Martin S Kohn

US Patent:

8583586, Nov 12, 2013

Filed:

Jan 21, 2011

Appl. No.:

13/011632

Inventors:

Shahram Ebadollahi - White Plains NY, US
Jianying Hu - Bronx NY, US
Martin S. Kohn - East Hills NY, US
Noah Lee - New York NY, US
Robert K. Sorrentino - Rancho Palos Verdes CA, US
Jimeng Sun - White Plains NY, US
Fei Wang - San Jose CA, US

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06N 5/02

US Classification:

706 53, 706 20

Abstract:

Methods and systems for event pattern mining are shown that include representing longitudinal event data in a measurable geometric space as a temporal event matrix representation (TEMR) using spatial temporal shapes, wherein event data is organized into hierarchical categories of event type and performing temporal event pattern mining with a processor by locating visual event patterns among the spatial temporal shapes of said TEMR using a constraint sparse coding framework.

US Patent:

20110301965, Dec 8, 2011

Filed:

Jun 7, 2010

Appl. No.:

12/795106

Inventors:

RAYMOND R. HITNEY - BUCHANAN NY, US
MARTIN S. KOHN - EAST HILLS NY, US
ERIK T. MUELLER - CHEVY CHASE MD, US

Assignee:

INTERNATIONAL BUSINESS MACHINES CORPORATION - ARMONK NY

International Classification:

G06Q 50/00
G06Q 10/00

US Classification:

705 2

Abstract:

Current patients in an emergency department of a hospital are described according to their quantity, their triage classification levels, and their wait times to calculate a current patient backlog. A sum of weight-adjusted triage classification levels of all of the current patients is calculated. Current patient arrival rates in the emergency department are tracked to calculate a current change in patient arrival rates, which are compared with historical changes in patient arrival rates. A size of an imminent influx of arriving patients into the emergency department is then predicted based on the current patient backlog, the sum of weight-adjusted triage classification levels of patients currently in the emergency department, and the current change in patient arrival rates.

US Patent:

20110307264, Dec 15, 2011

Filed:

Jun 10, 2010

Appl. No.:

12/797888

Inventors:

RAYMOND R. HITNEY - BUCHANAN NY, US
MARTIN S. KOHN - EAST HILLS NY, US
ERIK T. MUELLER - CHEVY CHASE MD, US

Assignee:

INTERNATIONAL BUSINESS MACHINES CORPORATION - ARMONK NY

International Classification:

G06Q 50/00
G06Q 10/00

US Classification:

705 2

Abstract:

An initial triage level classification for a latest patient to arrive at an emergency department (ED) is received. Availability levels of resources needed to treat the latest patient are electronically collected, along with triage level classifications for all other patients currently in the ED. The initial triage level classification of the latest patient is adjusted upward or downward based on the availability levels of resources needed to treat the latest patient and based on the triage level classifications for the patients in the ED. The triage level classifications for all patients currently in the ED are summed up. If a sum of all triage level classifications exceeds a first predetermined threshold, other resources are reallocated in order to provide the resources needed to treat the latest patient to arrive at the ED. If the sum of all triage level classifications exceeds a second predetermined threshold, then a disaster plan is implemented.

US Patent:

20120109683, May 3, 2012

Filed:

Oct 27, 2010

Appl. No.:

12/913042

Inventors:

SHAHRAM EBADOLLAHI - White Plains NY, US
Jianying Hu - Bronx NY, US
Martin S. Kohn - East Hills NY, US
Jonathan D. Laserson - Menlo Park CA, US
Hani Neuvirth-Telem - Tel Aviv, IS
Lavi Shpigelman - Jerusalem, IS
Robert K. Sorrentino - Rancho Palos Verdes CA, US

Assignee:

INTERNATIONAL BUSINESS MACHINES CORPORATION - ARMONK NY

International Classification:

G06Q 50/00

US Classification:

705 3

Abstract:

A recommendation system and method includes extracting patient features for a current patient to generate representation of the current patient. The patient features for the current patient are compared to physician features of one or more physicians and patient-to-physician features of a group of patients from medically related records. Outcome measures associated with physicians are compared related to a current query. A future outcome for patient, physician pairs are predicted for the current patient based upon at least one predictive model constructed from the features and outcome measures to output.

US Patent:

20150006189, Jan 1, 2015

Filed:

Jul 1, 2013

Appl. No.:

13/932022

Inventors:

- Armonk NY, US
Jianying Hu - Bronx NY, US
Martin Steven Kohn - East Hills NY, US
Michal Ozery-Flato - Tel Aviv, IL
Michal Rosen-Zvi - Jerusalem, IL

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 19/00
A61B 5/00

US Classification:

705 2

Abstract:

A computer-implemented method and apparatus for assessing treatment adherence by patients, the method comprising: receiving a model providing statistical significance of patients' response to treatment, the model based on treatment assigned to the patients, wherein the patients are diagnosed with a disease; computing by the computerized device a p-value for a result received for a patient diagnosed with the disease and being treated by the treatment, by applying the model to at least one patient; and issuing an alert responsive to the p-value being indicative of the result being unexpected beyond a threshold.