Machine learning (ML) programs computers to learn the way we do – through the continual assessment of data and identification of patterns based on past outcomes. ML can quickly pick out trends in big datasets, operate with little to no human interaction and improve its predictions over time. Due to these abilities, it is rapidly finding its way into medical research.
People with breast cancer may soon be diagnosed through ML faster than through a biopsy. Those suffering from depression might be able to predict mood changes through smart phone recordings of daily activities such as the time they wake up and amount of time they spend exercising. ML may also help paralyzed people regain autonomy using prosthetics controlled by patterns identified in brain scan data. ML research promises these and many other possibilities to help people lead healthier lives.
But while the number of ML studies grow, the actual use of it in doctors’ offices has not expanded much past simple functions such as converting voice to text for notetaking.
The limitations lie in medical research’s small sample sizes and unique datasets. This small data makes it hard for machines to identify meaningful patterns. The more data, the more accuracy in ML diagnoses and predictions. For many diagnostic uses, massive numbers of subjects in the thousands would be needed, but most studies use smaller numbers in the dozens of subjects.
But there are ways to find significant results from small datasets if you know how to manipulate the numbers. Running statistical tests over and over again with different subsets of your data can indicate significance in a dataset that in reality may be just random outliers.
This tactic, known as P-hacking or feature hacking in ML, leads to the creation of predictive models that are too limited to be useful in the real world. What looks good on paper doesn’t translate to a doctor’s ability to diagnose or treat us.
These statistical mistakes, oftentimes done unknowingly, can lead to dangerous conclusions.
To help scientists avoid these mistakes and push ML applications forward, Konrad Kording, Nathan Francis Mossell University Professor with appointments in the Departments of Bioengineering and Computer and Information Science in Penn Engineering and the Department of Neuroscience at Penn’s Perelman School of Medicine, is leading an aspect of a large, NIH-funded program known as CENTER – Creating an Educational Nexus for Training in Experimental Rigor. Kording will lead Penn’s cohort by creating the Community for Rigor which will provide open-access resources on conducting sound science. Members of this inclusive scientific community will be able to engage with ML simulations and discussion-based courses.
“The reason for the lack of ML in real-world scenarios is due to statistical misuse rather than the limitations of the tool itself,” says Kording. “If a study publishes a claim that seems too good to be true, it usually is, and many times we can track that back to their use of statistics.”
Such studies that make their way into peer-reviewed journals contribute to misinformation and mistrust in science and are more common than one might expect.
Neuroscientists frequently say that neural activity ‘represents’ certain phenomena, PIK Professor Konrad Kording and postdoc Ben Baker led a study that took a philosophical approach to tease out what the term means.
One of neuroscience’s greatest challenges is to bridge the gaps between the external environment, the brain’s internal electrical activity, and the abstract workings of behavior and cognition. Many neuroscientists rely on the word “representation” to connect these phenomena: A burst of neural activity in the visual cortex may represent the face of a friend or neurons in the brain’s memory centers may represent a childhood memory.
But with the many complex relationships between mind, brain, and environment, it’s not always clear what neuroscientists mean when they say neural activity “represents” something. Lack of clarity around this concept can lead to miscommunication, flawed conclusions, and unnecessary disagreements.
To tackle this issue, an interdisciplinary paper takes a philosophical approach to delineating the many aspects of the word “representation” in neuroscience. The work, published in Trends in Cognitive Sciences, comes from the lab of Konrad Kording, a Penn Integrates Knowledge University Professor and senior author on the study whose research lies at the intersection of neuroscience and machine learning.
In 2005, John Ioannidis published a bombshell paper titled “Why Most Published Research Findings Are False.” In it, Ioannidis argued that a lack of scientific rigor in biomedical research — such as poor study design, small sample sizes and improper assessment of the significance of data— meant that a large percentage of experiments would not return the same results if they were conducted again.
Since then, researchers’ awareness of this “replication crisis” has grown, especially in fields that directly impact the health and wellbeing of people, where lapses in rigor can have life-or-death consequences. Despite this attention and motivation, however, little progress has been made in addressing the roots of the problem. Formal training in rigorous research practices remains rare; while mentors advise their students on how to properly construct and conduct experiments to produce the most reliable evidence, few educational resources exist to support them.
Konrad Kording, a Penn Integrates Knowledge Professor with appointments in the Departments of Bioengineering and Computer and Information Science in Penn Engineering and the Department of Neuroscience in Penn’s Perelman School of Medicine, has been awarded one of the initiative’s first five grants.
“The replication crisis is real,” says Kording. “I’ve tried to replicate the research of others and failed. I’ve reanalyzed my own data and found major mistakes that needed to be corrected. I was never properly taught how to do rigorous science, and I want to improve that for the next generation.”
Though the technology for brain-computer interfaces (or BCI’s) has existed for decades, recent strides have been made to create BCI devices which are safer, smaller, and more effective. Konrad Kording, Nathan Francis Mossell University Professor in Bioengineering, Neuroscience, and Computer and Information Science, helps to elucidate the potential future of this technology in a recent feature in Wired. In the article, he discusses the “invasive” aspects of previous BCI technology, in contrast to recent innovations, such as a new device by Synchron, which do not require surgery and are consequently much less risky:
“The device, called a Stentrode, has a mesh-like design and is about the length of a AAA battery. It is implanted endovascularly, meaning it’s placed into a blood vessel in the brain, in the region known as the motor cortex, which controls movement. Insertion involves cutting into the jugular vein in the neck, snaking a catheter in, and feeding the device through it all the way up into the brain, where, when the catheter is removed, it opens up like a flower and nestles itself into the blood vessel’s wall. Most neurosurgeons are already up to speed on the basic approach required to put it in, which reduces a high-risk surgery to a procedure that could send the patient home the very same day. ‘And that is the big innovation,” Kording says.
Konrad Kording, Nathan Francis Mossell University Professor in Bioengineering, Neuroscience, and Computer and Information Sciences, was appointed the Co-Director of the CIFAR Program in Learning in Machines & Brains. The appointment will start April 1, 2022.
CIFAR is a global research organization that convenes extraordinary minds to address the most important questions facing science and humanity. CIFAR was founded in 1982 and now includes over 400 interdisciplinary fellows and scholars, representing over 130 institutions and 22 countries. CIFAR supports research at all levels of development in areas ranging from Artificial Intelligence and child and brain development, to astrophysics and quantum computing. The program in Learning in Machines & Brains brings together international scientists to examine “how artificial neural networks could be inspired by the human brain, and developing the powerful technique of deep learning.” Scientists, industry experts, and policymakers in the program are working to understand the computational and mathematical principles behind learning, whether in brains or in machines, in order to understand human intelligence and improve the engineering of machine learning. As Co-Director, Kording will oversee the collective intellectual development of the LMB program which includes over 30 Fellows, Advisors, and Global Scholars. The program is also co-directed by Yoshua Benigo, the Canada CIFAR AI Chair and Professor in Computer Science and Operations Research at Université de Montréal.
Kording, a Penn Integrates Knowledge (PIK) Professor, was previously named an associate fellow of CIFAR in 2017. Kording’s groundbreaking interdisciplinary research uses data science to advance a broad range of topics that include understanding brain function, improving personalized medicine, collaborating with clinicians to diagnose diseases based on mobile phone data and even understanding the careers of professors. Across many areas of biomedical research, his group analyzes large datasets to test new models and thus get closer to an understanding of complex problems in bioengineering, neuroscience and beyond.
From smartphones and fitness trackers to social media posts and COVID-19 cases, the past few years have seen an explosion in the amount and types of data that are generated daily. To help make sense of these large, complex datasets, the field of data science has grown, providing methodologies, tools, and perspectives across a wide range of academic disciplines.
As part of its $750 million investment in science, engineering, and medicine, the University has committed to supporting the future needs of this field. To this end, the Innovation in Data Engineering and Science (IDEAS) initiative will help Penn become a leader in developing data-driven approaches that can transform scientific discovery, engineering research, and technological innovation.
“The IDEAS initiative is game-changing for our University,” says President Amy Gutmann. “This new investment allows us to boost our interdisciplinary efforts across campus, recruit phenomenal additional team members, and generate an even more sound foundation for discovery, experimentation, and design. This initiative is a clear statement that Penn is committed to taking data science head-on.”
“One of the unique things about data science and data engineering is that it’s a very horizontal technology, one that is going to be impacting every department on campus,” says George Pappas, Electrical and Systems Engineering Department chair. “When you have a horizontal technology in a competitive area, we have to figure out specific areas where Penn can become a worldwide leader.”
To do this, IDEAS aims to recruit new faculty across three research areas: artificial intelligence (AI) to transform scientific discovery, trustworthy AI for autonomous systems, and understanding connections between the human brain and AI.
In the area of neuroscience and how the human brain is similar to AI and machine learning approaches, research from PIK Professor Konrad Kording and Dani Bassett’sComplex Systems lab exemplifies the types of cross-disciplinary efforts that are essential for addressing complex questions. By recruiting additional faculty in this area, IDEAS will help Penn make strides in bio-inspired computing and in future life-changing discoveries that could address cognitive disorders and nervous system diseases.
When Nathan Francis Mossell graduated in 1882, he became the first African American to earn a medical degree from Penn. He soon became a prominent African American physician, the first to be elected to the Philadelphia County Medical Society. He helped found the Frederick Douglass Memorial Hospital and Training School, which treated Black patients and helped train the next generation of Black doctors and nurses.
“Dr. Mossell was truly inspiring. He had to fight for everything, yet never reneged on his principles. He pretty much started a hospital and was a major champion for the advancement of equality for African Americans,” Kording said. “In my research, where I study how intelligence works, I am inspired by scholars like him who combine many different insights. He was a wonderful man, and I will be proud to carry his name.”
While artificial intelligence is becoming a bigger part of nearly every industry and increasingly present in everyday life, even the most impressive AI is no match for a toddler, chimpanzee, or even a honeybee when it comes to learning, creativity, abstract thinking or connecting cause and effect in ways they haven’t been explicitly programmed to recognize.
This discrepancy gets at one of the field’s fundamental questions: what does it mean to say an artificial system is “intelligent” in the first place?
Seventy years ago, Alan Turing famously proposed such a benchmark; a machine could be considered to have artificial intelligence if it could successfully fool a person into thinking it was a human as well. Now, many artificial systems could pass a “Turing Test” in certain limited domains, but none come close to imitating the holistic sense of intelligence we recognize in animals and people.
Understanding how AI might someday be more like this kind of biological intelligence — and developing new versions of the Turing Test with those principles in mind — is the goal of a new collaboration between researchers at the University of Pennsylvania, Carnegie Mellon University and Johns Hopkins University.
The project, called “From Biological Intelligence to Human Intelligence to Artificial General Intelligence,” is led by Konrad Kording, a Penn Integrates Knowledge Professor with appointments in the Departments of Bioengineering and Computer and Information Science in Penn Engineering and the Department of Neuroscience at Penn’s Perelman School of Medicine. Kording will collaborate with Timothy Verstynen of Carnegie Mellon University, as well Joshua T. Vogelstein and Leyla Isik, both of Johns Hopkins University, on the project.
When the COVID-19 pandemic began taking hold in the United States, one of the first “superspreader” events was an academic conference. Such conferences have long been a primary way for researchers to share new findings and launch collaborations, but with thousands of people from around the world, indoors and in close proximity, it quickly became clear that the traditional format for these events would need to radically change.
Konrad Kording, a Penn Integrates Knowledge Professor with appointments in the departments of Bioengineering and Computer and Information Science in Penn Engineering and the Department of Neuroscience at Penn’s Perelman School of Medicine, was ahead of the curve on this shift. With the issues of prohibitive costs and environmental impact of travel in mind, Kording had already started brainstorming ways of reinventing the traditional conference format when the pandemic made it a necessity.
The resulting event, Neuromatch, involved algorithmically analyzing participants’ work in order to connect researchers who might not otherwise meet. Building on the success of that “unconference,” Kording and his colleagues launched the Neuromatch Academy, a free-ranging online summer school organized around the same principles.
Kording already had experience quickly pulling together online events. Early in the pandemic, together with Dan Goodman, Titipat Achakulvisut and Brad Wyble, he developed an online ‘unconference,’ which featured both lectures and a virtual networking component designed to mimic the in-person interactions that make conferences so valuable. (For more, see “Designing a Virtual Neuroscience Conference.”) Soon after, they decided to spin that success into a full-fledged summer school offering live lectures with top computational neuroscientists, guided coding exercises to teach mathematical approaches to neural modeling and analysis, and community support from mentors and teaching assistants (TAs).
The result was a summer school with well-designed content, a diverse student body, including participants from U.S.-sanctioned Iran, and a determined group of organizers who managed to pull off the most inclusive computational neuroscience school yet. NMA now has its eye on a future with even broader representation across countries, languages and skill levels. This year has been incredibly difficult for many, but NMA has provided an important precedent for how to collaborate across, and even dismantle, all sorts of barriers.
In response to the unprecedented challenges presented by the global outbreak of the novel coronavirus SARS-CoV-2, Penn Bioengineering’s faculty, students, and staff are finding innovative ways of pivoting their research and academic projects to contribute to the fight against COVID-19. Though these projects are all works in progress, I think it is vitally important to keep those in our broader communities informed of the critical contributions our people are making. Whether adapting current research to focus on COVID-19, investing time, technology, and equipment to help health care infrastructure, or creating new outreach and educational programs for students, I am incredibly proud of the way Penn Bioengineering is making a difference. I invite you to read more about our ongoing projects below.
Novel Chest X-Ray Contrast
David Cormode, Associate Professor of Radiology and Bioengineering
The Cormode and Noel labs are working to develop dark-field X-ray imaging, which may prove very helpful for COVID patients. It involves fabricating diffusers that incorporate gold nanoparticles to modify the X-ray beam. This method gives excellent images of lung structure. Chest X-ray is being used on the front lines for COVID patients, and this could potentially be an easy to implement modification of existing X-ray systems. The additional data give insight into the health state of the microstructures (alveoli) in the lung. This new contrast mechanics could be an early insight into the disease status of COVID-19 patients. For more on this research, see Cormode and Noel’s chapter in the forthcoming volume Spectral, Photon Counting Computed Tomography: Technology and Applications, edited by Katsuyuki Taguchi, Ira Blevis, and Krzysztof Iniewski (Routledge 2020).
Computational Models for Targeting Acute Respiratory Distress Syndrome (ARDS). The severe forms of COVID-19 infections resulting in death proceeds by the propagation of the acute respiratory distress syndrome or ARDS. In ARDS, the lungs fill up with fluid preventing oxygenation and effective delivery of therapeutics through the inhalation route. To overcome this major limitation, delivery of antiinflammatory drugs through the vasculature (IV injection) is a better approach; however, the high injected dose required can lead to toxicity. A group of undergraduate and postdoctoral researchers in the Radhakrishnan Lab (Emma Glass, Christina Eng, Samaneh Farokhirad, and Sreeja Kandy) are developing a computational model that can design drug-filled nanoparticles and target them to the inflamed lung regions. The model combines different length-scales, (namely, pharmacodynamic factors at the organ scale, hydrodynamic and transport factors in the tissue scale, and nanoparticle-cell interaction at the subcellular scale), into one integrated framework. This targeted approach can significantly decrease the required dose for combating ARDS. This project is done in collaboration with Clinical Scientist Dr. Jacob Brenner, who is an attending ER Physician in Penn Medicine. This research is adapted from prior findings published in Volume 13, Issue 4 of Nanomedicine: Nanotechnology, Biology and Medicine: “Mechanisms that determine nanocarrier targeting to healthy versus inflamed lung regions” (May 2017).
Sydney Shaffer, Assistant Professor of Bioengineering and Pathology and Laboratory Medicine
Arjun Raj, David Issadore, and Sydney Shaffer are working on developing an integrated, rapid point-of-care diagnostic for SARS-CoV-2 using single molecule RNA FISH. The platform currently in development uses sequence specific fluorescent probes that bind to the viral RNA when it is present. The fluorescent probes are detected using a iPhone compatible point-of-care reader device that determines whether the specimen is infected or uninfected. As the entire assay takes less than 10 minutes and can be performed with minimal equipment, we envision that this platform could ultimately be used for screening for active COVID19 at doctors’ offices and testing sites. Support for this project will come from a recently-announced IRM Collaborative Research Grant from the Institute of Regenerative Medicine with matching funding provided by the Departments of Bioengineering and Pathology and Laboratory Medicine in the Perelman School of Medicine (PSOM) (PI’s: Sydney Shaffer, Sara Cherry, Ophir Shalem, Arjun Raj). This research is adapted from findings published in the journal Lab on a Chip: “Multiplexed detection of viral infections using rapid in situ RNA analysis on a chip” (Issue 15, 2015). See also United States Provisional Patent Application Serial No. 14/900,494 (2014): “Methods for rapid ribonucleic acid fluorescence in situ hybridization” (Inventors: Raj A., Shaffer S.M., Issadore D.).
HEALTH CARE INFRASTRUCTURE
Penn Health-Tech Coronavirus COVID-19 Collaborations
Brian Litt, Professor of Bioengineering, Neurology, and Neurosurgery
In his role as one of the faculty directors for Penn Health-Tech, Professor Brian Litt is working closely with me to facilitate all the rapid response team initiatives, and in helping to garner support the center and remove obstacles. These projects include ramping up ventilator capacity and fabrication of ventilator parts, the creation of point-of-care ultrasounds and diagnostic testing, evaluating processes of PPE decontamination, and more. Visit the Penn Health-Tech coronavirus website to learn more, get involved with an existing team, or submit a new idea.
Dr. Maltese is rapidly developing a low-cost ventilator that could be deployed in Penn Medicine for the expected surge, and any surge in subsequent waves. This design is currently under consideration by the FDA for Emergency Use Authorization (EUA). This example is one of several designs considered by Penn Medicine in dealing with the patient surge.
David F. Meaney, Solomon R. Pollack Professor of Bioengineering and Senior Associate Dean
Led by David Meaney, Kevin Turner, Peter Bruno and Mark Yim, the face shield team at Penn Health-Tech is working on developing thousands of rapidly producible shields to protect and prolong the usage of Personal Protective Equipment (PPE). Learn more about Penn Health-Tech’s initiatives and apply to get involved here.
Update 4/29/20: The Penn Engineering community has sprung into action over the course of the past few weeks in response to COVID-19. Dr. Meaney shared his perspective on those efforts and the ones that will come online as the pandemic continues to unfold. Read the full post on the Penn Engineering blog.
OUTREACH & EDUCATION
Student Community Building
Yale Cohen, Professor of Otorhinolaryngology, Department of Psychology, BE Graduate Group Member, and BE Graduate Chair
Yale Cohen, and Penn Bioengineering’s Graduate Chair, is working with Penn faculty and peer institutions across the country to identify intellectually engaging and/or community-building activities for Bioengineering students. While those ideas are in progress, he has also worked with BE Department Chair Ravi Radhakrishnan and Undergraduate Chair Andrew Tsourkas to set up a dedicated Penn Bioengineering slack channel open to all Penn Bioengineering Undergrads, Master’s and Doctoral Students, and Postdocs as well as faculty and staff. It has already become an enjoyable place for the Penn BE community to connect and share ideas, articles, and funny memes.
Undergraduate Course: Biotechnology, Immunology, Vaccines and COVID-19 (ENGR 35)
Daniel A. Hammer, Alfred G. and Meta A. Ennis Professor of Bioengineering and Chemical and Biomolecular Engineering
This Summer Session II, Professor Dan Hammer and CBE Senior Lecturer Miriam R. Wattenbarger will teach a brand-new course introducing Penn undergraduates to a basic understanding of biological systems, immunology, viruses, and vaccines. This course will start with the fundamentals of biotechnology, and no prior knowledge of biotechnology is necessary. Some chemistry is needed to understand how biological systems work. The course will cover basic concepts in biotechnology, including DNA, RNA, the Central Dogma, proteins, recombinant DNA technology, polymerase chain reaction, DNA sequencing, the functioning of the immune system, acquired vs. innate immunity, viruses (including HIV, influenza, adenovirus, and coronavirus), gene therapy, CRISPR-Cas9 editing, drug discovery, types of pharmaceuticals (including small molecule inhibitors and monoclonal antibodies), vaccines, clinical trials. Some quantitative principles will be used to quantifying the strength of binding, calculate the dynamics of enzymes, writing and solving simple epidemiological models, methods for making and purifying drugs and vaccines. The course will end with specific case study of coronavirus pandemic, types of drugs proposed and their mechanism of action, and vaccine development.
Update 4/29/20: Read the Penn Engineering blog post on this course published April 27, 2020.
Konrad Kording, Penn Integrates Knowledge University Professor of Bioengineering, Neuroscience, and Computer and Information Science
Dr. Kording facilitated Neuromatch 2020, a large virtual neurosciences conferences consisting of over 3,000 registrants. All of the conference talk videos are archived on the conference website and Dr. Kording has blogged about what he learned in the course of running a large conference entirely online. Based on the success of Neuromatch 1.0, the team are now working on planning Neuromatch 2.0, which will take place in May 2020. Dr. Kording is also working on facilitating the transition of neuroscience communication into the online space, including a weekly social (#neurodrinking) with both US and EU versions.
Konrad Kording, Penn Integrates Knowledge University Professor of Bioengineering, Neuroscience, and Computer and Information Science
Dr. Kording is working to launch the Neuromatch Academy, an open, online, 3-week intensive tutorial-based computational neuroscience training event (July 13-31, 2020). Participants from undergraduate to professors as well as industry are welcome. The Neuromatch Academy will introduce traditional and emerging computational neuroscience tools, their complementarity, and what they can tell us about the brain. A main focus is not just on using the techniques, but on understanding how they relate to biological questions. The school will be Python-based making use of Google Colab. The Academy will also include professional development / meta-science, model interpretation, and networking sessions. The goal is to give participants the computational background needed to do research in neuroscience. Interested participants can learn more and apply here.
Journal of Biomedical Engineering Call for Review Articles
Beth Winkelstein, Vice Provost for Education and Eduardo D. Glandt President’s Distinguished Professor of Bioengineering
The American Society of Medical Engineers’ (ASME) Journal of Biomechanical Engineering (JBME), of which Dr. Winkelstein is an Editor, has put out a call for review articles by trainees for a special issue of the journal. The call was made in March 2020 when many labs were ramping down, and trainees began refocusing on review articles and remote work. This call continues the JBME’s long history of supporting junior faculty and trainees and promoting their intellectual contributions during challenging times.
Update 4/29/20: CFP for the special 2021 issue here.
Are you a Penn Bioengineering community member involved in a coronavirus-related project? Let us know! Please reach out to firstname.lastname@example.org.