Automated statistical inference in medical research meets the criterion of artificial intelligence. John McCarthy, widely recognized as the father of Artificial Intelligence, defined the term AI as “the science and engineering of making intelligent machines”. These would be computer tools, modeled on the functioning of the human mind, as well as technologies and research in the field of fuzzy logic, evolutionary computing, neural networks or artificial life, robotics.
In the field of clinical medicine the concept of AI is widely used , e.g. computer-assisted diagnosis, computer consultation systems (Stanford University, a leading center of AI in medicine), pattern recognition, machine learning, electronic health record EHR, clinical guidelines in a computerized form, diagnosis of the individual diseases and can be further listed.
We have carried out research focused on statistical elaboration of clinical data and some software solutions that automate statistical works.
In research projects defined as epidemiological and statistical, two people (or groups) are involved: an epidemiologist specifying the subject and scope of the analysis, the research plan, and statistician translating the research assumptions into the language of statistics, including the selection of statistical analyzes, finding libraries, correct execution and interpretation of the results analyzes. In the AI approach, an "intelligent computer program" works similarly to a human statistician. The epidemiologist plans the analyzes, saves the assumptions in metadata files for computer aims. Specialized computer program manages the statistical program in every step . First, it creates rational command texts based metafile , as if a programmer would do it using a screen interface and his mind (knowledge, skills, experience). Second, it "uses" a statistical package to execute prepared scripts. Third, he transforms the results of statistical program into a text for epidemiologist in plain tekst.. Statistical program is hidden from the user.
The project currently covers GLM, GLMM, one- and two-level linear and logistic regression models, Cox regression , KM, as well as preliminary data analysis.
If you would like to read the computer implementation of this issue I write in the discussion "AI Statistical Analysis of Clinical Data for Non-Statisticians - part 2: computer implementation"
Dear Hanna Mielniczuk . See the following useful RG link: Article Influential Usage of Big Data and Artificial Intelligence in...
Kindly see also the following useful RG link: Article Is there a role for statistics in artificial intelligence?
Also check please the following useful RG link: Article Applications of Artificial Intelligence and Big Data Analyti...
The following RG link is also very useful: Article Artificial Intelligence in Various Medical Fields With Empha...
Visit also the following useful links: https://clinicaltrials.gov/ct2/show/NCT05176769
https://academic.oup.com/jamiaopen/article/3/3/326/5902619
Respected Aref Wazwaz Sir,
These all are must helpful and fruitful for Hanna Mielniczuk Ma'am and others also.
Sir, Salute You!!!!!!!!!!!!!!!!!
Thank you so much dear Avadhesh Kumar Patel for your appreciation. Wish you the best always.
@Aref Wazwaz thank you for the useful links. I take up another issue, I do not use advanced mathematical methods like machine learning and big data presented in your articles. I ask myself whether doctors working both in research centers and far from the centers can conduct independent research on their own clinical material while maintaining a high level of professionalism, in accordance with the applicable standards of EBM. The barrier is the methodology of statistical compilation of clinical data. So far, the research team consists of a statistician who, having professional knowledge, performs statistical analysis of the results by operating the statistical program through a screen interface. Finding the right professional can be difficult, especially in small settings. We set ourselves the goal of developing a new method addressed to a doctor-researcher, enabling the independent development of data while maintaining the quality and credibility of conclusions. In our method, we decide to use artificial intelligence (AI), creating an IT tool whose operation is modeled on the human thinking process - a statistician performing statistical analysis in the statistical program R.
dear @ Aref Wazwaz ,The argument for the usefulness of this AI system dedicated to clinical trials is that with the current medical EBM (Evidence Based Medicine) paradigm, each clinician using this program can carry out epidemiological proceedings without the knowledge and skills in the selection of statistical techniques and statistical programming. It would be impossible and completely unnecessary in the education of doctors.
Article ARTIFICIAL INTELLIGENCE IN THE SYSTEM OF STATISTICAL ANALYSIS
Article A retrieval system for the selection and statistical analysi...
Article A retrieval system for the selection and statistical analysi...
Please consinder the above links
This project is very interesting & important to the future development of biology and medicine. Automatized creation of hypothesis (see details in the paper below) has a very bright future in biology and medicine. Simultaneously, it possesses a great challenge to our current mathematical and computational tools from the following reasons.
Firstly, statistical methods are insufficient in discerning processes undergoing in very complex systems in most cases. Secondly, this can be overcome by a clever application of complexity measures that projecting a functioning complex system under consideration (body, organ, ecosystem, society, etc.) into a data stream (typically a biosignal), which is fed into statistical data.
Why is this approach favorable? Complexity measures are using the notion of entropy developed by Ludwig Boltzmann & Claude Shannon (see details in the paper) to distill the operational mode of the system under consideration. Statistical methods are often insufficient in doing so.
A direct application of statistical methods on the observed complex system do not allow classification of different modes of its behavior. Complexity measures processed by statistical methods gives a chance to AI and ML methods to discern!
Details are provided in the methodical paper:
https://www.researchgate.net/publication/340460356_Prediction_of_Medical_Drugs-Induced_Arrhythmias_Torsades_de_Pointes_Ventricular_Tachycardia_and_Ventricular_Fibrillation_on_Rabbit_Model_Up_to_One_Hour_Before_Their_Onset_Using_Computational_Method_Ba
Thank you Jiří Kroc for your appreciation and interesting voice in the discussion.
Our idea of automate analysis is to delegate the operation of the statistical package to a computer program.
This extends the competence of the doctor practicing medicine according to the principles of EBM, by the possibility of confronting the results of his own research on his patients with the knowledge resources (Cochrane library) and enriching the general medical knowledge.
Our method of automatic analysis especially belongs to the EBM methodology. It is particularly useful in small studies that can not employ a statistician in the research team without requiring the physician to learn statistical language, which is unnecessary and impossible for him. The method is mainly intended for medicine and social sciences, where knowledge of epidemiology is mandatory, and the method will be correctly applied.
Hanna Mielniczuk Thank you very much indeed for this wonderful and comprehensive article, wishing you all the best in your pioneer study.
- Badges
- Science topic