Most extant clinics still rely on paper charts, and it is a daunting task to convert all existing charts to computer files. A common approach to work around this problem is to maintain a hybrid system that keeps track of all new patients electronically while referencing paper charts when necessary. This way, the paper archive would not continue to expand. Old charts would be retrieved only when necessary, since it is a relatively expensive operation compared to a database search. While this method cleverly sidesteps the need to perform any conversion, it does not make the mountain of paper any smaller; a small modification solves this problem nicely. When a paper chart is ready to be archived again after being retrieved, it is scanned into a computer file instead. Only the actively-used charts are converted, greatly optimizing future lookups while saving resources.

Another problem with electronic medical records is authentication and authorization. Digital files are very easily modified and copied, so they need to be properly protected. In addition, many common methods of exchanging such files, such as email, are inherently insecure. Public-key cryptography provides two ways to protect data integrity and authenticity. Firstly, digital signatures using the public-key infrastructure can only be applied by the signer (who holds the private key), but could be verified by anyone (using the public key). Secondly, the public-key infrastructure may be used to set up encrypted communication channels that are resistant to eavesdropping.

Finally, there is a problem with how electronic health records are handled. Most clinics that use such systems currently outsource record-keeping to other companies. To protect their commercial interests, these companies do not document how to access stored data. This is fine if a clinic keeps using the same company, but there is no way to make backups, for example, in preparation of switching to a different company. By entrusting business records to third-parties that have purely commercial interests in mind, clinics allow these parties to hold their business hostage. Some companies do provide backups in exchange for payment, but this is hardly flexible.

Thus, there is a pressing need for an open source record keeping and practice management system that is flexible, secure, and transparent. Some people assume that transparency of protocol means insecurity. On the contrary, there are many secure systems whose programming is fully open for auditing. One question remains: how is such a system commercially viable? By closing down the interface and creating vendor lock-in situations, current medical record-keeping vendors are able to ensure a constant revenue stream in the short run. However, there is much business to be done providing hosting and support for these systems. Most physicians would not want to maintain their own systems, and would rather rely on service providers. Those who are more knowledgeable in software development may even be able to contribute to the project. Canonical, for example, offers a totally free and open operating system, while continuing to grow because of their successful support business.

…

Right now doctor is cutting across some vessels & ligaments that connect the ovaries to the uterus.

We are cutting the neck of the cervix right now. This is done so doctors can put a graph or a mesh around it to hold the vagina in place.

Dr. Rozeboom has removed the uterus now and will place it near the belly & remove it later.

Having a good assistant surgeon like Dr. McCarron is very important. He is helping move the bowel out of the way to put the mesh in place.

Surgical nurses are getting equipment for removing the uterus ready. The tool twists the uterus and cuts it in tiny pieces.

…

Several photographs were published along with the textual stream. (The patient knows about this event, by the way, and agreed to participating weeks prior to the surgery. Sarah Corizzo, who wrote the updates, was sitting outside the sterile field, ensuring patient safety. The surgeon was not tweeting himself, obviously.)

From an observer’s point of view, the twittercast provided a simple and accessible account of a typical procedure. Such use of technology not only brings medical insight to the public, but it also helps alleviate fears of something that may be difficult to understand. There was quite a bit of buzz around this stream of updates, ranging from disgust to curiosity, but as a student I found the experience immensely educational and fascinating.

Facebook is a different networking platform that centers on building communities as opposed to open publishing of information. Through it, patients are beginning to send private messages to physicians who also use the service. A half-year ago, a Deloitte survey found that “55 percent want the ability to communicate with their doctor via email to exchange health information and get answers to questions” and showed that a substantial population of patients would like to be able to communicate online with their doctors.

Doctors are not as enthused about conducting their work online, however. Traditionally, doctors have preferred a direct relationship with the patients, avoiding intermediating factors. A doctor may be able to gain some understanding about a patient’s condition over the phone, for example, but would usually ask for a formal visit. The reasons for this are threefold:

• Face-to-face interaction allows the doctor to find out more about the patient’s condition. Non-verbal communication is impossible to achieve online, and a physical examination is required for most diagnoses and treatments. While it is sometimes possible to make a diagnosis online, a direct visit is often preferable because it allows the doctor to actually treat the disease.
• Those who participate in online communities often expect each other to be instantly available; after all, the purpose of such networking is improve availability during times when people are not able to see each other. A medical professional who is online for personal reasons may be expected to respond instantly to their patients’ queries. While doctors do want to help as many individuals as they could, they also need time away from their practice. Online interactions thus blur the line between private life and business.
• Finally, insurance companies typically do not reimburse doctors for interacting with patients online, and social networking tends to consume a lot of time. In addition, doctors have the same liability whether they work with their patients online or away from the keyboard.

While it is not always medically appropriate to diagnose and treat illnesses online, social networking does hold potential in healthcare. Care and cure go hand-in-hand in medicine, and online communication can enhance the patient-doctor relationship. Such communication may include notifications about prescription refills and clinical visits, answers to general health questions, and public education. The aforementioned surgical twittercast is an excellent educational use of networking technology. In a world where online networking has gained substantial momentum, traditional modes of communication may no longer be sufficient for patients.

The healthcare system is changing, however. Many current college and medical students already participate in online networking and are likely to continue doing so in their careers, if only for housekeeping tasks. Insurance companies are also beginning to recognize the work that physicians do for their patients online.

People are complex creatures, and so medicine is a complex subject encompassing multiple fields of discipline. Many technologies have been developed to advance medicine to its current form, but one particular aspect of medical technology remains elusive: how to supplement physician’s medical knowledge using computers. Now, I know what you’re very likely thinking: when I catch a cold I want to see a doctor, not a machine! I too would much prefer to see a doctor. However, it must be noted that machines are already playing a significant role in medicine and they could propel medicine so much farther if we just knew how to use them properly.

Medical intelligence is a branch of artificial intelligence dedicated to using machines to help diagnose and treat diseases. Many doctors see dozens of patients every day, and must have amazing physical and mental stamina to serve each patient reliably. Wouldn’t it be nice for a doctor to have a PDA capable of suggesting courses of action, allowing her to focus on the more complex aspects of treatment without tiring as easily? Such a system would not only streamline the process of seeing patients, but also improve speed and accuracy. The question, then, is this: how do we build a computer system with intelligence comparable to a doctor’s?

The answer is simple: send it to school! This is how we learn as humans, so this is how our mechanical doctors must learn. But we don’t send it to just any school; we let it apprentice with real doctors all over the world, so that it may have the knowledge to treat the whole world of disease. As soon as it learns something new, the knowledge becomes instantly available to all doctors using it. Medical knowledge has never spread so quickly.

Current medical intelligence systems are inefficient for a few reasons:

• given the vastness and complexity of medical knowledge, it is difficult to construct a single program to deal with all of it
• because medical intelligence is fragmented, it could only be used in isolated situations where contact with other disciplines is limited
• since the fragments are isolated, it is difficult to network them into a single entity
• without a network, the fragments cannot share knowledge and improve themselves effectively

Therefore I suggest the following:

• create a universal medical intelligence system using the vast distributed computing resources available today
• allow anyone with medical knowledge to use the system
• as the system is used, it improves itself
• every user has access instantly to the latest knowledge that is incorporated

One of my current projects has been to set up a freely available system for building classifiers. I have limited computational resources, but if this takes off it may form the foundation for something greater…

While this series of postings will be about the U.S. healthcare system, it may occasionally include information about the technical side of medicine or even international systems. The primary focus will be on the support frameworks, however. So stay tuned, and join the discussion as we proceed through our investigation.