannot blindfold all the interviewers. And, if the picture is not biased enough, what about our voices? I mean everyone has a distinct accent. Uh oh, now applicants must wear sound mufflers to make sure that we cannot determine their identities.  And, what about our clothes? Our clothes can give away our culture and attitudes. Why don’t we have all applicants arrive at our interviews wearing the same required outfit? I think you get the point, but you can take anti-bias precautions to an extreme that no longer makes sense. And, that’s where both of these articles went.

My Final Opinion About Applicant Photographs

Applicant photographs do not belong in the prescreening process. We should choose who we interview based on merit alone. Perhaps, we should look at these pictures only after we have selected the candidate for an interview.

However, I believe these papers over-sanitize the interviewing process and residency program use of photographs. We are not perfect in making decisions about our candidates. And, we all have our innate biases. But, we should not erase the interview pictures from the applicant’s record just because it may affect our judgment. We need our judgment to decide who we should choose for our programs. Let’s not take this anti-bias point too far!

Posted on by

Does Artificial Intelligence Spell The End For Radiology?

artificial intelligence

Question About Artificial Intelligence:

Greetings, could you elaborate on these words ”(Artificial intelligence) will profoundly affect all of our careers, for better or FOR WORSE” and ”have more to gain and MORE TO LOSE”.

I am asking because, in the above text, you’ve written only about the good things about AI, while with these words, you’re also implying bad things about it, but I, as a reader, don’t know about them as you haven’t listed them.

I am a doctor from Europe whose first specialty choice is radiology, but this artificial intelligence surge is making me think twice about it. Everything I read, including your piece, is a 2-way street ala. ”AI is great, but you must adapt to it.”. The end. Could somebody please tell me HOW I will have to adapt and what the BAD things about AI in the radiology field are? It’s freaking me out! Radiology, as it is now, is a fantastic specialty, but I don’t want to be jobless and incompetent 10,15,20 years from now. It’s a life’s decision, and I have exactly ten days to decide!!

Thanks,

Worried Applicant

 ————————————————————–

Answer:

You are not alone in worrying about the future of radiology and AI. However, after attending the RSNA meeting and talking to colleagues, AI will not take over a radiologist’s job entirely for a long time (if ever). That aside, AI technology may allow fewer radiologists to do the same amount of work that we do right now. Improving triage, artifacts, and integration will make the radiologist’s job easier.

AI Will Not Take Over The World!

Why do I say this and not worry about AI taking over the world? First, the ability of an algorithm to detect something is only as good as the programmer, the number of data points, and the quality of the data. However, programmers have not optimized the algorithms. The data points are too few. And the quality of the data is not uniform. So, I don’t believe that will happen for many, many years from now.

Moreover, deep learning algorithms still have difficulty distinguishing simple solitary findings on a plain film, such as pneumothorax (often mistaken for chest tubes), let alone all the findings on a chest film. Therefore, I don’t believe the interpreting programs can independently function.

More importantly, companies will not want to accept the consequences of the liability of missing findings on films that go unchecked by a radiologist. So, I see AI as more of a team effort instead of a radical upheaval of all radiologist’s jobs. Let’s spread the liability risk!

What Is The Real Downside Of AI?

With the advent of any new technology, we will see our fair share of crashes, bugs, and technical problems. So, I believe that these would be the main downside. But I think the downside is reasonably limited overall. My advice- if you like radiology, you should go for it. If I were deciding on a profession today, I would not let my fears of AI dissuade me from choosing the radiological field.

My two cents,

Barry Julius, MD

Posted on by

RSNA 2018 Meeting: What Residents Should Expect From Artificial Intelligence?

By far, the RSNA is the largest and most publicized radiology meeting of the year. But, I usually attend other meetings instead because so much goes on at once at the RSNA that it is next to impossible to concentrate on one area. Moreover, to get from one side of the Mccormick conference center to the other takes almost 10-15 minutes!

In any case, for the first time in eight years, I bit the bullet and decided to attend the RSNA meeting this year. Partly, I needed additional CME credits, but also I was not able to participate in the SNMMI meeting due to timing. But, I am delighted that I did. Why? It allowed me to grasp the most current themes in radiology that exist today. And, for residents, in particular, I thought it was critical to share with all of you what may be coming down the pike.

To start with, if I had to give one overarching theme from the conference, I would have to say that the central idea was artificial intelligence. Some of these revelations about artificial intelligence were not all that critical. But, others will play an enormous role in your careers down the road. So, I will try to emphasize those items from the conference that will undoubtedly influence your career. And, I will briefly talk about a few issues that the AI companies and academic sorts may overhype.

Strong AI Career Influences

Integration

When you pull up your PACS system to read cases ten or twenty years down the road, no longer will you have to pull up your history, labs, pathology, priors, EHR, and films separately. Instead, all hospitals and outpatient offices will have software and systems that will allow you to sort through all the information at once. Right now, some institutions are more integrated than others. For most of you, lack of integration this will become a relic of the past. Walking through the technical exhibits, you could see many solutions today that will allow the radiologists of the future to read films with all the clinical information at your fingertips.

Triage

Imagine having a helper sort through films to determine which ones you should look at first and others that can wait a bit. Well, now they have multiple software packages that use deep learning to create work lists that make sense. And other programs try to detect STAT findings such as brain bleeds to make sure that radiologists read these studies first. Finally, other software programs can make sure that the correct radiologists are reading the appropriate studies. Right now, most practices do not have the staff to scrutinize cases before dictation. So, all these AI solutions, will allow more efficient and appropriate reading of STAT and essential studies.

Reducing noise

Having stopped at numerous vendors, I noticed that most of the big ones were touting deep learning algorithms to increase the quality of images. What do I mean by that? Many had sophisticated programs that mitigated artifacts and increased conspicuity of lesions and vessels. Some allowed you to image patients with significantly lower contrast dosage to prevent acute renal failure. Motion artifact on a CT scan or PET-CT scan may become a rarity. The future in this arena is now!

Increasing Reading Efficiency And Quality

Right now, some companies have created Computer-Aided Detection (CAD) packages that assist the radiologist in reading images. At the meeting, these solutions seemed to emphasize lung nodules and mammography.  I would expect some improvement over the coming years in these imaging modalities. And, I think we will begin to see other imaging modalities that utilize CAD. CAD will continue to reduce the time and effort that goes into reading studies.

One of the new types of CAD that I thought would be of help to the average radiologist was a bone age reader. It’s the perfect place for AI to begin because medical liability is a bit lower.

Additionally, new software packages can integrate CAD functions into the current dictation and PACS systems. We will see a lot more integration to improve radiologist reading efficiency.

Weaker AI Career Influences

Radiology 3.0

As much as the RSNA academics liked to state that we will no longer be image-centric and instead become patient-centric, I don’t see many powerful economic and political factors to drive the current radiology business in that direction. Currently, I am a bit skeptical about the rate of progress toward that goal. I have a feeling we will still have considerable time pressures to get tons of cases out rapidly.  Until fee for service no longer becomes relevant, radiologists will not have the time to see each patient after reading their chest film. It’s just not realistic. However, we will have more information at our fingertips about our patients’ care to make better reports and decisions. But seeing a patient after reading each film is a pipe dream.

Driving Direct Patient Care

In one of the plenary sessions, a computer scientist gave a whole lecture on improving metrics such as hand washing and patient falls with artificial intelligence. She discussed placing sensors all around the hospital to create a virtual environment that can sense these events to improve patient morbidity and mortality. While I agree that we should try to improve these issues since they cause harm to patients, the lecturer did not convince me that hospitals and institutions are ready to spend the money and time to accomplish these goals. For the foreseeable future, I see too many financial and legal hurdles to extrapolate these ideas to a larger scale.

Artificial Intelligence And The RSNA- Final Take Home Messages

Artificial intelligence will have a profound effect upon all of our careers, for better or for worse. But, the younger generations of radiologists have more to gain and more to lose. Therefore, for residents, especially, it is critical to follow the developments within the field. And, the RSNA meeting is just the right place to get a sense of AI and your future. If you have an opportunity to attend a meeting like the RSNA, it is well worth it. Take advantage of the event and learn about how the main themes will affect your career!

Posted on by

The Dean’s Letter Dilemma: A Rogue Evaluation

dean's letter

Within the application, few sources give as much information to the residency application committees as the Dean’s Letter. Yet, the Dean’s Letter also exposes a large crack in our system for deciding upon applicants. And today, I will talk about one of them- the rogue evaluation.

Here is an example of the sort of rotations comments that you may come across in a Deans Letter with a rogue evaluation:

Evaluations

Surgery- A, Excellent. Received glowing evaluations from all residents and attendings.

Psychiatry- A, Fantastic student, Able to empathize well with patients, acts as an intern (above his level of training!)

Family Medicine- A, Actively participated and gave excellent concise, and helpful histories

Radiology- A. Incredible eye, Great talk on Histiocytosis X/eosinophilic granuloma.

Medicine- A-, Worked hard, good scores on the shelf exam.

Ob/Gyn- B, Unable to do an appropriate pelvic exam, forgot to take a good history on several patients, and would not scrub in on many of the cases because he didn’t think it was necessary.

The Dilemma

Whoa. Look at that last rotation. Notice how it does not fit in with all the others. So, what are the possibilities behind the poor Ob/Gyn Deans Letter evaluation? What do admission committees do with this information? And, how does a Deans letter such as this one affect the applicant?

Why Did This Student Get Such A Horrible OB/GYN Evaluation?

Well, it could have been the medical student’s first rotation. Sometimes, in this situation, you have a medical student who initially had no clue how clinical rotations worked and just messed up. Or, maybe, one resident or attending had a vendetta against this medical student and wanted to stick it to him. And finally, perhaps, this medical student indeed did not function well in a rotation that did not interest him.

Regardless of the cause, this resident has been screwed (for lack of a better term!). What do you do when you have scores of applications without a significant blemish, and then you run into this one rogue Deans Letter? Well, you run it by your team, the admissions committee!

The Next Step: The Admissions Committee

So, how does the Admissions Committee deal with a Deans letter like this? And let’s assume that all the other factors, such as board scores, recommendations, personal statements, and extracurricular activities, were just fine.

Well, you can probably imagine the discussions at an admissions committee meeting. First, half the committee says we should give this candidate a shot at an interview because everything else on the applications sounded OK. And the other half wants to dump this application since it has a blemish. Moreover, this year has such stiff competition. In the real world, these are the discussions that take place.

As a program director, if the candidate makes it to the interview process, then the interview needs to proceed with this issue in mind. Typically, we need to press the medical student on this question. If he responds to the problem with a reasonable answer, we will then place the application in a separate pile where we need to confirm the candidate with another well-placed phone call to some of the faculty. On the other hand, if he evades the question or gives a vague answer, we put the application in the DNR (Do Not Rank) pile. The whole process can hinge on this one comment.

The Moral Of The Deans Letter

All this brings us back to the double point of this blog. First of all, as you can see, some schools do not filter the Dean’s Letter at all. And its comments can change the whole disposition of the applicant because often it is the only negative piece of information on the entire application. Is it fair? Sometimes, the alleged student misconduct is actual. But, often, a poorly edited/written Deans Letter is merely a function of the negligence of the institution delivering it. Vengeful comments do not belong in a Deans Letter. Truthful and objective statements do. But, most institutions will allow any old phrase to go into the Dean’s Letter. I see that as a significant issue with the system.

And lastly, all medical students must look at their Deans letter if they can. For one, they should try to edit it if they can. Or, at the very least, they need to know to address it if they make it to the interview stage. You are better off learning about the issues on the Dean’s Letter before starting your first interviews (if you are fortunate enough to get one).

Deans Letter Woes

My relationship with the Dean’s Letter is a love/hate one. Why? Primarily because it does help to ferret out differences among the candidates so that you can rank residents appropriately. At the same time, I am aware that it is an imperfect evaluation tool that can cause the demise of many applications of suitable candidates—bottom line. We need to find a better way to evaluate our medical students. Medical schools should take a second look to re-evaluate how they create the Dean’s Letter. It may lead to better selection criteria and improved treatment of their students!