Major Roles of Technology and Analytics together towards Advancement in Clinical Trials

 

Goshiya A. Shaikh

JSPM’s Charak College of Pharmacy and Research, 1/2, Nagar Rd, Kawade Wasti,

Wagholi, Pune 412207, Maharashtra, India.

*Corresponding Author E-mail: gass.pharmacy@gmail.com

 

ABSTRACT:

For hassle-free management and reduce this errors tour booking 75% as compared to manual methods visual analytics is most sought-after technique in clinical trials for data presentation it evaluates large number of data and makes it easier to review dimensional database model and traditional relational database model explode in self-service mode and can deliver results with Precision and efficiency the graphs charts are few of the examples the promising future looking at vigorously changing market and technologies health care system adopting the good digital Moto for reducing cost and accelerate authorization process. The terabytes of the machineries get involved and management is looking after the easier on confidence systems to work on with Data Analytics the safety and delivery system of Healthcare is improving gradually with clinical professionals leveraging the information technology. The EHR is employed to nullify management in patient care for hassle-free management and reduce this errors to whooping 75% as compared to manual methods.

 

KEYWORDS: Analytics, clinical trials, data visualization, electronic human records, clinical decision support.

 

 

 

INTRODUCTION:

Analytics, the core element of medical research and information has a major role to play. Nowadays as technology advances with the changing trends, even they need to be more newer framed and productive strategies for improvement when it comes to the healthcare system management, patient engagement, diagnosis and spending. Information technology plays a very important role in the advancements of significant business transformations as a main source of competitive advantage [1]. Clinical trials have started adopting analytics far and wide, and are adapting fast with changing tools of better management. Analytics are being looked after as automated solutions and assistance to existing problems and tasks.

 

 

CLINICAL TRIALS:

Clinical trials are research studies that evaluate new ways to improve treatment and quality of life for people with diseases. Clinical trials are important for study of safety and efficacy of drug. Diseases or medicines that are in demand in current studies are focused more and their need is studied while determining their growth, research and development. When a preclinical study is carried out, it makes us aware about the quantity of drugs and their safety margins. Clinical trials are done with a criterion where adverse effects are minimum and therapeutic effects are maximum. Trials should be strictly done under good clinical practices. New drug development can improve quality and lifespan of patient. As clinical trial plays important role in development of new drug, government is trying to safeguard that the safety as well as rights of the human subjects are secure and the quality of the trials completed in India expand to international standards. Indian regulation has set guidelines for informed consent, compensation in case of injury or death and serious adverse events (SAEs) reporting. The clinical trials which are performed in India should comply with schedule Y of Drugs and Cosmetics Act and International Committee of Harmonization-Good Clinical Practices (ICH-GCP) Guidelines for clinical trials [2]. Recruitment of pediatric patients into the clinical studies is still a challenging job [3]. A patient needs to have a certain medical condition to fit in the eligibility criteria to undergo any trials. All detailed information about the trials must be provided to the patient and an informed consent document should be signed. A patient can leave a clinical trial in between but needs to discuss it with the doctor for their safety. Studies are divided in the groups and are randomized and performed based on single or double-blinded type. Clinical trials helps science moves forward [4].

 

ANALYTICAL INTRODUCTION:

A term called as big data analytics has numerous benefits for the improvement of services provided to the patients, to detect any kind of disease spreading as soon as possible, to monitor the quality of the medical and healthcare institutions as well as better treatment methods [5]. It is also very systematic data analysis that helps to improve patient health and provides great opportunities to healthcare professionals [6]. More clinical trials provides strategies to reduce side effects and minimal cost. Educate people by health education program especially risky groups about control, prevention any disease transmission, and correct treatment. Base Camp should be followed frequently by health teams to diagnose and alleviate health problems particularly infectious diseases [7]. Planned way of method development with the aim of drug analysis is critical to success for fast and effective method development [8].

 

ROLE OF ANALYTICS IN CLINICAL TRIALS:

The pharmaceutical industry has prime responsibility for the safety of medicines, from the start of drug development and thereafter throughout the lifetime of the drug [9]. Electronic Data Capture Electronic Data Capture is used to record and report the outcomes of the trials and to access and assess the record, which is very convenient rather than book records that are done manually. It took 20 years for the industry to use this technology [10].

 

Analytics uses different processing-based techniques that include mathematical and algorithmic base. [11] In addition, the techniques used are text-mining, natural language processing and visual analytics to produce expressive, extrapolative, prescriptive model to scrutinize and derive insights from data. Natural language processing and text mining involve the retrieval and extraction of non-retrieval information from unstructured, semi-structured, and structured text, such as discovering operating site impurities through text mining of unstructured clinical notes in an integrated electronic medical record [12,13].

 

Analytics gives the health information and data, decision support, patient support, electronic communication and connectivity updated reporting and population health. It helps to know at a very early stage if condition of any patient is not as good as expected. Health analytics bids numerous methods for the potential enhancement of patient care [14].

 

Analytics has a common data model in which EHR has been involved which is processed by means of different analytic techniques to stratify patients as high risk. Unlabeled and free text databases such as mammography data can be transformed into searchable and accessible collections that are usable for large-scale health [15]. Analytics can supplementary real-time analysis of physiological data streams in the neonatal Intensive Care Unit for early detection of worsening medical conditions with considerable accountability and accuracy. [16].

 

The rule-based systems that are already in use can be enhanced by employing analytics methods. Electronic Health Record (EHR) helps in decision making in clinical workflow. Clinical decision support (CDS) systems that is clinical decision support systems they help in reducing errors and give precise clinical outcomes for example in pediatric Intensive Care units [16,17]. The Clinical decision support (CDS) systems, which are designed to protect medication errors are mostly based on commercial available software packages which rely on relatively simple rules [18].

 

Analytics has also been playing a major role in Healthcare applications outside of the traditional inpatient and outpatient care settings where wearable monitors are used when by the patients at home [19]. Such health monitoring systems also cut down Health Care costs and their reduced by disease prevention and enhance the quality of life with disease management and can be tailored to specific uses such as intelligent health monitoring of the elderly in nursing homes and for individuals with dementia or Parkinson's disease [20,21,22].

 

Finance is another role played by analytics in clinical trials that is not only by reducing cost but it also reduces time and human efforts, it shows that instead of doing hard work one should do smart work also analytics is an effective tool in Healthcare. Before finding errors in any buildings or rule based approaches or any audits were done manually also identification of, simple errors were also done manually and due to that, it was really time-consuming and error-prone. Healthcare organizations can use analytics not only to improve building practices browser to better manage resource allocation and demand throughout the organization one example is to use analytics to determine these factors impacting a patient length of stay [20,18]. Cost-reducing actions have been directed and restrained using Analytics, and have profits making interpositions such as using promoting analytics and Graphical information systems to aim catchment areas [20,24]. A case in point to be given, one organization use analytics and concluded that ineffectiveness at the radiology department unfavorably extended a patient span of stay on preliminary estimates. The authors then advocated the use of proactive analytics assessment of network of activities to boost organizational proficiency [29]. 

 

RECONNOITERING SPECIFIC ANALYTICS METHOD: VISUALIZATION:

Visual analytics is the most trending and effective tool in scientific field. Large amount of data is stored and when desired it can be viewed in very less time using visual analytics software. Visual analytics is widely used because it evaluates large and complex data sets and makes it easier for one to review. There are two different database models one is dimensional database model and the other is traditional relational database model. Dimensional database model is used nowadays because it stores a large set of data and it makes the data simple and easy to use by using Visual analytics tools. Visual analytics also displays diagrams and graphs in order to identify when explore data. It can also be used to visualize clinical trial data; it gives support and cuts down work done manually to a considerable extent. It mainly has three benefits first data can be explored in self-service mode, second the complete ideas can get a clarity, Precision and efficiency in visual graph instead of tabular data, third that one can view large volumes of filter data in lesser time compared to traditional ways. [5].

 

Visual analytics is the most essential part of clinical research and site selection in which visualization performance analytics methods go hand in hand. Visual analytics techniques can help understanding performance indicators in optimized site works. Visual analytics can be a helping hand when findings need to be clear and easy to analyze and evaluate. In addition, visuals can improve communication and interoperability. With this in addition to it, Complex ideas can also get Precision and transparency.

 

Data exploration and hypothesis generation can also be enabled using visual analytics tools within a specific group of data and it is a way that facilitates better understanding. Visual analytics techniques are utilized in three areas for analysis: 1) business purposes, 2) clinical operations and 3) scientific research in various Healthcare related fields such as genomics immunology and epidemiology [32,33,34,35].

A research group used a visual analytics application in order to visualize EHR data with an objective of improving patient’s care and they also described the usage of the tool for chore that were difficult to retort with the providers EHR software studying: hospital room allocation patterns, performing follow-up studies and replicating studies among others [18]. To provide CDS at the point of care the data visualization can also be used as a visual analytic tool [36,37].

 

Focus on other uses as well that vision and it helps that would be dashboards attach Hospital include monitoring EHR alerts as well as dashboard for monitoring hand hygiene, nursing metrics, supply chain performance, and other into clinical guidelines. In Literature a lot of example the available division undertakes has been helping health in Healthcare such as to track symptom evolution during disease progression, to track performing pharmacokinetic and pharmacodynamics analysis, building detection models for disease surveillance and visualizing outcome data [38,39,40,41].

 

One way to enhance the process would be using social media as a platform. Social media in todays generation has more power than any other platform. For instance if volunteers are wanted for any clinical trials we can make a page on every social media and can broadcast it and people who fit in the eligibility criteria can opt in for the same [42].

 

Additional Method -

BIOMARKERS APPLICATION IN CLINICAL TRIALS:

Latterly, biomarkers has the premier role in clinical oncology. For the evaluation of a drug therapy we employ "Imaging Biomarkers" which is well known on the field of "pharmaco imaging". In the senior years it has become endorsed. We are using this novel technology in Computed technology (CT), magnetic resonance technology (MRI) and in position emission tomography (PET). Biomarkers has been utilized for analysis of serum levels in medicine and drug development process. But in the recent times, use of biomarkers from imaging to genomics gripping attentiveness.

Some characteristics/features of imaging biomarkers are as follows

1.     We are utilizing non- invasion imaging technique for management and diagnosis of disease on daily basis because of this now we clearly understood pathophysiology.

2.     As imaging biomarkers are directly related to the phenotype of disease so now it become accessible to acknowledge co-relation between drug therapy and its interaction / effects.

3.     Imaging biomarkers illustrate structural and functional hallmarks which made it easier to comprehend bioactivity of drug compounds.

4.     To promote "translational research" it plays prominent role as it provides assessment in human as well as in animals.

 

To summarize, biomarkers focuses on results and integrity of imaging rather than their theoretical applications. [43]

 

FUTURE OF ANALYTICS IN CLINICAL DATA:

Most hospitals uses the same analytical procedure for the care of various diseases and disorders as those used almost ten to fifteen years ago, so we need to do better for the patients in clinical trials. The main motto of digital health care is to lower the costs and accelerate the drug authorization. In clinical trials, patients have a right to access data and technology that could influence their health. The floor of hospitals generated about tera bytes of data, which is full of electronic health records. Physiological medical monitors like medical monitor pulse oximetry, these are artifacts and they may produce faulty conclusions so for that analytics can be employed with machine learning, neural network in data auditing and it can use to detect error prior to analysis [42]. Creation of EHR has bring about large amounts of data of hospital and other health care organizations to cope and evaluate various purposes. For professionals it is increasing in demand [43,44]. Via EHRs, telemedicine and evidence based medicine using tools such as clinical decision support systems and data analytics, the safety and delivery of healthcare is improving and even clinical professionals leverage the information technology [45, 46]

 

CONCLUSION:

The future of health care analytics will involve of an ever-increasing ultimatum for and application of erudite analytics methods and tools, for instance-visual analytics to discover and scrutinize data with the aims of improving patient care, growing proficiency, elevating resource utilization and distribution, and augmenting decision-making at both the clinical and enterprise levels. Health care professionals with experience and expertise in clinical informatics will be required to put up a strategy and implement the forthcoming analytic applications and advances of EHR and communication systems to meet those necessities.

 

REFERENCES:

1.      Dimpy Sachar, Harshmeet Kaur. Impact of Digitalization in an Organization and its importance in Knowledge and Value Management System. Asian J. Management; 2017; 8(1): 37-48. doi: 10.5958/2321-5763.2017.00007.5

2.      Kalpana Kamnoore, M P Venkatesh, Balamuralidhara V, T M Pramod Kumar. Regulatory requirements for conducting Clinical Trials in India. Research J. Pharm. and Tech 2020; 13(3): 1517-1522. doi: 10.5958/0974-360X.2020.00276.0

3.      Nilima Kanwar Hada, Mahendra Singh Ashawat. Ethical Conduct of Paediatric Clinical Trials; Issues and Challenges. Res. J. Pharm. Dosage Form. and Tech. 6(3):July- Sept. 2014; Page 156-160.

4.      ThePancreasPatient, youtube channel, topic-understanding clinical trials, http://www.AnimatedPancreasPatient.com

5.      Clinical Trial Performance Analytics: Data Is the Core of Research, https://conductscience.com/clinical-trial-performance-analytics-explained/.

6.      Simpao, Allan F., et al. "A review of analytics and clinical informatics in health care." Journal of medical systems 38.4 (2014): 45.

7.      Manohar D. Kengar, Kiran K. Patole, Akshay K. Ade, Sumesh M. Kumbhar, Chetan D. Patil, Ashutosh R. Ganjave. Introduction to Pharmacovigilance and Monitoring. Asian J. Pharm. Res. 2019; 9(2): 116-122. doi: 10.5958/2231-5691.2019.00019.4

8.      Nisreen M. Ibraheem. Controlled Clinical Trials: Comparison The efficacy of some Single Topical Scabies Treatment Modalities versus Combined Topical Modalities. Research J. Pharm. and Tech. 2019; 12(3): 1361-1368. doi: 10.5958/0974-360X.2019.00229.4

9.      Hamid Khan. Analytical Method Development in Pharmaceutical Research: Steps involved in HPLC Method Development. Asian J. Pharm. Res. 2017; 7(3): 203-207. doi: 10.5958/2231-5691.2017.00031.4

10.   C. Vijayabanu, R. Renganthan, S H Shahana Hameedha, J. Arokiya Monica4;. Clinical Trials in Digital Era on Pharmaceutical Industry. Research J. Pharm. and Tech 2017; 10(11): 4047-4050. doi: 10.5958/0974-360X.2017.00734.X

11.   Kudyba, Stephan P. Healthcare informatics: improving efficiency and productivity. CRC Press, 2010.

12.   Erhardt, Ramón AA, Reinhard Schneider, and Christian Blaschke. "Status of text-mining techniques applied to biomedical text." Drug discovery today 11.7-8 (2006): 315-325.

13.   Michelson, James D., Jenna S. Pariseau, and William C. Paganelli. "Assessing surgical site infection risk factors using electronic medical records and text mining." American journal of infection control 42.3 (2014): 333-336.

14.   Gotz, David, et al. "ICDA: a platform for intelligent care delivery analytics." AMIA annual symposium proceedings. Vol. 2012. American Medical Informatics Association, 2012.

15.   Rojas, Carlos C., Robert M. Patton, and Barbara G. Beckerman. "Characterizing mammography reports for health analytics." Journal of medical systems 35.5 (2011): 1197-1210.

16.   Blount, Marion, et al. "Real-time analysis for intensive care: development and deployment of the artemis analytic system." IEEE Engineering in Medicine and Biology Magazine 29.2 (2010): 110-118.

17.   van Rosse, Floor, et al. "The effect of computerized physician order entry on medication prescription errors and clinical outcome in pediatric and intensive care: a systematic review." Pediatrics 123.4 (2009): 1184-1190.

18.   Korhan, Esra Akin, et al. "Determination of Attitudes of Nurses in Medical Errors and Related Factors." International Journal of Caring Sciences 10.2 (2017).

19.   Resetar, Ervina, et al. "Customizing a commercial rule base for detecting drug-drug interactions." AMIA Annual Symposium Proceedings. Vol. 2005. American Medical Informatics Association, 2005.

20.   Simpao, Allan F., et al. "A review of analytics and clinical informatics in health care." Journal of medical systems 38.4 (2014): 45.

21.   Tseng, Kevin C., Chien-Lung Hsu, and Yu-Hao Chuang. "Designing an intelligent health monitoring system and exploring user acceptance for the elderly." Journal of Medical Systems 37.6 (2013): 9967.

22.   Baig, Mirza Mansoor, and Hamid Gholamhosseini. "Smart health monitoring systems: an overview of design and modeling." Journal of medical systems 37.2 (2013): 9898.

23.   Schouten, Pieter. "Big data in health care: solving provider revenue leakage with advanced analytics." Healthcare Financial Management 67.2 (2013): 40-43.

24.   Bradley, Paul, and Jell Kaplan. "Turning hospital data into dollars: healthcare financial executives can use predictive analytics to enhance their ability to capture charges and identify underpayments." Healthcare Financial Management 64.2 (2010): 64-69.

25.   Buell, Dan. "Leveraging data and analytics to generate new revenue." Healthcare Financial Management 67.4 (2013): 40-44.

26.   Costantino, Mary E., et al. "The influence of a postdischarge intervention on reducing hospital readmissions in a Medicare population." Population health management 16.5 (2013): 310-316.

27.   Kudyba, Stephan, and Thomas Gregorio. "Identifying factors that impact patient length of stay metrics for healthcare providers with advanced analytics." Health informatics journal 16.4 (2010): 235-245.

28.   Whitham, Diane, et al. "Development of a standardised set of metrics for monitoring site performance in multicentre randomised trials: a Delphi study." Trials 19.1 (2018): 557.

29.   Yang, Eric, et al. "Quantifying and visualizing site performance in clinical trials." Contemporary clinical trials communications 9 (2018): 108-114.

30.   Tufte, Edward R. The visual display of quantitative information. Vol. 2. Cheshire, CT: Graphics press, 2001.

31.   Thomas, James J., and Kristin A. Cook. "A visual analytics agenda." IEEE computer graphics and applications 26.1 (2006): 10-13.

32.   Kumasaka, Natsuhiko, Yusuke Nakamura, and Naoyuki Kamatani. "The textile plot: a new linkage disequilibrium display of multiple-single nucleotide polymorphism genotype data." PloS one 5.4 (2010): e10207.

33.   Naumova, Elena N. "Visual analytics for immunologists: data compression and fractal distributions." Self/nonself 1.3 (2010): 241-249.

34.   Chui, Kenneth KH, et al. "Visual analytics for epidemiologists: understanding the interactions between age, time, and disease with multi-panel graphs." PloS one 6.2 (2011): e14683.

35.   Mane, Ketan K., et al. "Patient Electronic Health Data–Driven Approach to Clinical Decision Support." Clinical and translational science 4.5 (2011): 369-371.

36.   Mane, K. K., Bizon, C., Schmitt, C., Owen, P., Burchett, B., Pietrobon, R., and Gersing, K., VisualDecisionLinc: a visual analytics approach for comparative effectiveness-based clinical decision support in psychiatry. J. Biomed. Inform. 45:101–106, 2012.

37.   Goldsmith, Michael-Rock, et al. "PAVA: physiological and anatomical visual analytics for mapping of tissue-specific concentration and time-course data." Journal of Pharmacokinetics and Pharmacodynamics 37.3 (2010): 277-287.

38.   Perer, Adam, and Jimeng Sun. "Matrixflow: temporal network visual analytics to track symptom evolution during disease progression." AMIA annual symposium proceedings. Vol. 2012. American Medical Informatics Association, 2012.

39.   Sornalakshmi. K, Vadivu. G, Sujatha G, Hemavathi. D. A Survey on using Social Media Data        Analytics for Pharmacovigilance. Research J. Pharm. and Tech 2017; 10(10): 3474-3478

40.   Lo, Yu-Sheng, Wen-Sen Lee, and Chien-Tsai Liu. "Utilization of electronic medical records to build a detection model for surveillance of healthcare-associated urinary tract infections." Journal of medical systems 37.2 (2013): 9923.

41.   Rajwan, Yair G., et al. "Visualizing Central Line–Associated Blood Stream Infection (CLABSI) Outcome Data for Decision Making by Health Care Consumers and Practitioners—An Evaluation Study." Online journal of public health informatics 5.2 (2013): 218.

42.   Kochilas, Lazaros K., et al. "A comparison of retesting rates using alternative testing algorithms in the pilot implementation of critical congenital heart disease screening in Minnesota." Pediatric cardiology 36.3 (2015): 550-554.

43.   Pien, Homer H., et al. "Using imaging biomarkers to accelerate drug development and clinical trials." Drug discovery today 10.4 (2005): 259-266.

44.    Lehmann, C. U., Shorte, V., and Gundlapalli, A. V., Clinical informatics sub-specialty board certification. Pediatr. Rev. 34:525–530, 2013.

45.   Detmer, Don E., Benson S. Munger, and Christoph U. Lehmann. "Clinical informatics board certification: history, current status, and predicted impact on the clinical informatics workforce." Applied clinical informatics 1.1 (2010): 11.

46.   Google search. URL: https://www.accenture.com/dk-en/insights/life-sciences/future-clinical-trials.

 

 

 

Received on 20.09.2020            Modified on 25.11.2020

Accepted on 14.01.2021      ©Asian Pharma Press All Right Reserved

Asian J. Res. Pharm. Sci. 2021; 11(2):155-159.

DOI: 10.52711/2231-5659.2021-11-2-11