27 Sep

Telemedicine Branching Out to Smallest Patients

By Matthew Sappern, CEO, PeriGen

Remote communication in obstetricsTelemedicine is getting much attention these days as innovative health systems look to increase operational efficiency and patient satisfaction. Leaders such as Stephen Klasko, MD at Thomas Jefferson University Hospital are mandating telemedicine and this top down approach will surely accelerate adoption.

Telemedicine is quickly moving beyond telestroke and the ICU. At least one major EMR company and one of the nation’s leading health systems – fortunately a PeriGen client – are investing significant resources to bring telemedicine to labor and delivery. Complexity, risk and attrition in the ranks of OBs and MFMs make labor and delivery an ideal service line in which to deploy these technologies. PeriGen’s fetal surveillance platform uses Artificial Intelligence to identify troubling patterns and long-term trends in fetal strips. This real time capability is now at the heart of a telemedicine infrastructure which allows a single OB to be alerted to specific cases – showing patterns identified as the most troubling – across an entire health system.

Telemedicine branching out to smallest patients
As a standalone tool or in concert with the above-mentioned EMR module, telemedicine creates a cost-effective way to leverage valuable clinical resources across an enterprise and help safeguard one of a health system’s most risky and most valuable service lines.

27 Sep

My Post-Summer Research Reading List

In The myths and physiology surrounding intrapartum decelerations: the critical role of the peripheral chemoreflex published in the Journal of Physiology, Lear et al have written a highly readable and methodical analysis of current evidence about the mechanisms of fetal heart rate decelerations. This is a must read for anyone seriously using fetal monitoring. He challenges long held tenets and presents a simplified coherent approach to the interpretation of heart rate monitoring. Here are two excerpts that may compel you to read further:

“… Despite multiple detailed analyses, there is no consistent FHR marker of fetal compromise …”

“… We believe that it is better to focus on the frequency, depth and total duration of decelerations during labor rather than on timing, shape or supposed aetiology of the specific deceleration.”

In an article published recently in the American Journal of Obstetrics & Gynecology titled Triggers, bundles, protocols, and checklists — what every maternal care provider needs to know, Arora et al define and provide examples of various methods to standardize and streamline clinical care and summarize the evidence supporting their association with improved outcomes. Many examples are provided for obstetrical issues such as hemorrhage, hypertension, oxytocin usage or preop preparation. With burgeoning evidence from diverse medical and non-medical domains, the question is no longer “Do these methods work?“, but rather “How can we get wider adoption and sustain compliance?” In short, how do we actually change established clinical beliefs and behaviors? This article is less informative on these practical issues.

InfluencerThere is abundant data about effective ways to change behavior. In short, behaviors will not change without aligning a critical mass of influential factors. Determination and good intentions alone are insufficient and depending upon them alone is destined to fail. To supplement this review of available obstetrical safety packages we strongly recommend the book- Influencer: The New Science of Leading Change, Second Edition by David Maxfield, Ron McMillan, Al Switzler. (Click here to see a summary of this excellent work)

12 Sep

Improvement over Wallpaper

L&D leadershipSix Focuses for a Happy L&D Unit

Take a look at your L&D unit bulletin board and tell us: Is there at least one piece of paper dealing with employee satisfaction?

Let’s face it. When asked to complete questionnaires about how we view our work and our performance, many of us glaze over. Especially when those questions seem standardized and unrelated to what we really do and where we really work.

This certainly is the case as well for nurse managers using tools such as Gallup’s Q12 to assess their team’s engagement and work satisfaction. This applies even more so for high-stress units such as labor & delivery where the intrinsic life value of helping to bring life is tempered by the demands of patient attention, documentation, and lots of long hours and hard work.

This week Rose Sherman, the editor of the blog Emerging Nurse Leader, summarizes how to put results from employee surveys like Gallup Q12 to effective use. She highlight six (of the way too many) questions for serious focus by managers looking to measure and improve employee satisfaction:

  1. Clearly defined expectations
  2. Necessary tools & equipment
  3. Opportunity to use strengths
  4. Recognition & praise
  5. Empathy with manager
  6. A mentor

Four of these are areas where nurse managers have direct control. #2 and #6 are certainly in a nurse manager’s sphere of influence.

To read Rose’s article click here

11 Aug

Part 3: Perinatal Nursing & Technology

Rebecca Cypher, PeriGen Chief Nursing OfficerPart 3:
Perinatal Nursing & Technology
Time to Accept & Embrace the Challenge

by Rebecca Cypher, MSN, PNNP
Chief Nursing Officer, PeriGen

I hope you enjoyed the first two excerpts from my recent white paper on technologies in perinatal nursing. This article, done on request by PeriGen (the electronic fetal monitoring software firm for which I serve as Chief Nursing Officer), looks at how technology has evolved in response to changes in perinatal nursing, how we in turn have changed as a result of electronic FHR monitoring, and a view to how we as nursing professionals can influence continued improvement in perinatal technologies.

Below is the final excerpt where we examine the importance of a perinatal nurses view on technology improvements. In case you missed the first two installments, PeriGen has posted the full article as a PDF here.

Why Should Nurses Care?

Between 2008-2012, there were 2.8 million registered nurses (including advanced practice nurses) in the United States workforce making nursing one of the largest health-related professional groups. 24, 29, 30 According to Gallup polls, these professionals are regarded by the public as the most trusted in the United States. Nursing is a caring profession that requires licensure, knowledge and clinical skill. Nursing demonstrates the best side of humanity. Well-designed HIT augments nursing capacity. Nurses must be clear in thinking and understanding the relative strengths and limitations of all parties in order to direct the evolution of these technologies. In turn, nurses can harness these technologies to support the mission of providing high quality patient care that is evidence-based, individualized, efficient and safe.

Government agencies expect a 21% increase in demand for nurses nationwide by 2025 though considerable variation of supply and demand at the state level is anticipated. Nursing employment will continue to be affected by factors including population growth, a shift in demographics as the median age increases, economic conditions, employment and retirement of nursing personnel and changes in health care reimbursement. Workforce projection models demonstrate that the rapidly changing health care delivery system, which includes HIT, is shifting how patient care is delivered and the specific role the nursing workforce plays in these changes. 31

Perinatal nurses are using technology in conjunction with clinical knowledge that has been accumulated through hands on experience and education. This combination assists in improving care and facilitates multidisciplinary communication. Technology allows nurses to ask the right questions at the right time, perform streamlined nursing assessments, accurately determine a correct diagnosis from a multidisciplinary approach, and perform appropriate tasks and intervention on the front and back end of decision-making processes. 32


In this modern era, technology is commonplace whether it’s embedded in households, communication methods, modes of transportation or healthcare. In these areas technology continues to be created, refined and updated on a regular basis. Advances in technology, whether it’s a new cellular phone model or component of medical equipment, are requisite in order to provide and improve efficiency, convenience, accessibility and safety. As nurses provide day to day quality patient care in the perinatal setting, technology will continue to influence many facets of the nursing process framework. In today’s healthcare environment, few perinatal nurses can envision delivering patient care without assistance from some form of technology, whether that technology be an automatic blood pressure machine or fetal surveillance with an electronic fetal monitor. Nursing is what we as individuals do best and nurses working in conjunction with HIT is clearly an investment in optimizing efficiency, perinatal outcomes and patient safety. Throughout time women in labor have sought assistance from others with experience and skills. Clearly nurses will continue to fill that essential role backed by increasingly complex technology as HIT evolves.

To continue reading this article or review the references, please click here

04 Aug

Part 2: Perinatal Nursing & Technology

Rebecca Cypher, PeriGen Chief Nursing OfficerPart 2: Perinatal Nursing & Technology
Time to Accept & Embrace the Challenge

by Rebecca Cypher, MSN, PNNP
Chief Nursing Officer, PeriGen

You may remember that I shared the first part of my recent white paper with you not too long ago. It examined how healthcare technology as evolved as a result of perinatal nursing needs and changes in standards. Now it’s time to look at the flip side: How nursing as changed as a result of technology, specifically systems that help us monitor FHR.

PeriGen has also made the full article available as a PDF here.

Clinical Acumen and Care

While the fundamental technology in standard fetal monitoring equipment has changed little in recent decades, clinical behavior in response to FHR monitoring has changed considerably. Clearly defined nomenclature, 10, 11 standardized clinical guidelines, 12-16 and structured communication techniques are now part of obstetric care. Moreover, published nursing position statements and other resources have highlighted that skilled clinicians are essential to ensure maternal and fetal well-being when fetal monitoring is utilized. Additional publications focus on HIT’s vital healthcare role in terms of enhancing opportunities for reducing error in perinatal settings. 3, 11, 17, 18

There is increased awareness that environmental and human factors can impair clinical judgment resulting in delayed intervention and birth-related injury. To address some of these issues healthcare professionals have:

  • Legislation that limits working hours
  • Updated recommendations on nurse-patient ratios
  • Stricter and more frequent credentialing
  • Chain of command procedures
  • In-house coverage rather than on-call at home

Despite these measures, assessing a clinical situation is still challenging. Nurses must often project what will happen in the future. Furthermore, these same nurses prefer to avoid allowing patients to deteriorate to a suboptimal status because, once changes have occurred, safe recovery may be impossible. To make decisions, the clinical mind must focus on what is important and disregard the irrelevant. The human brain is vulnerable to well described biases in this task.

Recent “vivid” experiences affect individual’s perception of risk. The psychological phenomenon of “Tunnel Vision” refers to a tendency to perceive and confirm only the information that aligns with a particular viewpoint and discard contradicting information. 19 Variations of this phenomenon include “Wishful thinking.” For example, a belief that a patient will deliver soon or not deteriorate on a shift can lead to poor FHR tracing assessments which is inconsistent under the best of conditions. Occasionally, humans get tired, distracted, have memory lapses, take risky shortcuts, or get diverted by competing interests. Furthermore, inadequate training or clinical experience can compound problems at the bedside. The objective, unbiased, statistical methods offered by HIT can counter these types of human bias, reduce information overload and assist novice and seasoned nurses to make more confident decisions. 20, 21, 22

Another attractive HIT feature for perinatal leaders is the ability to collect and organize outcome and performance data such as the number of cesarean births or elective inductions. Instead of hand counting data from multiple sources, which takes up valuable nursing time and resources, HIT can collect this data and provide written reports on a regular basis. Performance can be compared over time, to other unit level quality improvement goals or datasets of core measure such as those established by the Joint Commission and the National Perinatal Information Center. Policies and procedures can then be further refined based on benchmarked data in order to provide safer care to patients. 18, 23

The divisions between fetal monitoring technologies, technologies in healthcare information and modern nursing care have been become increasingly blurred. Monitors contain software. Systems in HIT employ clinical algorithms. Clinical algorithms are often based on research using huge datasets derived from HIT systems. Clinicians make decisions on monitoring data and research findings. A brief comparison of strengths and weakness related to computer and human faculties is outlined in Figure 2. Both are fallible but each one has strengths in specific areas. The strengths of one counter weaknesses of the others. Computers crunch numbers well. Let the computers apply that capacity to analyze, organize and display critical information without bias so that nurses can be empowered to use technology and focus on higher order clinical reasoning, collaborative dialogue with colleagues and compassionate quality care. Surely valuable nursing time should not be consumed by the repetitive, manual labor of measuring, counting and calculating. On the other hand, nurses are essential to seek out and integrate information from additional sources, see exceptions to the general rule, cue in to unspoken patient fears, and even make do with missing data. Nurses communicate, reason, educate, encourage and empathize with patients and families. The profession makes a profound difference as hands-on patient contact, visual interpretation at the bedside and having an underlying basic foundation in obstetric care is absolutely necessary to validate HIT information. The perception that technology will take over nursing responsibilities, such as FHR interpretation, leaving all data to be interpreted, documented and managed by artificial intelligence is not only incorrect but illogical. However, given what is known about human error, surely one could not advocate for one approach without the other i.e., nurses without equipment or equipment without nurses.

As HIT related to antepartum and intrapartum fetal surveillance techniques evolve, the profession is often concerned with how to integrate them without challenging or devaluing the role of nursing. This is where an understanding of HIT strengths is important so that they can insist on HIT functionality that is truly helpful allowing nurses to have more time with patients. Perinatal nurses must continue to be involved in the design of state-of-the art systems at the bedside that optimize time for hands-on patient care and streamlined workflow and patient safety. 18, 24 Additionally, nurses play an important role in collaboratively developing and utilizing a variety of quality improvement and risk reductions strategies with the aid of HIT to improve patient care, reduce adverse perinatal and neonatal outcomes (e.g. emergent cesarean section or neonatal intensive care unit admission) and potentially reduce liability. 13,25-28 These include but are not limited to

Developing clear fetal monitoring guidelines that include multidisciplinary protocols for interpretation, intervention, and documentation

Educating nurses, residents, nurse midwives, and physicians on fundamentals of fetal monitoring using standardized fetal monitoring nomenclature

Applying HIT to patient care by using high quality up to date decision aids, bundles and toolkits

Implementing peer reviewed evidence based information, such as clinical protocols, checklists (i.e. oxytocin), and guidelines in a high reliability organization to reduce clinician practice variation

To continue reading this article or review the references, please click here

29 Jul

Trending in OB

Telehealth in labor & deliveryTelemedicine Branching Out to the Smallest Patients

Telemedicine is getting much attention these days as innovative health systems look to increase operational efficiency and patient satisfaction. Leaders such as Stephen Klasko, MD at Thomas Jefferson University Hospital are mandating telemedicine and this top down approach will surely accelerate adoption.

Telemedicine is quickly moving beyond telestroke and the ICU. At least one major EMR company and one of the nation’s leading health systems – fortunately a PeriGen client – are investing significant resources to bring telemedicine to labor and delivery. Complexity, risk and attrition in the ranks of OBs and MFMs make labor and delivery an ideal service line in which to deploy these technologies. PeriGen’s fetal surveillance platform uses Artificial Intelligence to identify troubling patterns and long-term trends in fetal strips. This real time capability is now at the heart of a telemedicine infrastructure which allows a single OB to be alerted to specific cases – showing patterns identified as the most troubling – across an entire health system.

As a standalone tool or in concert with the above-mentioned EMR module, telemedicine creates a cost-effective way to leverage valuable clinical resources across an enterprise and help safeguard one of a health system’s most risky and most valuable service lines.

I’d love to hear how your meeting the twin challenges of improving patient safety and the expected shortage of labor & delivery providers.


28 Jul

Part 1: Perinatal Nursing & Technology

Rebecca Cypher, PeriGen Chief Nursing OfficerTechnologies in Perinatal Nursing:
Time to Accept & Embrace the Challenge

by Rebecca Cypher, MSN, PNNP
Chief Nursing Officer, PeriGen, Inc.

I wanted to share with you a white paper that PeriGen asked me to prepare on how today’s healthcare technologies can help us in perinatal nursing. Since the paper is lengthy and few of us have time to read such articles in one sitting, I’ve split the paper into three parts and will deliver it to you via email and PeriGen’s social media platforms (Facebook, LinkedIn, Twitter) over the next several weeks. If, by chance, you would like the full article, click here for access to the PDF

Let’s start with a look back at where we’ve come from:

Humans have a long history of inventing tools to survive and achieve goals more efficiently.1 Some tools survive the test of time and evolve while others are abandoned. Healthcare is no different. Monitoring devices and healthcare information technologies (HIT) are key tools used in modern healthcare and time will tell how well they advance as healthcare changes.

Perinatal Nursing Technology-Figure 1Perinatal nursing is just one example of where HIT has had a significant influence on integrating technology with a nursing process framework. 3 Monitoring technology, information technology and clinical acumen can be thought of as an interdependent hierarchy. (See Figure 1 above ). For example, at the most basic level, electronic fetal monitor (EFM) sensors measure fetal heart rates (FHR) and uterine activity. At an intermediate level, HIT consolidates and analyzes the monitoring data for clinicians. At the highest level, nurses decide what the data means, what is likely to happen next and implement the most beneficial interventions. Each level depends, in part, upon the former. Historically, nurses did everything including auscultating FHRs with a fetoscope, palpating uterine activity, recording data in a paper record, and made FHR decisions based on what could be heard and recorded. Now EFM and software accomplish several of these tasks. For some nurses, these new technologies evoked insecurity, a feeling that professional value and roles would be diminished. For others, new technology provided a release from endless listening, counting and transcribing and consequently freeing time to focus on clinical judgment and hands on patient care. In fact, while fetal monitors did reduce the counting tasks they also elevated the expectation for medical reasoning or tracing interpretation.

The purpose of this document is to broadly outline the evolution in each of the three levels of data collection via monitors, interpretation and clinical intervention. In addition, we will discuss relative strengths and weakness of clinicians and HIT in the context of modern perinatal care and how they complement each other.

Clarity on this subject is important to:

  1. Emphasize that clinical acumen for diagnostic and therapeutic decisions and compassionate care is paramount
  2. Determine where and why technology can be a help or a hindrance for nurses
  3. Provide guidance for designers of new technology to meet a nurse’s greatest clinical need

Monitoring Technology

By 2004, 89% of births in the United States were monitored electronically. 4 In view of the high and stable rate of electronic monitoring Vital Statistics ceased reporting EFM utilization rates in annual birth-related reports. Monitoring sensors and signal processing have evolved to provide excellent measurement of FHR, uterine activity and maternal vital signs. 5 Fetal monitors can indicate signal coincidence when two sources of heart rate measurement are the same. On the other hand, monitoring faces new physical challenges. Obesity impedes monitoring by Doppler ultrasound based external sensor technology.

Given the imprecise relationship between FHR and fetal brain oxygenation or acid- base status, a considerable effort has been devoted to finding other physiological measures that would be more discriminating. Unfortunately, prospective clinical trials show no clinical benefit in using EFM with additional sensors that measure fetal oxygen saturation or fetal ST segments of the fetal ECG compared to using EFM alone. 6, 7 Thus, for the near future, the obstetrical world remains dependent upon standard EFM.

Healthcare Information Technology

HIT has evolved considerably in contrast, to the relative stagnation of the monitoring devices. Early electronic medical records allowed clinicians to collect, display and store information in a legible fashion, but at considerable inefficiency. Data entry was often arduous, time-consuming and error -prone. “Cut and paste” shortcuts led to nonsense entries with costly legal repercussions. Lack of interoperability wasted time with redundant documentation.

Perinatal nurses have played an important role in this evolution. Working alongside HIT experts, nurses have been vital members of multidisciplinary teams in which integrating, implementing, and maintaining fetal surveillance technologies with clinical practice has become a priority in patient centered care and safety. This is especially apparent in organizations that promote high reliability units.

There has been considerable industry consolidation on a few types of hospital-wide electronic medical records boosting interoperability. IT networks, smartphones and cloud-based computing give nurses unprecedented and speedy access to information and human expertise. The computational power and reliability of basic computers and networks means very complex analytical methods can be available in real-time at the bedside. 8, 9 Computerized analyses can now be applied to EFM tracings or evaluate labor progression to bring consistent interpretation, reducing clinical variation.

Psychological testing has underlined the importance of simplicity and clarity of information displayed on computer screens. Overcrowded or confusing displays can lead to medical error. Better graphical designs mean critical information is consolidated for efficient review by clinicians. High rates of false alarms lead to frustration and disregard of the device. Truly discriminating alerts based on better evidence-based algorithms alleviate this alarm fatigue.

To continue reading this article or review the references, please click here

13 Jun

Full House for PeriGen Reception @ AWHONN

Short Stories of OB Malpractice

Full House for

“Short Stories of OB Malpractice &

How They Might

Have Been Avoided

Stephen Brzezinski, a leading OB malpractice defense attorney from Kitch, Drutchas Wagner Valitutti & Sherbrook, and Emily Hamilton, PeriGen Senior Vice President of Clinical Research presented to a packed house of labor & delivery directors, clinicians, educators, and risk managers last night at the AWHONN Convention in Grapevine, Texas.

The invitation-only presentation focused on factors leading to OB malpractice complaints as well as recent malpractice actions involving labor & delivery clinicians and offered practice strategies and discussion on how they might have been avoided.

Presentation slides are now available here

PeriGen is also exhibiting at the AWHONN Convention (Booth 615), where the event team will be offering demonstrations of the latest features of the PeriCALM obstetric decision support system, an electronic fetal monitoring (EFM) system that provides “safety net” benefits for labor & delivery clinical teams.

PeriGen is dedicated to helping prevent OB malpractice by providing enriched data that support clinical decisions at the bedside, at the nurses station and to providers remotely.

09 Jun

We Can Do Better

We Can Do Better

Recent research finds medical error third leading cause of death in USBy Matthew Sappern, CEO, PeriGen

Earlier this month, the well respected, widely read British Medical Journal published a scary study coming out of Johns Hopkins. Entitled Medical Error, the Third Leading Cause of Death in the US,  it immediately sparked debate in many corners as to the veracity of the data, the precision of the study, the complexity and limitations of actually compiling and analyzing this information. I’ll leave that to others – I see a blunt message here: We Can Do Better.

To me, this is not so much a question of enhanced training or personnel or protocols. Humans excel at critical thinking, but there will always be a “Human Factor” to manage – those few instances where a human misses something. This study begs the question “are there tools that can help clinicians at the bedside – patient by patient?” How can we best leverage technology to augment caregivers?

As you all know better than I, the clinical setting is challenging! At the labor and delivery bedside, nurses are monitoring and documenting several aspects of the labor, interacting and calming the patient, managing the patient’s family (Nurse Luisa, I apologize again for asking the same questions every five minutes 12 years ago), keeping the rest of the care team informed. All while looking for what might be faint indications of an intervention needed.

Fortunately, PeriGen customers have at their disposal some of the most advanced tools in the world to help share the load. PeriGen systems help count and calculate critical factors, providing a safety net for L&D clinicians and the world’s most precious patients. Other specialties in the hospital should take note of the great work that PeriGen users are delivering.

03 Jun

AI will always need humans

Watson and His AI Cousins Will

Always Need Humans:

AI will always need humans

Is the Converse True?

by Emily Hamilton
Senior Vice President, PeriGen

Most of us will easily concede that computers are better at number crunching than humans. How many of us, even in our prime, can quickly complete the dreaded serial sevens test? (counting down from one hundred by sevens, a clinical test used to test mental status) .

As for higher level functions like reasoning, clinical judgment, strategic planning, creativity, empathy surely these are better achieved by humans. Well yes, but maybe not always.

This year Google’s AlphaGo defeated a human champion at the ancient game of Go, not by brute force (calculating the best of every possible move at each turn) but by using deep neural networks to learn successful and efficient strategies. AlphaGo learned its strategies by playing the game. With modern computational capacity AlphaGo was able to play more games in a day and that a human could play in a decade. Furthermore, it could remember that experience!

Chess is not medicine. What does the evidence show in medicine?

In 1954 the acclaimed psychologist Paul E. Meehl began a debate that would last more than half a century when he compared the accuracy of clinical versus statistical methods to predict patient condition.(1) His analysis, described in the book Clinical vs. Statistical Prediction: A Theoretical Analysis and a Review of the Evidence, concluded that statistical   (e.g., explicit equations, actuarial tables, defined algorithmic prediction) outperformed clinical methods (e.g., subjective, informal, reasoning, clinical intuition).

Later in 2000, Grove et al published a comprehensive analysis of relevant publications on man versus machine methods. (2)  Their meta-analysis included 136 published reports and compared performance of clinical and statistical methods in a wide variety of domains. Their results confirmed the findings of Meehl! Statistical methods outperformed clinical methods again.

They reported that better performance with statistical methods held across subject matter (medical, mental health, forensic, academic performance ) although the advantage was greatest in the forensic domains. The level of clinician experience did not make a difference, even when the statistical methods were compared to the best performing clinician(s). Superior results were not entirely uniform.   In about half of the studies the difference was small and the clinical methods were approximately the same as the statistical methods. In about one third, the statistical methods substantially outperformed clinicians especially when clinical interviews were involved. That is, detection rates were higher by about 10% or more for predictions with intermediate accuracy. In a small minority, 6% of the studies, the clinical methods were better.

In 2006, Hilton et al reported similar findings and noted a widening gap between statistical and clinical methods when reviewing 66 years of research on the prediction of violence. (3) Reports in current medical literature differ somewhat. A recent review by Sanders et al showed more equivalence between clinical methods and statistical prediction using a wider variety of assessment measures.   Only 31 studies met their inclusion criteria highlighting both the relative scarcity of complex statistical techniques in clinical use and the scientific inadequacy of the comparison methods.(4)

There are many reasons to believe that clinical judgement is better today than in previous eras

Our basic understanding of disease has improved. We have better laboratory tests and higher standards for medical evidence and easier access to information. In fact, one could argue that the clinician today has better access and better information compared to many years ago when there were few genetic markers, biomarkers and environmental conditions to consider. In fact, we may have too much information. The very same mental processes that are essential to “size up” a situation efficiently in the face of so much information can also result in erroneous decisions on occasion.

Two well-established psychological phenomena bear special mention in any discussion of medical error. Recent events or vivid anecdotes form strong and highly influential memories that can distort our perception of the real incidence or usual consequences of specific scenarios. Tunnel vision refers to the tendency to perceive and confirm information that aligns with a particular viewpoint. It includes Framing bias – the tendency to create a coherent interpretation without examining all available information and Confirmation bias which refers to seeking only the information that supports a particular opinion. Finally, too much information can actually obscure critical information. These biases and the burden of too much information are not so problematic for statistical methods.

Pitting clinical methods against computer based methods is unrealistic. “Medical reasoning” and “statistical algorithms” are both derived from real clinical data   Moreover, clinicians incorporate statistical methods unconsciously when reasoning.   They consider the background general incidence of the condition, typical constellations of signs and symptoms and weigh the pros and cons of potential diagnosis and treatments. Many clinicians know and use scoring systems which are essentially simplified statistical weighting methods. Statistics is but a formalized mathematical way to analyze real data and then summarize it succinctly to help us make inferences. Thus one would expect performance measures of human and clinicians to converge.

Mark Twain is often credited with writing – “Facts are stubborn things, statistics are more pliable”. But in this context, clinicians are more pliable. Clinicians can obtain and integrate information from additional sources, see exceptions to the rules, factor in patient fears and desires and even make do with missing data. Clinicians communicate with patients, reason and have empathy. However, occasionally they get tired, take risky shortcuts and must deal with competing interests. In contrast, statistical facts are stubborn things and not subject to the effects of fatigue or recent experience. At present they are not very communicative nor empathetic. Robotic companions for seniors may change our opinion.

The strengths of human and statistical methods are complementary

The objective unbiased statistical methods help to counter the potential for human bias, reduce information overload and help the seasoned clinician make more confident decisions.   The idea of a clear division between clinical reasoning and statistical methods is becoming increasing blurred. The good news is that the best is yet to come and it will probably arrive on your phone.

  1. Meehl, P.E. (1954). Clinical versus statistical prediction: A theoretical analysis and a review of the evidence. Minneapolis: University of Minnesota
  2. Grove WM, Zald DH, Lebow BS, Snitz BE, Nelson C. Clinical versus mechanical prediction: a meta-analysis. Psychol Assess. 2000 ;12(1):19-30
  3. Hilton NZ, Harris GT, Rice ME, Sixty-Six Years of Research on the Clinical Versus Actuarial Prediction of Violence. The Counseling Psychologist, 2006 ; 34(3):400-409.
  4. Sanders S, Doust J, Glasziou P. A systematic review of studies comparing diagnostic clinical prediction rules with clinical judgment. PLoS One. 2015 Jun 3;10(6):e0128233.
  5. Lee YH, Bang H, Kim DJ. How to Establish Clinical Prediction Models. Endocrinol Metab (Seoul). 2016 Mar;31(1):38-44.