Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -4,14 +4,14 @@ from graphviz import Digraph
|
|
4 |
|
5 |
st.markdown("""
|
6 |
# Goals of Cognitive AI with Human Feedback (CAHF):
|
7 |
-
1. Use Models to predict outcomes
|
8 |
-
2. Use AI to predict conditions, disease,
|
9 |
-
3. Cognitive AI -
|
10 |
-
4. Reasoning cycles - "Recommended for You" reasoners - what type of person, classification of users, recommend what products
|
11 |
-
5. High Acuity Reasoners - Only make decisions on rules of what it can and cannot do within human feedback guidelines.
|
12 |
-
-Emphasis on explainability, transparency, removing administrative burden and protocolize what staff is doing.
|
13 |
-
-Vetted by SME's, adding value of judgement and training to pick up skills from human feedback
|
14 |
-
|
15 |
6. Non static multi agent cognitive approach - real time series - factors predictive of outcome.
|
16 |
7. Cognitive models take form of Ontology - for some type of computable set - relationships stored in Ontology can be ingested by reasoner
|
17 |
-Use models of world to build predictions and recommendations with answers that are cumulative with information we know
|
@@ -20,39 +20,39 @@ st.markdown("""
|
|
20 |
|
21 |
st.markdown("""
|
22 |
# 📚 Clinical Terminology and Ontologies for Medications and Conditions for Behavioral Health
|
23 |
-
1. 1️⃣ National Library of Medicine's RxNorm
|
24 |
- Standardized nomenclature for clinical drugs developed by NLM
|
25 |
- Provides links between drug names and related information such as ingredients, strengths, and dosages
|
26 |
-
- Data type: controlled vocabulary
|
27 |
-
- Access through NLM's RxNorm website
|
28 |
2. 2️⃣ Centers for Medicare and Medicaid Services' Healthcare Common Procedure Coding System (HCPCS):
|
29 |
-
- Coding system used to identify healthcare services, procedures, and supplies
|
30 |
-
- Includes codes for drugs, biologicals, and other items used in medical care
|
31 |
-
- Data type: coding system
|
32 |
-
- Access through CMS website
|
33 |
3. 3️⃣ Unified Medical Language System (UMLS):
|
34 |
- Set of files and software tools developed by NLM for integrating and mapping biomedical vocabularies
|
35 |
- Includes RxNorm and other drug vocabularies, as well as other terminologies used in medicine
|
36 |
-
- Data type: controlled vocabulary
|
37 |
- Access through UMLS Metathesaurus: https://www.nlm.nih.gov/research/umls/index.html
|
38 |
4. 4️⃣ PubMed:
|
39 |
-
- Database of biomedical literature maintained by the National Center for Biotechnology Information (NCBI)
|
40 |
-
- Includes information about drugs, including drug names, chemical structures, and pharmacological actions
|
41 |
-
- Data type: bibliographic database
|
42 |
-
- Access through PubMed website
|
43 |
5. 5️⃣ PubChem:
|
44 |
- Database of chemical substances maintained by NCBI
|
45 |
-
- Includes information about drugs, including chemical structures, properties, and activities
|
46 |
-
- Data type: chemical database
|
47 |
-
- Access through PubChem website
|
48 |
6. 6️⃣ Behavioral Health Code Terminology Sets:
|
49 |
- Code terminology sets specific to behavioral health
|
50 |
-
- Includes DSM published by American Psychiatric Association, ICD published by World Health Organization, and CPT published by American Medical Association
|
51 |
-
- Data type: coding system
|
52 |
-
- Access through respective organizations' websites
|
53 |
-
1. DSM
|
54 |
-
2. ICD
|
55 |
-
3. CPT
|
56 |
""")
|
57 |
|
58 |
st.markdown("""
|
|
|
4 |
|
5 |
st.markdown("""
|
6 |
# Goals of Cognitive AI with Human Feedback (CAHF):
|
7 |
+
1. Use Models to predict **outcomes**
|
8 |
+
2. Use AI to predict **conditions, disease, opportunities** using flavors of AI with **explainability**.
|
9 |
+
3. **Cognitive AI** - Mimics how humans reason through decision making processes.
|
10 |
+
4. **Reasoning cycles** - "Recommended for You" reasoners - what type of person, classification of users, recommend what products
|
11 |
+
5. **High Acuity Reasoners** - Only make decisions on rules of **what it can and cannot do within human feedback** guidelines.
|
12 |
+
-Emphasis on **explainability, transparency, removing administrative burden** and **protocolize** what staff is doing.
|
13 |
+
-Vetted by SME's, adding value of **judgement and training** to pick up **skills from human feedback**.
|
14 |
+
-**Alerts, Recommended Actions, and Clinical Terminology** per entity including LOINC, SNOMED, ICD10, RXNORM. SMILES, HCPCS and CPT codes,
|
15 |
6. Non static multi agent cognitive approach - real time series - factors predictive of outcome.
|
16 |
7. Cognitive models take form of Ontology - for some type of computable set - relationships stored in Ontology can be ingested by reasoner
|
17 |
-Use models of world to build predictions and recommendations with answers that are cumulative with information we know
|
|
|
20 |
|
21 |
st.markdown("""
|
22 |
# 📚 Clinical Terminology and Ontologies for Medications and Conditions for Behavioral Health
|
23 |
+
1. 1️⃣ National Library of Medicine's **RxNorm**:
|
24 |
- Standardized nomenclature for clinical drugs developed by NLM
|
25 |
- Provides links between drug names and related information such as ingredients, strengths, and dosages
|
26 |
+
- **Data type: controlled vocabulary**
|
27 |
+
- Access through **NLM's RxNorm website**: https://www.nlm.nih.gov/research/umls/rxnorm/index.html
|
28 |
2. 2️⃣ Centers for Medicare and Medicaid Services' Healthcare Common Procedure Coding System (HCPCS):
|
29 |
+
- Coding system used to identify healthcare **services, procedures, and supplies**
|
30 |
+
- Includes **codes for drugs, biologicals, and other items** used in medical care
|
31 |
+
- **Data type: coding system**
|
32 |
+
- Access through **CMS website**: https://www.cms.gov/Medicare/Coding/MedHCPCSGenInfo
|
33 |
3. 3️⃣ Unified Medical Language System (UMLS):
|
34 |
- Set of files and software tools developed by NLM for integrating and mapping biomedical vocabularies
|
35 |
- Includes RxNorm and other drug vocabularies, as well as other terminologies used in medicine
|
36 |
+
- **Data type: controlled vocabulary**
|
37 |
- Access through UMLS Metathesaurus: https://www.nlm.nih.gov/research/umls/index.html
|
38 |
4. 4️⃣ PubMed:
|
39 |
+
- Database of **biomedical literature** maintained by the National Center for Biotechnology Information (NCBI)
|
40 |
+
- Includes information about **drugs, including drug names, chemical structures, and pharmacological actions**
|
41 |
+
- **Data type: bibliographic database**
|
42 |
+
- Access through **PubMed website**: https://pubmed.ncbi.nlm.nih.gov/
|
43 |
5. 5️⃣ PubChem:
|
44 |
- Database of chemical substances maintained by NCBI
|
45 |
+
- Includes information about drugs, including **chemical structures, properties, and activities**
|
46 |
+
- **Data type: chemical database**
|
47 |
+
- Access through **PubChem website**: https://pubchem.ncbi.nlm.nih.gov/
|
48 |
6. 6️⃣ Behavioral Health Code Terminology Sets:
|
49 |
- Code terminology sets specific to behavioral health
|
50 |
+
- Includes **DSM** published by American Psychiatric Association, **ICD** published by World Health Organization, and **CPT** published by American Medical Association
|
51 |
+
- **Data type: coding system**
|
52 |
+
- Access through respective **organizations' websites**:
|
53 |
+
1. [DSM](https://www.psychiatry.org/psychiatrists/practice/dsm)
|
54 |
+
2. [ICD](https://www.who.int/standards/classifications/classification-of-diseases)
|
55 |
+
3. [CPT](https://www.ama-assn.org/practice-management/cpt/current-procedural-terminology-cpt)
|
56 |
""")
|
57 |
|
58 |
st.markdown("""
|