Novel drug delivery systems have been the subject of research for decades. This is because of a host of limitations with oral administration, the most widely-used route for administering medicine and challenges with several available alternatives. One of the most exciting new areas consist of pulmonary drug delivery systems, by which medication is delivered through the lungs. The harnessing of processes used in microelectronics and nanotechnology holds forth promise of a revolution in therapeutic medication.

The oral route: difficulties across generations, affects compliance
In spite of assumptions about convenience, oral dosage forms are not universally accepted. A recent study called ‘A Hard Truth to Swallow’ showed that over 55% of people, regardless of age or gender, faced “swallowing difficulties when taking tablets or capsules.” The study, by Spiegel Institut in Mannheim, surveyed 2,000 people in Germany and the US.
Surprisingly, although 44% of participants older than 65 years were affected, 70% of respondents in the 16–34 age group also reported problems – for example, with regard to swallowing, taste or odour, and irritation to digestive tract. This, in turn, clearly impacts on compliance.

The challenge of hepatic first pass metabolism
Broadly speaking, oral drug delivery faces challenges of low bioavailability and limits in the duration of therapeutic action.
A key problem consists of what is known as hepatic first pass metabolism (or pre-systemic metabolism). This is a phenomenon, by virtue of which the concentration of a medicinal product is reduced (in some cases, very sharply) before it reaches systemic circulation. Such a process involves the liver, to where a drug is borne from the gut wall via the portal vein, before reaching the rest of the body. The liver is biochemically selective and metabolizes drugs, in some cases to a massive extent, transferring only a part of the active ingredients to the circulatory system. As a result, there are marked differences in the effectiveness of oral drugs, due to variations in the degree of first pass metabolism.

IV administration
Bioavailability (BA) is defined as the proportion of an administered dose which reaches systemic circulation, and is considered one of the principal pharmacokinetic properties of drugs.
Given this, intravenous (IV) administration of a medicine means 100% bioavailability, which is why some consider IV administration to be a form of gold standard. The effects of IV medication are dependable. The entire administered dose immediately reaches systemic circulation. In turn, this allows for precise titration against a patient’s response.
However, IV administration has several limitations. It requires a functioning cannula, typically in a hospital, clinic or a patient’s bedsite – both due to procedural requirements as well as the need to avoid infections. Together, the latter entail that IV requires more staff and money. Finally, the process of cannulation can be distressing, especially in small children or those with needle phobias.
Indeed, even in a hospital setting, most IV patients are switched as soon as possible to oral therapy; the only exceptions are those critically ill or unable to absorb oral medications.

Injections, suppositories and topicals
Oral medications have sought to address some of their own inherent and long-evident limitations. These included slow- or extended-release formulations. However, as far as the issue of hepatic first pass metabolism is concerned, there is little reason to celebrate.
Instead, research has been focused on alternative routes of administration which, like IV, avoid first-pass effects, but do not necessarily require a clinical setting. Traditional alternatives include topical medications, intramuscular/subcutaneous injection and rectal administration via suppository drugs. Each of them continues to be investigated. All have pros and cons.

Topical administration is non-invasive and straightforward. It is also associated with significant patient satisfaction. However, most drugs have a high molecular weight and are poorly lipid soluble, and cannot be absorbed via skin or mucous membranes. Even when they are, the process is slow.

Injections have far better absorption profiles, and are preferred for drugs with low oral BA levels or those requiring a long duration of action, such as some psychotropic medications. Its onset is also more rapid than oral, or the topical route.  However, absorption via injection can be unpredictable, when a patient is poorly perfused. Like IV, injections can also frighten children and needle phobics.
On their part, rectal suppositories also have good absorption since hemorrhoidal veins drain directly into the inferior vena cava, and thus bypass the hepatic metabolism challenge. However, although onset of action is fast, the duration of action is short. In addition the absorptive ability of the rectum mucosa is lower than that of the small intestine.  Finally, rectal administration can provoke inherent feelings of resistance or revulsion, especially in adults.

Pulmonary delivery: the promise
In the light of all these, pulmonary drug delivery systems (PDDS) may offer a promising new alternative.
PDDS offers extremely fast absorption and onset of therapeutic action, due to the large surface area of the respiratory endothelium and its thinness. The plasma profiles after PDDS closely duplicate that of IV. As a result, it serves to reduce dose size and dosing intervals. This also helps to diminish side effects.
Aerosols and intra-tracheal inhalations
PDDS administers drugs to the lungs via the nasal or oral route, using two techniques: aerosol and intra-tracheal inhalation.
Aerosols provide more uniform distribution and greater penetration into the peripheral (alveolar) region of the lung. However, aerosol delivery is expensive. It also faces difficulty in measuring precise dose, when inside the lungs
Intra-tracheal inhalation (or instillation) is a much simpler and cheaper process than aerosols. It uses a syringe to deliver a medicated solution into the lungs. This addresses one of the major problems with aerosol delivery – to quantify the amount of drug delivered into the lungs.
Particle aerosol inhalers, in particular, are now increasingly commonplace for treating respiratory disease. Nebulizers, dry powder inhalers (DPI) and pressurized metered dose inhalers (pMDI) allow for local delivery of high concentrations of therapeutics in the lung, in many cases avoiding toxicities associated with oral or even injectable therapies.
Together, pMDIs and dry powder inhalers (DPIs) are estimated to deliver more than 90% of inhaled medications.

New PDDS applications
PDDS has also established its utility in emergency situations, given its absorption advantage.
One of the highest opportunities in PDDS is seen for macromolecules such as peptides and proteins, which usually need to be administered via injections (e.g. insulin). However, more experience with PDDS is required, especially about potential side effects after routine use.

Challenges for PDDS
PDDS, however, still faces limitations.
The first is that the particles which are to be inhaled need somewhat precise and reproducible aerodynamic factors related to diameter and density, as well as velocity, in order to successfully transit the nose and mouth and their filtration systems – which are designed to keep such matter out. As a result, there is always a certain degree of deposition of drugs in the nasal and oral passage.
Secondly, once in the lungs, the particles must overcome the pulmonary phagocytic barrier to release drugs at the required rate in order to achieve the intended therapeutic effect. For successful PDDS, designers must take careful account of properties such as pH value, ionic strength etc. which can affect the release of the drug, and thus its therapeutic effects.
Finally, PDDS is always accompanied by wastage of the drug. Due to material limitations of physics, a significant part of the drug is retained in the container.

As a result, pulmonary drug delivery remains inefficient, sometimes strikingly so. In spite of the growth in their availability, dose delivery efficiencies for dry powder asthma inhalers is estimated at just 3-15% for children and 10-30% for adults. The most advanced pMDIs deliver just 60% of inhaled material to bronchial airways. These were some of the findings in a review entitled ‘Targeted drug-aerosol delivery in the human respiratory system’, published in a 2008 issue of the  ‘Annual Review of Biomedical Engineering’.

Lessons from microelectronics manufacturing
In recent years, researchers have sought to address some of the key challenges of PDDS.
These, as we have noted, concern aerodynamic factors such as diameter and density of the particles.
Conventionally, pharmaceutical aerosols for DPIs are manufactured by milling (micronization) or spray drying techniques. These lead to wide particle size distributions and limited control over particle shape. Additional challenges include the need for non-agglomerating powders with the active ingredients, especially when they concern products such as proteins and monoclonal antibodies.
Recently, some manufacturers have sought to learn from the microelectronics industry by seeking to generate high-precision aerosol particle-based respiratory drug delivery systems. Such particle engineering techniques have shown special promise for targeted pulmonary delivery, when combined with inhalable nanoparticles, especially in solid-state dry powders.

PRINT and nano-particles
One leading example is called PRINT (Particle Replication in Non-Wetting Templates) which co-opts the precision and nanoscale spatial resolution in lithographic techniques used by the microelectronics industry, to provide  unprecedented control over particle size and shape.
A 2013 edition of ‘Angewandte Chemie International Edition’ describes PRINT as “a continuous, roll-to-roll, high-resolution molding technology which allows the design and synthesis of precisely defined micro- and nanoparticles.”
PRINT’s micromolding enables the formulation of particle systems of small molecules, biologics and oligonucleotides – all of which hold special promise for next-generation therapeutic PDDS applications.  In itself, the technique is highly versatile and is also being researched for application to oral and topical dosage forms.
The PRINT manufacturing process has begun to be tested for clinical applications. In the US, Liquidia Technologies and Accelovalence have completed Phase I and II studies to use PRINT to produce GMP-compliant bioabsorbable particles that improve the immune response and efficacy of seasonal influenza vaccines, at a scale relevant to clinical development.

Other approaches: iSPERSE
Other research efforts focus on chemistry. For example, another US firm, Pulmatrix, has recently been awarded a patent in Europe for iSPERSE, a PDDS systems based on proprietary cationic salt formulations which can accommodate high drug loads and large drug molecules in highly dispersible particles, in a manner claimed to be both robust and flexible enough to accommodate multi-drug formulations. The advantage of iSPERSE is that it has shown superior delivery capabilities compared with conventional dry powder technologies which use lactose blending or low-density particles.

Emerging markets: major new opportunities
Such efforts are likely to be rewarded given the large number of blockbuster respiratory products going off-patent – with growing demand in the developing world. In Latin America, for example, COPD deaths have risen by 65% in the last decade, while figures indicate 12 million people affected by the disease in India. In China, in China, chronic respiratory diseases have become the second leading cause of death.
We have seen that the generic capsule-based dry powder inhaler (DPI) segment in developing markets shows a lot of promise and demand is rising. However, when it comes to these products, patients in developing markets have not been best served by strategies employed by major pharmaceutical companies in the US and Europe, which have developed DPIs customized exclusively for one specific active pharmaceutical ingredient (API).

In February last year, the US Food and Drug Administration (FDA) cleared the first medical device which uses artificial intelligence (AI) to provide clinical decision support for stroke. The Viz.AI Contact application uses an AI algorithm to identify a suspected stroke and notifies a specialist more quickly than was previously possible. Faster treatment, in turn, lessens the extent of a stroke or its progression. Subsequent FDA clearances and a recent decision to formalize regulations for such evaluations are likely to stimulate further innovation and acceptance of AI devices.

Saving time
Viz.AI Contact analyses CT images of the brain and sends a text notification by smartphone or tablet to a vascular neurologist or a neuro-interventional specialist, should a large vessel occlusion (LVO) be suspected. The algorithm automatically notifies the specialist at the same time that a review of the images is being conducted by a first-line provider. This is faster than the usual standard of care where patients wait for a radiologist to firstly review CT images and then notify a neurovascular specialist.

Retrospective study and real world data
Viz.AI, Inc., which developed the Contact application, submitted a retrospective study of 300 CT scans. This compared the performance of the image analysis algorithm and notification functionality against two trained neuro-radiologists.
Real-world evidence from a clinical study demonstrated quicker notification of a neurovascular specialist, in cases where blockage of a large vessel in the brain was suspected. In more than 95 percent of cases, the automatic notification was faster, saving an average of 52 minutes (with a range of between 6 and 206 minutes).

De Novo premarket review
The Viz.AI application was reviewed by the FDA through its De Novo premarket review process, a regulatory pathway for new types of medical devices that carry low to moderate risk, but lack a legally marketed predicate device to base a determination of equivalence. The FDA action creates a new regulatory classification, allowing other devices with the same medical imaging intended to obtain marketing authorization by 510(k) notification. One of the first areas to benefit from Viz.Ai will be AI or computer-aided triage devices, whose potential in fields such as emergency medicine is likely to be vast. Viz.AI, Inc., itself is developing Viz ICH, which uses AI to automatically detect intra-cerebral hemorrhages and triage the patient directly to the neurosurgeon on call.

Decision support for breast cancer screening
Nine months after FDA approval of Viz.AI, at the 2018 Radiological Society of North America (RSNA) annual meeting in November, Siemens Healthineers showcased the AI-based features of syngo.Breast Care, a mammography solution. syngo.Breast Care aims to provide interactive decision support for breast cancer screening.
Transpira, Siemens’ mammography reading software, is based on deep learning techniques, with training provided via over 1 million images. As a result, syngo.Breast Care’s AI-based algorithms evaluate and interpret individual lesions as well as 2-D mammograms and 3-D tomosynthesis. The system also sorts and scores cases on a 10-point scale, based on radiologist preferences of risk factors such as lesions, micro-calcifications and other abnormalities.
Siemens Healthineers aims to integrate interactive decision support into syngo.Breast Care, and reduce radiologists’ workload for the interpretation of mammograms. This has become especially challenging, given rapid growth in the use of techniques such as 3-D breast tomosynthesis.

Small firms also in play
Smaller firms have also targeted this area. ICAD’s ProFound AI, for example, also leverages AI to detect cancer in breast tomosynthesis. The software, which was FDA cleared less than a month after syngo.Breast Care was unveiled, examines every image in a tomosynthesis scan, detects malignant soft tissue densities and calcifications.
Profound AI estimates a ‘Certainty of Finding’ for each detection and, like the classification system in syngo.Breast Care, assigns Case Scores to each case to represent confidence that a detection or case is malignant. The scores are represented on a scale from 0 to 100 percent, with higher scores indicate high confidence levels in malignancy. This, in turn, is expected to improve detection, lead to fewer patient recalls and save mammographers time in reading images. This makes it geared toward screening, although it can evidently be used for diagnostic studies.

AI at inflection point
The above examples demonstrate that the use of AI is now close to an inflection point in terms of clinical decision support tools. These will provide physicians usable interactive and dynamic pathways which move beyond decision support to true evidence-based decision making, along with personalized care recommendations.
To many experts, AI seems to have been the missing link for tools that assist radiologists in improving appropriateness of follow-up recommendations for incidental findings, and thereby to enhance adherence to guidelines available at point of care. One of the consequences of such AI-assisted tools will be to reduce the variability in follow-up recommendations, as well as unnecessary imaging studies.

Diagnosis and decision support versus analysis and detection
Maximum attention to AI in imaging is currently on diagnosis and decision support. AI in areas such as quantitative analysis and assisted detection can be considered a spin-off from automation, which has been around for a longer period of time, but reinforced more recently by machine learning.
Automated quantification tools are now sufficiently mature and routinely accepted in the market. AI algorithms are used to make measurements from imaging exams and perform calculations which were previously manual and time-consuming. AI-driven quantitative analysis tools also are being used in data analytics for data mining electronic medical records, billing systems, patient scheduling and even in stand-alone scanners. Mined data range from radiation dose used by particular technologists for specific protocols to predictive analytics that pinpoint spikes in demand by day and time, and schedule back-up staff in the radiology department.
By contrast, the application of AI (and even automation) in medical fields such as computer-aided diagnosis and clinical decision support is very recent, and is likely to be some time before they become commonplace. The principal focus on AI use for image diagnosis is where timing is crucial – such as a heart attack or stroke (e.g. Viz.AI Contact). Closely related areas include tools to reduce review time for complex exams, and help triage patients needing more immediate care or other kinds of back-up.

Other new AI imaging applications
One exciting new entrant into AI in imaging is IcoMetrix, from Belgium’s IcoBrain. This FDA-cleared algorithm analyses CT scans to characterize traumatic brain injury, using deep learning to quantify the severity of such typically qualitative indicators of brain injury as hyperdense volumes, compression of the basal cisterns and midline brain shift.
Another FDA-cleared device is Cardio AIMR, which analyses MR images for cardiovascular blood flow. Its developer, Arterys, also has other AI tools to measure and track liver lesions and lung nodules, accelerate display of medical images, and interface with the common desktop Google Chrome browser to display mammograms.

The challenge of integration
Although the FDA is clearing the way for follow-on AI products, there are concerns that the process is constrained to highly specific medical imaging diagnostic reviews. Some radiologists are questioning the viability of new AI software systems, if they require scores of different contracts and integration into a hospital or enterprise imaging system – which would be a problem not only for hospital IT departments but also for legal review.
One of the ways forward is by reconfiguring approaches to enterprise imaging by streamlining workflow. Some vendors are developing bridges between different AI applications. One of the immediate goals is to have AI imaging dovetail into picture archive and communication systems (PACS) as well as vendor neutral archives. For example, Viz.ai software is designed to receive DICOM images directly from any CT scanner to a local virtual machine (VM) behind a network’s firewall.

Major firms nurture start-ups
Leading healthcare technology vendors are also starting to actively partner with smaller companies to provide a combination of in-house and third-party apps via a web-based AI app store platform. One good example of this is Siemens’ Digital Ecosystem, which offers an online menu of apps from Siemens and its partner, including some offering AI-enabled technology. Similar AI app store initiatives are also being taken by other vendors.
At RSNA 2018, where Siemens showcased syngo.Breast Care, IBM Watson said it would begin to partner with AI vendors to offer products on its new AI Marketplace, by offering standardized application programming interfaces (API) for building or integrating third party software and making it available through the IBM Cloud. Smaller vendors have seized such opportunities. French imaging agent vendor Guerbet, for instance, is working with IBM Watson Health to develop AI software to support liver cancer diagnosis and care.
IBM had initially planned to develop and launch its own AI solutions across the healthcare spectrum. However, it had to cope not only with delays in commercializing its own AI products, but small and nimbler start-ups, such as viz.AI getting ahead in obtaining FDA clearance. The biggest setback was MD Anderson ending its partnership on cancer imaging with IBM.
Other major players are also treading similar paths. GE Healthcare’s Edison platform is designed to help accelerate the development and adoption of AI and other new technologies, with clinical partners using Edison to develop and test algorithms and mate them to Edison applications and smart devices. On its part, at RSNA 2018, Philips Healthcare also launched its IntelliSpace Discovery 3.0 visualization and analysis platform to prepare patient data to train and validate deep learning algorithms. The platform is designed specifically to support imaging research.

FDA to formalize De Novo rules
Developments in AI-enabled clinical decision support, like broader AI healthcare applications, are likely to pick up after the FDA decided to formally establish regulations for the De Novo classification process in December 2018. Although the De Novo process is part of the Food and Drug Administration Modernization Act, the FDA Safety Innovation Act and the 21st Century Cures Act, it is currently not covered by any specific regulations. If finalized, the proposed rules are intended to provide clarity and transparency on the De Novo classification process.

St Helier Hospital in the London Borough of Sutton – part of the Epsom and St Helier University Hospitals NHS Trust – has one of the largest renal medicine departments in the UK, and relies on FUJIFILM SonoSite pointof- care ultrasound (POCUS) systems to improve care and patient safety.
Dr Pritpal Virdee, a senior registrar in the department, explained: “We have a very busy renal department offering a wide range of services to people with kidney conditions, including coordination of the South West Thames Renal and Transplantation Unit. We use POCUS throughout the department for both patient assessment and ultrasound-guided interventions – such as line or drain insertions, aspirations, biopsies – performing over 1,000 procedures every year.”
Better for clinicians and patients
“Ultrasound allows you to visualise the target and surrounding structures during these procedures, making them faster and safer. We use POCUS extensively for patient management – for example, during cannulation or when assessing where to position an anaesthetic or pleural drain – or taking biopsies. The systems give you much more confidence when carrying out these procedures, as you can see exactly where you are placing the needle, and that you are not going to cause any damage from positioning them incorrectly. This helps you to reassure the patients as well, especially during kidney biopsies. Physician satisfaction has increased significantly in the department since adopting POCUS for these techniques, as we are much happier with the quality of work that we are now able to perform.”
Investigating the unknown
“POCUS is the ideal partner for quickly scanning a patient with unknown aetiology; I often use the systems for looking at renal patients that come in with acute kidney problems; if there is a delay to get a formal ultrasound examination, I can easily perform a scan myself. In this way, I can identify whether there is an obstruction or dilation of the kidney as soon as possible. It’s also useful for investigating the bladder, as sometimes the bladder scanners can be unreliable. I can simply select the appropriate probe and have a look; it’s really helpful in streamlining the process and providing a better clinical picture.”
“We also have a programme of medical insertion of peritoneal dialysis (PD) catheters under ultrasound guidance, which is quite unusual, and clinicians from other renal departments are now coming here to train in the procedure. This is another key area that POCUS is able to significantly improve as, without ultrasound guidance, there’s a high risk of perforating the bowel or causing injury to another structure. Having a good view of the peritonea shows you exactly what you are aiming for, and we now only perform this procedure with ultrasound.”
Ultrasound is a necessity
“We have always used SonoSite ultrasound systems in the department and have recently acquired two of the latest generation X-Porte systems. Buying the extra systems was a necessity, as we now use ultrasound for so many of our procedures. These instruments offer exceptional image quality and, crucially, they are very straightforward to operate; you can get a clearer view much quicker making each procedure even easier. When we first purchased the systems, we received a brief demo on how to operate them, and everyone started happily using them straightaway. This user-friendliness has been very popular with clinical staff, and the X-Portes have rapidly become our primary POCUS systems in our procedure rooms. This has allowed us to move our older systems onto the wards, which is very convenient as the department is spread over quite a large area. We are always open to learning about new ultrasound applications and, as the physicians here develop more specific interests, we will likely use the built-in tutorials that are supplied with the systems to further develop our skills.”
No turning back
“The X-Porte certainly gives us a level of detail that we’ve never seen before; you can easily visualise tiny blood vessels, or observe any bleeding that occurs during a biopsy procedure – it’s incredible. I have been working with ultrasound since 2010 and, when we first acquired the new instruments, it still took a little time to get used to the resolution available. Until you’ve used a system like the X-Porte, you don’t realise what can be achieved with ultrasound, but we wouldn’t go back now,” Pritpal said.