Aug
13
Tue
2013
Invited Talk: Remote Patient Monitoring – Challenges and Opportunities @ Amriteshwari Hall
Aug 13 @ 11:11 am – 11:44 am
Invited Talk: Remote Patient Monitoring – Challenges and Opportunities @ Amriteshwari Hall | Vallikavu | Kerala | India

Jaydeep Unni, Ph.D.
Sr. Project Manager, Robert Bosch Healthcare Systems, Palo Alto, CA


Remote Patient Monitoring – Challenges and Opportunities

Remote Patient Monitoring (RPM) is gaining importance and acceptance with rising number of chronic disease conditions and with increase in the aging population. As instances of Heart diseases, Diabetes etc are increasing the demand for these technologies are increasing. RPM devices typically collect patient vital sign data and in some case also patient responses to health related questions. Thus collected data is then transmitted through various modalities (wireless/Bluetooth/cellular) to Hospitals/Doctor’s office for clinical evaluation. With these solutions Doctors are able to access patient’s vital data ‘any time any where’ thus enabling them to intervene on a timely and effective manner. For older adult population chronic disease management, post-acute care management and safety monitoring are areas were RPM finds application. That said, there are significant challenges in adoption of Remote Patient Monitoring including patient willingness and compliance for adoption, affordability, availability of simpler/smarter technology to mention a few.  But experts contend that if implemented correctly Remote Patient Monitoring can contain healthcare expenditure by reducing avoidable hospitalization while greatly improving quality of care.

Invited Talk: Applying Machine learning for Automated Identification of Patient Cohorts @ Sathyam Hall
Aug 13 @ 2:40 pm – 3:05 pm

SriSairamSrisairam Achuthan, Ph.D.
Senior Scientific Programmer, Research Informatics Division, Department of Information Sciences, City of Hope, CA, USA


Applying Machine learning for Automated Identification of Patient Cohorts

Srisairam Achuthan, Mike Chang, Ajay Shah, Joyce Niland

Patient cohorts for a clinical study are typically identified based on specific selection criteria. In most cases considerable time and effort are spent in finding the most relevant criteria that could potentially lead to a successful study. For complex diseases, this process can be more difficult and error prone since relevant features may not be easily identifiable. Additionally, the information captured in clinical notes is in non-coded text format. Our goal is to discover patterns within the coded and non-coded fields and thereby reveal complex relationships between clinical characteristics across different patients that would be difficult to accomplish manually. Towards this, we have applied machine learning techniques such as artificial neural networks and decision trees to determine patients sharing similar characteristics from available medical records. For this proof of concept study, we used coded and non-coded (i.e., clinical notes) patient data from a clinical database. Coded clinical information such as diagnoses, labs, medications and demographics recorded within the database were pooled together with non-coded information from clinical notes including, smoking status, life style (active / inactive) status derived from clinical notes. The non-coded textual information was identified and interpreted using a Natural Language Processing (NLP) tool I2E from Linguamatics.

Delegate Talk: Designing electrochemical label free immunosensors for cytochrome c using nanocomposites functionalized screen printed electrodes
Aug 13 @ 3:53 pm – 4:06 pm
Delegate Talk: Designing electrochemical label free immunosensors for cytochrome c using nanocomposites functionalized screen printed electrodes

Pandiaraj Manickam, Niroj Kumar Sethy, Kalpana Bhargava, Vepa Kameswararao and Karunakaran Chandran


Designing electrochemical label free immunosensors for cytochrome c using nanocomposites functionalized screen printed electrodes

Release of cytochrome c (cyt c) from mitochondria into cytosol is a hallmark of apoptosis, used as a biomarker of mitochondrial dependent pathway of cell death (Kluck et al. 1997; Green et al. 1998). We have previously reported cytochrome c reductase (CcR) based biosensors for the measurement of mitochondrial cyt c release (Pandiaraj et al. 2013). Here, we describe the development of novel label-free, immunosensor for cyt c utilizing its specific monoclonal antibody. Two types of nanocomposite modified immunosensing platforms were used for the immobilization of anti-cyt c; (i) Self-assembled monolayer (SAM) functionalized gold nanoparticles (GNP) in conducting polypyrrole (PPy) modified screen printed electrodes (SPE) (ii) Carbon nanotubes (CNT) incorporated PPy on SPE. The nanotopologies of the modified electrodes were confirmed by scanning electron microscopy (SEM). Cyclic voltammetry, electrochemical impedance spectroscopy (EIS) were used for probing the electrochemical properties of the nanocomposite modified electrodes. Method for cyt c quantification is based on the direct electron transfer between Fe3+/Fe2+-heme of cyt c selectively bound to anti-cyt c modified electrode. The Faradaic current response of these nanoimmunosensor increases with increase in cyt c concentration. The procedure for cyt c detection was also optimized (pH, incubation times, and characteristics of electrodes) to improve the analytical characteristics of immunosensors. The analytical performance of anti-cyt c biofunctionalized GNP-PPy nanocomposite platform (detection limit 0.5 nM; linear range: 0.5 nM–2 μM) was better than the CNT-PPy (detection limit 2 nM; linear range: 2 nM-500nM). The detection limits were well below the normal physiological concentration range (Karunakaran et al. 2008). The proposed method does not require any signal amplification or labeled secondary antibodies contrast to widespread ELISA and Western blot. The immunosensors results in simple and rapid measurement of cyt c and has great potential to become an inexpensive and portable device for conventional clinical immunoassays.