System and method for predicting health condition of a patient

1. A method for utilizing sensor data to predict a health condition of a first patient via a combination of bio-sensors and supervised machine learning algorithms, said method comprising:

extracting, from a database server communicatively coupled to one or more processors, metadata pertaining to historical medical records of one or more second patients, the historical medical records including physiological parameters of the one or more second patients;

segregating the metadata into a first class and a second class, the first class representing a first portion of the one or more second patients that did not develop a medical condition during their hospital stay, the second class representing a second portion of the one or more second patients that developed a medical condition during their hospital stay;

extracting one or more selected words in the segregated metadata for each of the first class and the second class and determining a first feature vector, for the one or more second patients, based on a count of the selected one or more words in the segregated metadata;

determining a second feature vector, for the one or more second patients, based on the physiological parameters of the one or more second patients;

training one or more supervised machine learning algorithms using the first feature vector and the second feature vector;

obtaining, from one or more bio-sensors coupled to the processor, sensor data corresponding to one or more physiological parameters associated with said first patient;

analyzing, in real-time, the one or more physiological parameters of the first patient using the one or more supervised learning machines trained with the first feature vector and the second feature vector to identify an emerging complication for said first patient;

outputting the identified emerging complication in real-time; and

treating the identified emerging complication based on the analysis.

2. The method of claim 1 , further comprising:

extracting one or more headings from one or more medical records of said first patient based on one or more predefined rules, wherein each of said one or more headings corresponds to one or more medical specialties supported by a medical center where said first patient is observed; and

extracting one or more words from one or more phrases written under each of said extracted one or more headings, wherein said one or more phrases corresponds to documentation of said observation of said first patient by a medical attender,

wherein said one or more medical records comprises at least one of a nursing note and an investigative report.

3. The method of claim 2 , further comprising scanning, by an image capturing device, said one or more medical records associated with said first patient.

4. The method of claim 2 , further comprising determining, by an arithmetic logic unit, a first score for each of said one or more words under each of said extracted one or more headings based on a count of one or more words under said one or more headings in said historical medical records.

5. The method of claim 4 , further comprising ranking, by said one or more processors, said one or more words under each of said extracted one or more headings based on said first score.

6. The method of claim 5 , further comprising selecting, by said one or more processors, a pre-defined number of said one or more words from said ranked one or more words under each of said extracted one or more headings.

7. The method of claim 6 , further comprising determining, by said arithmetic logic unit, a third feature vector associated with said one or more medical records of the first patient based on said count of said selected one or more words in said one or more medical records of said first patient.

8. The method of claim 7 , further comprising determining, by said arithmetic logic unit, a fourth feature vector associated with said one or more physiological parameters of the first patient based on statistical parameters associated with each of said one or more physiological parameters of the first patient.

9. The method of claim 8 , wherein said one or more processors utilizes one or more supervised machine learning algorithms to predict said health condition of said first patient based on at least one of said third feature vector, said fourth feature vector, said historical medical records, and said one or more medical records of said first patient.